Add structural Health Connect export for Phoenix workouts by 9thLevelSoftware · Pull Request #516 · 9thLevelSoftware/Project-Phoenix-MP

9thLevelSoftware · 2026-06-07T20:27:52Z

Summary

Upgrade Android Health Connect to 1.2.0-alpha04 and export Phoenix workouts as one session with per-set ExerciseSegments.
Keep iOS on aggregate-only HealthKit writes, since the public write API does not support equivalent strength segments.
Add persisted-session/export mappers, repository accessors, historical backfill, and Integrations UI actions for retry permissions and sync previous workouts.

Testing

Passed :shared:testAndroidHostTest
Passed :shared:compileKotlinIosArm64
Passed :shared:verifyCommonMainVitruvianDatabaseMigration
Passed :shared:checkKotlinAbi
Passed :androidApp:assembleDebug
spotlessCheck still fails on a pre-existing unrelated formatting issue in OAuthRedirectActivity.kt

Copilot

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

gemini-code-assist

Code Review

This pull request refactors the health integration system to support rich workout data exports with set-level segments on Android and aggregate data on iOS, alongside a new backfill manager to sync previous workouts. The code review highlights several critical issues that must be addressed: compilation failures on Android due to the use of the non-existent ExerciseSegment.EXERCISE_SEGMENT_TYPE_WEIGHTLIFTING constant, a runtime crash caused by overlapping exercise segment times, a potential SQLite exception during backfill when querying more than 999 sessions, and overly fragile error handling that fails the entire backfill process if only a single workout fails to write.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

gemini-code-assist · 2026-06-07T20:29:42Z

+    private fun HealthWorkoutSegment.toHealthConnectSegment(): ExerciseSegment {
+        val sessionType = ExerciseSessionRecord.EXERCISE_TYPE_STRENGTH_TRAINING
+        val preferredType = segmentTypeForExercise(exerciseName)
+        val fallbackType = ExerciseSegment.EXERCISE_SEGMENT_TYPE_WEIGHTLIFTING


The constant ExerciseSegment.EXERCISE_SEGMENT_TYPE_WEIGHTLIFTING does not exist in the Android Health Connect SDK. Weightlifting is an exercise session type (ExerciseSessionRecord.EXERCISE_TYPE_WEIGHTLIFTING), not an individual segment type. Using this non-existent constant will cause a compilation failure. Please use ExerciseSegment.EXERCISE_SEGMENT_TYPE_UNKNOWN as the fallback type.

Suggested change

val fallbackType = ExerciseSegment.EXERCISE_SEGMENT_TYPE_WEIGHTLIFTING

val fallbackType = ExerciseSegment.EXERCISE_SEGMENT_TYPE_UNKNOWN

gemini-code-assist · 2026-06-07T20:29:42Z

+            "row" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_WEIGHTLIFTING
+            "pulldown" in normalized || "pull down" in normalized || "lat pull" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_WEIGHTLIFTING
+            "pull-up" in normalized || "pull up" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_PULL_UP
+            "lunge" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_LUNGE
+            "shoulder press" in normalized || "overhead press" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_SHOULDER_PRESS
+            "tricep" in normalized || "triceps" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_DOUBLE_ARM_TRICEPS_EXTENSION
+            else -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_WEIGHTLIFTING


As noted, ExerciseSegment.EXERCISE_SEGMENT_TYPE_WEIGHTLIFTING is not a valid segment type constant. Please map these generic strength exercises to ExerciseSegment.EXERCISE_SEGMENT_TYPE_UNKNOWN to prevent compilation errors.

Suggested change

"row" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_WEIGHTLIFTING

"pulldown" in normalized || "pull down" in normalized || "lat pull" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_WEIGHTLIFTING

"pull-up" in normalized || "pull up" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_PULL_UP

"lunge" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_LUNGE

"shoulder press" in normalized || "overhead press" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_SHOULDER_PRESS

"tricep" in normalized || "triceps" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_DOUBLE_ARM_TRICEPS_EXTENSION

else -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_WEIGHTLIFTING

"row" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_UNKNOWN

"pulldown" in normalized || "pull down" in normalized || "lat pull" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_UNKNOWN

"pull-up" in normalized || "pull up" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_PULL_UP

"lunge" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_LUNGE

"shoulder press" in normalized || "overhead press" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_SHOULDER_PRESS

"tricep" in normalized || "triceps" in normalized -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_DOUBLE_ARM_TRICEPS_EXTENSION

else -> ExerciseSegment.EXERCISE_SEGMENT_TYPE_UNKNOWN

gemini-code-assist · 2026-06-07T20:29:42Z

+    ): List<HealthWorkoutSegment> = sessions
+        .sortedBy { it.timestamp }
+        .flatMap { session ->
+            val completedSets = completedSetsBySessionId[session.id]
+                .orEmpty()
+                .sortedWith(compareBy<CompletedSet> { it.setNumber }.thenBy { it.completedAt })
+
+            if (completedSets.isNotEmpty()) {
+                completedSets.mapNotNull { completedSet ->
+                    buildSegment(session, completedSet)
+                }
+            } else {
+                buildSegment(session, completedSet = null)?.let(::listOf).orEmpty()
+            }
+        }


Android Health Connect strictly prohibits overlapping ExerciseSegments within an ExerciseSessionRecord. Because buildSegment calculates segment times independently using session.duration (the entire exercise duration), multiple sets within the same session will heavily overlap. This will cause a runtime IllegalArgumentException on insertion. Adjust the segment times sequentially to ensure they are strictly non-overlapping.

val rawSegments = sessions .sortedBy { it.timestamp } .flatMap { session -> val completedSets = completedSetsBySessionId[session.id] .orEmpty() .sortedWith(compareBy<CompletedSet> { it.setNumber }.thenBy { it.completedAt }) if (completedSets.isNotEmpty()) { completedSets.mapNotNull { completedSet -> buildSegment(session, completedSet) } } else { buildSegment(session, completedSet = null)?.let(::listOf).orEmpty() } } var lastEndTime = 0L return rawSegments.map { segment -> val adjustedStart = maxOf(segment.startTimeMs, lastEndTime) val adjustedEnd = maxOf(segment.endTimeMs, adjustedStart + 1000L) lastEndTime = adjustedEnd segment.copy(startTimeMs = adjustedStart, endTimeMs = adjustedEnd) }

gemini-code-assist · 2026-06-07T20:29:42Z

+        val completedSetsBySessionId = completedSetRepository
+            .getCompletedSetsForSessions(sessions.map { it.id })
+            .groupBy { it.sessionId }


Querying completed sets for all candidate sessions at once using an IN clause can trigger a SQLite exception (too many SQL variables) if the user has more than 999 candidate sessions. To prevent production crashes for long-time users, chunk the session IDs into batches of 500 before querying.

Suggested change

val completedSetsBySessionId = completedSetRepository

.getCompletedSetsForSessions(sessions.map { it.id })

.groupBy { it.sessionId }

val completedSetsBySessionId = sessions.map { it.id }

.chunked(500)

.flatMap { chunk -> completedSetRepository.getCompletedSetsForSessions(chunk) }

.groupBy { it.sessionId }

gemini-code-assist · 2026-06-07T20:29:42Z

+            skippedWorkouts = (workouts.size - written).coerceAtLeast(0),
+        )
+
+        return firstFailure?.let { Result.failure(it) } ?: Result.success(result)


Returning a failure for the entire backfill operation if a single workout fails to write is too fragile. If 99 out of 100 workouts succeed, the operation is still marked as a failure, which sets the overall integration status to ConnectionStatus.ERROR in IntegrationsViewModel. Consider failing only if all writes fail, and succeeding otherwise.

return if (written == 0 && workouts.isNotEmpty()) { Result.failure(firstFailure ?: IllegalStateException("All backfill writes failed")) } else { Result.success(result) }

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: f9c728ce5d

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector · 2026-06-07T20:32:29Z

+        workouts.forEach { workout ->
+            healthIntegration.writeHealthWorkout(workout)


Avoid re-exporting already synced health workouts

On Apple Health, pressing “Sync previous” after workouts have already been auto-pushed, or pressing it a second time, runs this loop over the same candidates and saves them again; the new backfill path does not filter by an export marker/cutoff or query existing health records, and the iOS writer just calls saveObject with metadata, which does not make HKExternalUUID unique. This leaves duplicate workouts in Health for normal connected users who use the backfill action.

Useful? React with 👍 / 👎.

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: f1a20e4859

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector · 2026-06-07T20:56:35Z

+                )
+                _uiState.value = _uiState.value.copy(errorMessage = "Health sync failed: ${e.message}")
+            } finally {
+                setOperationLoading(provider, "health_backfill", false)


Preserve health sync errors after clearing loading state

When the health backfill fails, the failure branch sets errorMessage, but the finally block immediately calls setOperationLoading(..., false), and that helper always rewrites errorMessage = null. In the sync-previous error path this can clear the failure before the screen's LaunchedEffect(uiState.errorMessage) has a chance to show the snackbar, leaving users with no visible feedback even though the provider was moved to ERROR.

Useful? React with 👍 / 👎.

Resolve merge conflicts with weight recommendation (PR #499), timed-set countdown cues (PR #505), and Health Connect export (PR #516) by keeping both deload modifiers and the new main features. https://claude.ai/code/session_01MBWwVaUrnXjzZxYKKnn33i

Add structural Health Connect export for Phoenix workouts

f9c728c

Copilot AI review requested due to automatic review settings June 7, 2026 20:27

Copilot AI reviewed Jun 7, 2026

gemini-code-assist Bot reviewed Jun 7, 2026

View reviewed changes

chatgpt-codex-connector Bot reviewed Jun 7, 2026

View reviewed changes

9thLevelSoftware linked an issue Jun 7, 2026 that may be closed by this pull request

[Feature] Google Health Connect – structural logging for complex strength training and routines #513

Closed

Add health export dedupe and backfill hardening

f1a20e4

chatgpt-codex-connector Bot reviewed Jun 7, 2026

View reviewed changes

9thLevelSoftware merged commit 615dd7d into main Jun 7, 2026
10 checks passed

9thLevelSoftware deleted the feat/513-structural-logging branch June 7, 2026 23:07

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Add structural Health Connect export for Phoenix workouts#516

Add structural Health Connect export for Phoenix workouts#516
9thLevelSoftware merged 2 commits into
mainfrom
feat/513-structural-logging

9thLevelSoftware commented Jun 7, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

gemini-code-assist Bot Jun 7, 2026

Uh oh!

gemini-code-assist Bot Jun 7, 2026

Uh oh!

gemini-code-assist Bot Jun 7, 2026

Uh oh!

gemini-code-assist Bot Jun 7, 2026

Uh oh!

gemini-code-assist Bot Jun 7, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

chatgpt-codex-connector Bot Jun 7, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

chatgpt-codex-connector Bot Jun 7, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

	val fallbackType = ExerciseSegment.EXERCISE_SEGMENT_TYPE_WEIGHTLIFTING
	val fallbackType = ExerciseSegment.EXERCISE_SEGMENT_TYPE_UNKNOWN

		workouts.forEach { workout ->
		healthIntegration.writeHealthWorkout(workout)

Uh oh!

Conversation

9thLevelSoftware commented Jun 7, 2026

Summary

Testing

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist Bot Jun 7, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Jun 7, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Jun 7, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Jun 7, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Jun 7, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot Jun 7, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot Jun 7, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants