diff --git a/app/lib/core/patch_capture.dart b/app/lib/core/patch_capture.dart index c0bcf80..ae2ff7e 100644 --- a/app/lib/core/patch_capture.dart +++ b/app/lib/core/patch_capture.dart @@ -1,13 +1,22 @@ import 'dart:async'; +import 'dart:convert'; import 'dart:io'; +import 'package:crypto/crypto.dart'; import 'package:dart_arena/runner/subprocess_environment.dart'; +const patchBaselineRef = 'arena_baseline'; + class PatchCaptureResult { - const PatchCaptureResult({required this.patch, required this.status}); + const PatchCaptureResult({ + required this.patch, + required this.status, + required this.patchSha256, + }); final String patch; final String status; + final String patchSha256; bool get hasMeaningfulDiff => patch.trim().isNotEmpty; } @@ -27,19 +36,24 @@ class PatchCapture { final Duration timeout; final int maxOutputChars; - Future capture(Directory workspace) async { + Future capture( + Directory workspace, { + String baselineRef = patchBaselineRef, + }) async { const addIntentArgs = ['add', '-N', '.']; final intentToAdd = await _runGit(workspace, addIntentArgs); _checkGitResult(intentToAdd, addIntentArgs); const statusArgs = ['status', '--porcelain']; - const diffArgs = ['diff', '--binary']; + final diffArgs = ['diff', baselineRef, '--binary']; final status = await _runGit(workspace, statusArgs); final diff = await _runGit(workspace, diffArgs); _checkGitResult(status, statusArgs); _checkGitResult(diff, diffArgs); + final patch = diff.stdout.toString(); return PatchCaptureResult( - patch: diff.stdout.toString(), + patch: patch, status: status.stdout.toString(), + patchSha256: sha256.convert(utf8.encode(patch)).toString(), ); } diff --git a/app/lib/core/task_run_result.dart b/app/lib/core/task_run_result.dart index 14e5b27..66508e7 100644 --- a/app/lib/core/task_run_result.dart +++ b/app/lib/core/task_run_result.dart @@ -21,6 +21,7 @@ class TaskRunResult extends Equatable { this.patchText, this.trajectoryLogPath, this.planId, + this.provenance = const {}, }); final String runId; @@ -40,6 +41,7 @@ class TaskRunResult extends Equatable { final String? patchText; final String? trajectoryLogPath; final String? planId; + final Map provenance; @override List get props => [ @@ -60,5 +62,6 @@ class TaskRunResult extends Equatable { patchText, trajectoryLogPath, planId, + provenance, ]; } diff --git a/app/lib/export/leaderboard_exporter.dart b/app/lib/export/leaderboard_exporter.dart index 655edc6..a4b5594 100644 --- a/app/lib/export/leaderboard_exporter.dart +++ b/app/lib/export/leaderboard_exporter.dart @@ -115,10 +115,12 @@ Future> buildLeaderboardExport( evaluationsByTaskRunId, modelConfigIndex, ); + final taskBundleDigests = _corpusManifestTaskBundleDigests(corpusManifest); final tasks = _buildTaskRows( selected.taskRuns, warnings, evaluationsByTaskRunId, + taskBundleDigests, ); final taskModelCells = _buildTaskModelCells( selected.taskRuns, @@ -427,6 +429,7 @@ List> _buildTaskRows( List taskRuns, List warnings, Map> evaluationsByTaskRunId, + Map taskBundleDigests, ) { final groups = >{}; for (final taskRun in taskRuns) { @@ -468,6 +471,12 @@ List> _buildTaskRows( rows.add({ 'taskId': group.first.taskId, 'taskVersion': group.first.taskVersion, + if (taskBundleDigests[_taskManifestKey( + group.first.taskId, + group.first.taskVersion, + )] + case final taskBundleDigest?) + 'taskBundleDigest': taskBundleDigest, 'benchmarkTrack': group.first.benchmarkTrack, 'trialCount': sampleCount, 'sampleCount': sampleCount, @@ -503,6 +512,28 @@ List> _buildTaskRows( return rows; } +Map _corpusManifestTaskBundleDigests( + Map? corpusManifest, +) { + if (corpusManifest == null) return const {}; + final digests = {}; + for (final entry in _objectList(corpusManifest['tasks'])) { + final taskId = entry['taskId']; + final taskVersion = entry['taskVersion']; + final taskBundleDigest = entry['taskBundleDigest']; + if (taskId is! String || + taskVersion is! int || + taskBundleDigest is! String) { + continue; + } + digests[_taskManifestKey(taskId, taskVersion)] = taskBundleDigest; + } + return digests; +} + +String _taskManifestKey(String taskId, int taskVersion) => + '$taskId@v$taskVersion'; + List> _buildTaskModelCells( List taskRuns, Map> evaluationsByTaskRunId, diff --git a/app/lib/export/release_report.dart b/app/lib/export/release_report.dart index 511abe4..d93711b 100644 --- a/app/lib/export/release_report.dart +++ b/app/lib/export/release_report.dart @@ -1,6 +1,7 @@ import 'dart:collection'; import 'package:dart_arena/analytics/result_primitives.dart'; +import 'package:dart_arena/core/task_bundle_digest.dart'; import 'package:dart_arena/core/model_identity.dart'; const _standardBundleFilePaths = [ @@ -219,6 +220,12 @@ Map buildReleaseReport({ 'snapshot the corpus before an official release.', ); } + _validateFrozenCorpusManifest( + selectedTasks: selectedTasks, + corpusManifestDigest: corpusManifestDigest, + taskRows: taskRows, + blockers: blockers, + ); if (evaluatorSchemaVersion <= 0) { blockers.add( 'Leaderboard benchmark evaluator schema version metadata is missing.', @@ -335,6 +342,7 @@ Map buildReleaseReport({ final provenance = _provenanceSummary( runIds: runIds, runProvenanceById: runProvenanceById, + taskBundleDigestEvidence: taskBundleDigestEvidence, blockers: blockers, ); if (runProvenanceById != null) { @@ -7890,6 +7898,73 @@ Map _taskRef(Map report) => { String _taskKey(Map report) => '${report['taskId']}@v${report['taskVersion']}'; +void _validateFrozenCorpusManifest({ + required Object? selectedTasks, + required String? corpusManifestDigest, + required List> taskRows, + required Set blockers, +}) { + if (selectedTasks is! List || corpusManifestDigest == null) return; + final entries = []; + final selectedTaskKeys = {}; + var valid = true; + for (final selectedTask in selectedTasks) { + final entry = _objectMap(selectedTask); + final taskId = _nonEmptyString(entry['taskId']); + final taskVersion = entry['taskVersion']; + final taskBundleDigest = _nonEmptyString(entry['taskBundleDigest']); + if (taskId == null || + taskVersion is! int || + taskBundleDigest == null || + !_sha256DigestPattern.hasMatch(taskBundleDigest)) { + valid = false; + continue; + } + final key = '$taskId@v$taskVersion'; + if (!selectedTaskKeys.add(key)) valid = false; + entries.add( + CorpusManifestEntry( + taskId: taskId, + taskVersion: taskVersion, + taskBundleDigest: taskBundleDigest, + ), + ); + } + final taskRowsByKey = >{}; + for (final taskRow in taskRows) { + final taskId = _nonEmptyString(taskRow['taskId']); + final taskVersion = taskRow['taskVersion']; + if (taskId == null || taskVersion is! int) { + valid = false; + continue; + } + final key = '$taskId@v$taskVersion'; + if (taskRowsByKey.containsKey(key)) { + valid = false; + continue; + } + taskRowsByKey[key] = taskRow; + } + if (selectedTaskKeys.length != taskRowsByKey.length) valid = false; + for (final entry in entries) { + final row = taskRowsByKey['${entry.taskId}@v${entry.taskVersion}']; + if (row == null || row['taskBundleDigest'] != entry.taskBundleDigest) { + valid = false; + } + } + if (!valid) { + blockers.add( + 'Leaderboard frozen corpus manifest entries do not match leaderboard tasks.', + ); + } + if (entries.length != selectedTasks.length || + corpusManifestDigestSha256(entries) != corpusManifestDigest) { + blockers.add( + 'Leaderboard frozen corpus manifest digest does not match its entries.', + ); + } +} + Map _publicTaskRef(Map task) => { 'taskId': task['taskId'], 'taskVersion': task['taskVersion'], @@ -7916,6 +7991,7 @@ bool? _boolField( Map _provenanceSummary({ required List runIds, required Map>? runProvenanceById, + required List> taskBundleDigestEvidence, required Set blockers, }) { if (runIds.isNotEmpty && runProvenanceById == null) { @@ -7930,6 +8006,18 @@ Map _provenanceSummary({ var sdkVersionRunCount = 0; var dependencySnapshotRunCount = 0; var pricingRegistryRunCount = 0; + var resultProvenanceCount = 0; + var cleanReplayResultCount = 0; + final gradingModeCounts = SplayTreeMap(); + var hiddenFixtureIsolationAssertedResultCount = 0; + var hiddenFixtureIsolationLeakResultCount = 0; + var hiddenVerifierDigestMatchedResultCount = 0; + final currentHiddenVerifierDigestsByTaskKey = { + for (final evidence in taskBundleDigestEvidence) + if (_taskQaReportKey(evidence) case final key?) + if (evidence.containsKey('hiddenVerifierDigests')) + key: _objectMap(evidence['hiddenVerifierDigests']), + }; for (final runId in runIds) { final provenance = runProvenanceById?[runId]; if (runProvenanceById != null && provenance == null) { @@ -7956,6 +8044,95 @@ Map _provenanceSummary({ final pricingRegistryStatus = provenance == null ? 'missing' : _pricingRegistryStatus(provenance); + final resultProvenance = provenance == null + ? const >[] + : _objectMaps(provenance['resultProvenance']); + final expectedResultCount = provenance == null + ? 0 + : _objectMaps(provenance['combos']).length; + if (provenance != null && + (provenance['resultProvenance'] is! List || + resultProvenance.length != expectedResultCount)) { + blockers.add( + 'Run $runId is missing clean-replay result provenance for some results.', + ); + } + var runCleanReplayResultCount = 0; + var runHiddenFixtureIsolationAssertedResultCount = 0; + var runHiddenFixtureIsolationLeakResultCount = 0; + for (final result in resultProvenance) { + resultProvenanceCount++; + final gradingMode = result['gradingMode']; + final gradingModeKey = gradingMode is String && gradingMode.isNotEmpty + ? gradingMode + : 'missing'; + gradingModeCounts[gradingModeKey] = + (gradingModeCounts[gradingModeKey] ?? 0) + 1; + + final benchmarkTrack = result['benchmarkTrack']; + if (benchmarkTrack == 'codegen') { + continue; + } + if (benchmarkTrack != 'agentic') { + blockers.add( + 'Result provenance has a missing or unrecognized benchmark track.', + ); + continue; + } + + if (result['gradingMode'] == 'clean_replay') { + cleanReplayResultCount++; + runCleanReplayResultCount++; + } else { + blockers.add( + 'Result was graded in the agent workspace, not a clean replay baseline.', + ); + } + + final hiddenFixtureIsolation = _objectMap( + result['hiddenFixtureIsolation'], + ); + final leakedPaths = _stringList(hiddenFixtureIsolation['leakedPaths']); + if (hiddenFixtureIsolation['asserted'] == true) { + hiddenFixtureIsolationAssertedResultCount++; + runHiddenFixtureIsolationAssertedResultCount++; + } else { + blockers.add( + 'Result is missing hidden verifier fixture isolation provenance.', + ); + } + if (leakedPaths.isNotEmpty) { + hiddenFixtureIsolationLeakResultCount++; + runHiddenFixtureIsolationLeakResultCount++; + blockers.add( + 'Hidden verifier fixtures were readable from the agent workspace.', + ); + } + + final taskKey = _resultProvenanceTaskKey(result); + final storedHiddenVerifierDigests = _objectMap( + result['hiddenVerifierDigests'], + ); + if (taskKey == null) { + blockers.add( + 'Result is missing task identity for hidden verifier digest verification.', + ); + } else if (!currentHiddenVerifierDigestsByTaskKey.containsKey(taskKey)) { + blockers.add( + 'Could not recompute hidden verifier digests from the live task ' + 'bundle for a graded result.', + ); + } else if (_stringMapEquals( + storedHiddenVerifierDigests, + currentHiddenVerifierDigestsByTaskKey[taskKey], + )) { + hiddenVerifierDigestMatchedResultCount++; + } else { + blockers.add( + 'Hidden verifier digests drifted from the corpus since the run.', + ); + } + } if (provenance != null) { if (sandboxStatus['status'] == 'enforced') { sandboxEnforcedRunCount++; @@ -8017,11 +8194,19 @@ Map _provenanceSummary({ 'sdkVersionStatus': sdkVersionStatus, 'dependencySnapshotStatus': dependencySnapshotStatus, 'pricingRegistryStatus': pricingRegistryStatus, + 'resultProvenanceCount': resultProvenance.length, + 'gradingModeCounts': _gradingModeCounts(resultProvenance), + 'cleanReplayResultCount': runCleanReplayResultCount, + 'hiddenFixtureIsolationAssertedResultCount': + runHiddenFixtureIsolationAssertedResultCount, + 'hiddenFixtureIsolationLeakResultCount': + runHiddenFixtureIsolationLeakResultCount, if (provenance != null) 'provenance': _sanitize(provenance), }); } return { + 'schemaVersion': 2, 'requiredRunIds': runIds, 'embeddedRunCount': runs.where((run) => run['status'] == 'present').length, 'sandboxEnforcedRunCount': sandboxEnforcedRunCount, @@ -8031,10 +8216,52 @@ Map _provenanceSummary({ 'sdkVersionRunCount': sdkVersionRunCount, 'dependencySnapshotRunCount': dependencySnapshotRunCount, 'pricingRegistryRunCount': pricingRegistryRunCount, + 'resultProvenanceCount': resultProvenanceCount, + 'cleanReplayResultCount': cleanReplayResultCount, + 'gradingModeCounts': gradingModeCounts, + 'hiddenFixtureIsolationAssertedResultCount': + hiddenFixtureIsolationAssertedResultCount, + 'hiddenFixtureIsolationLeakResultCount': + hiddenFixtureIsolationLeakResultCount, + 'hiddenVerifierDigestMatchedResultCount': + hiddenVerifierDigestMatchedResultCount, 'runs': runs, }; } +bool _stringMapEquals( + Map actual, + Map? expected, +) { + if (expected == null || actual.length != expected.length) return false; + for (final entry in expected.entries) { + if (actual[entry.key] != entry.value) return false; + } + return true; +} + +Map _gradingModeCounts( + Iterable> resultProvenance, +) { + final counts = SplayTreeMap(); + for (final result in resultProvenance) { + final gradingMode = result['gradingMode']; + final key = gradingMode is String && gradingMode.isNotEmpty + ? gradingMode + : 'missing'; + counts[key] = (counts[key] ?? 0) + 1; + } + return counts; +} + +String? _resultProvenanceTaskKey(Map result) { + final benchmarkTrack = result['benchmarkTrack']; + return _taskQaReportKey({ + ...result, + if (benchmarkTrack is String) 'track': benchmarkTrack, + }); +} + Map _generatedCodeSandboxStatus( Map provenance, ) { diff --git a/app/lib/export/release_report_cli_runner.dart b/app/lib/export/release_report_cli_runner.dart index 17d3ced..4cb85ca 100644 --- a/app/lib/export/release_report_cli_runner.dart +++ b/app/lib/export/release_report_cli_runner.dart @@ -2,9 +2,11 @@ import 'dart:convert'; import 'dart:io'; import 'package:dart_arena/core/task_bundle_digest.dart'; +import 'package:dart_arena/core/task_integrity.dart'; import 'package:dart_arena/export/leaderboard_cli_runner.dart'; import 'package:dart_arena/export/release_report.dart'; import 'package:dart_arena/storage/database.dart'; +import 'package:dart_arena/tasks/file_backed/file_backed_task.dart'; import 'package:crypto/crypto.dart'; import 'package:path/path.dart' as p; @@ -296,9 +298,15 @@ Future> _taskBundleDigestEvidence( }; } try { + final task = await FileBackedTask.load(bundleDirectory); + await task.ensureLoaded(); return { ...evidence, 'taskBundleDigest': await taskBundleDigestSha256(bundleDirectory), + 'hiddenVerifierDigests': { + for (final entry in hiddenVerifierDigests(task).entries) + entry.key: entry.value, + }, }; } on Object { return { diff --git a/app/lib/headless/headless_benchmark_runner.dart b/app/lib/headless/headless_benchmark_runner.dart index ef8279d..1508443 100644 --- a/app/lib/headless/headless_benchmark_runner.dart +++ b/app/lib/headless/headless_benchmark_runner.dart @@ -253,7 +253,12 @@ class HeadlessBenchmarkRunner { await config.runDao.updateRunProvenance(config.runId, provenanceJson); cancellation.throwIfCancelled(); - await _runCombos(config, plannedCombos, cancellation); + final results = await _runCombos(config, plannedCombos, cancellation); + cancellation.throwIfCancelled(); + await config.runDao.updateRunProvenance( + config.runId, + appendResultProvenance(provenanceJson, results), + ); cancellation.throwIfCancelled(); await config.runDao.finishRun(config.runId, config.now()); cancellation.throwIfCancelled(); @@ -352,7 +357,7 @@ class HeadlessBenchmarkRunner { return combos; } - Future _runCombos( + Future> _runCombos( HeadlessBenchmarkConfig config, List<_HeadlessCombo> combos, _HeadlessRunCancellation cancellation, @@ -373,6 +378,7 @@ class HeadlessBenchmarkRunner { for (final harness in config.agentHarnesses) harness.id: harness, }; final failures = <_HeadlessComboFailure>[]; + final results = []; var nextIndex = 0; final workerCount = config.maxConcurrency.clamp(1, 8); @@ -394,6 +400,7 @@ class HeadlessBenchmarkRunner { ); cancellation.throwIfCancelled(); await config.runDao.persistTaskRun(result); + results.add(result); cancellation.throwIfCancelled(); } catch (error, stackTrace) { cancellation.throwIfCancelled(); @@ -418,6 +425,7 @@ class HeadlessBenchmarkRunner { failures.sort((a, b) => a.index.compareTo(b.index)); throw StateError(_failedComboMessage(failures)); } + return results; } Future _runCombo({ diff --git a/app/lib/runner/agentic_run_orchestrator.dart b/app/lib/runner/agentic_run_orchestrator.dart index 5eeb491..8da0a16 100644 --- a/app/lib/runner/agentic_run_orchestrator.dart +++ b/app/lib/runner/agentic_run_orchestrator.dart @@ -8,10 +8,12 @@ import 'package:dart_arena/core/evaluation_context.dart'; import 'package:dart_arena/core/evaluation_result.dart'; import 'package:dart_arena/core/evaluator_blocking.dart'; import 'package:dart_arena/core/evaluator_config.dart'; +import 'package:dart_arena/core/task_integrity.dart'; import 'package:dart_arena/core/model_response.dart'; import 'package:dart_arena/core/patch_capture.dart'; import 'package:dart_arena/core/scoring.dart'; import 'package:dart_arena/core/task_run_result.dart'; +import 'package:dart_arena/core/workspace_path.dart'; import 'package:dart_arena/evaluators/evaluator.dart'; import 'package:dart_arena/runner/evaluator_resource_limits.dart'; import 'package:dart_arena/runner/generated_code_sandbox.dart'; @@ -101,8 +103,9 @@ class AgenticRunOrchestrator { error: initialPrep.stderr, ); } + final String patchBaselineSha; try { - await workdirManager.resetPatchBaseline(workspace); + patchBaselineSha = await workdirManager.resetPatchBaseline(workspace); } on Object catch (e) { return _environmentFailureResult( runId: runId, @@ -149,7 +152,10 @@ class AgenticRunOrchestrator { PatchCaptureResult? capturedPatch; EvaluationResult? patchFailure; try { - capturedPatch = await patchCapture.capture(workspace); + capturedPatch = await patchCapture.capture( + workspace, + baselineRef: patchBaselineSha, + ); } on Object catch (e) { patchFailure = EvaluationResult( evaluatorId: 'agent_patch', @@ -160,6 +166,59 @@ class AgenticRunOrchestrator { ); } + late final Map hiddenFixtureIsolation; + try { + hiddenFixtureIsolation = await _hiddenFixtureIsolation(task, workspace); + } on Object catch (e) { + return _environmentFailureResult( + runId: runId, + providerId: providerId, + modelId: modelId, + task: task, + trialIndex: trialIndex, + planId: planId, + harnessId: harness.id, + evaluatorConfig: evaluatorConfig, + phase: 'workspace_isolation', + rationale: 'workspace isolation evidence failed', + error: e, + ); + } + final resultProvenance = { + 'gradingMode': 'replay_failed', + 'patchApplied': false, + 'patchSha256': capturedPatch?.patchSha256, + 'hiddenFixtureIsolation': hiddenFixtureIsolation, + 'hiddenVerifierDigests': hiddenVerifierDigests(task), + }; + + late final Directory gradingWorkspace; + try { + gradingWorkspace = await workdirManager.createAgenticGradingWorkdir( + runId: runId, + providerId: providerId, + modelId: modelId, + taskId: task.id, + workspace: task.workspace, + trialIndex: trialIndex, + ); + } on Object catch (e) { + return _environmentFailureResult( + runId: runId, + providerId: providerId, + modelId: modelId, + task: task, + trialIndex: trialIndex, + planId: planId, + harnessId: harness.id, + evaluatorConfig: evaluatorConfig, + phase: 'grading_workspace', + rationale: 'grading workspace preparation failed', + error: e, + provenance: resultProvenance, + ); + } + final patchText = capturedPatch == null ? null : _boundedPatch(capturedPatch.patch); @@ -175,30 +234,55 @@ class AgenticRunOrchestrator { if (patchFailure != null) patchFailure, ]; - cancellationCheck?.call(); - final gradingPrep = await workdirManager.prepare( - workspace, - isFlutter: task.isFlutter, - allowInternet: task.allowInternet, - remainingTimeout: remainingTimeout, - cancellationCheck: cancellationCheck, - cancellationSignal: cancellationSignal, - generatedCodeSandbox: generatedCodeSandbox, - maxCpuCores: task.effectiveResourceLimits.cpus, - ); cancellationCheck?.call(); final evaluators = applyTaskResourceLimitsToEvaluators( task.evaluatorsFor(evaluatorConfig), task, ); - if (gradingPrep is PrepareFailed) { + + PrepareFailed? gradingFailure; + var gradingFailurePhase = 'grading_prepare'; + if (capturedPatch == null) { + gradingFailure = const PrepareFailed('patch capture failed'); + gradingFailurePhase = 'patch_capture'; + } else { + try { + await workdirManager.applyCapturedPatch( + gradingWorkspace, + capturedPatch.patch, + ); + resultProvenance['patchApplied'] = capturedPatch.hasMeaningfulDiff; + } on Object catch (e) { + gradingFailure = PrepareFailed(e.toString()); + gradingFailurePhase = 'grading_patch_apply'; + } + if (gradingFailure == null) { + cancellationCheck?.call(); + final gradingPrep = await workdirManager.prepare( + gradingWorkspace, + isFlutter: task.isFlutter, + allowInternet: task.allowInternet, + remainingTimeout: remainingTimeout, + cancellationCheck: cancellationCheck, + cancellationSignal: cancellationSignal, + generatedCodeSandbox: generatedCodeSandbox, + maxCpuCores: task.effectiveResourceLimits.cpus, + ); + cancellationCheck?.call(); + if (gradingPrep is PrepareFailed) { + gradingFailure = gradingPrep; + } + } + } + if (gradingFailure != null) { _addPrepareFailureEvaluations( evaluations: evaluations, evaluators: evaluators, - failure: gradingPrep, - phase: 'grading_prepare', + failure: gradingFailure, + phase: gradingFailurePhase, ); } else { + resultProvenance['gradingMode'] = 'clean_replay'; for (final evaluator in evaluators) { final blocked = blockedEvaluationFor( evaluatorId: evaluator.id, @@ -211,7 +295,7 @@ class AgenticRunOrchestrator { evaluations.add( await evaluator.evaluate( EvaluationContext( - workDir: workspace, + workDir: gradingWorkspace, response: response, task: task, previousResults: evaluations, @@ -249,6 +333,7 @@ class AgenticRunOrchestrator { patchText: patchText, trajectoryLogPath: agentResult.trajectoryLogPath, planId: planId, + provenance: resultProvenance, ); } @@ -283,6 +368,7 @@ class AgenticRunOrchestrator { required String? harnessId, required String rationale, required Object error, + Map provenance = const {}, }) { final response = ModelResponse( rawText: error.toString(), @@ -320,6 +406,7 @@ class AgenticRunOrchestrator { primaryPass: primitives.primaryPass, failureTag: primitives.failureTag, planId: planId, + provenance: provenance, ); } @@ -335,6 +422,7 @@ class AgenticRunOrchestrator { required String phase, required String rationale, required Object error, + Map provenance = const {}, }) { final response = ModelResponse( rawText: error.toString(), @@ -384,9 +472,33 @@ class AgenticRunOrchestrator { primaryPass: primitives.primaryPass, failureTag: primitives.failureTag, planId: planId, + provenance: provenance, ); } + Future> _hiddenFixtureIsolation( + BenchmarkTask task, + Directory workspace, + ) async { + final leakedPaths = {}; + for (final verifier in task.hiddenVerifiers) { + final paths = {verifier.testPath, ...verifier.files.keys}; + for (final path in paths) { + try { + final file = resolveWorkspaceFile(workspace, path); + final handle = await file.open(mode: FileMode.read); + await handle.close(); + leakedPaths.add(path); + } on FileSystemException { + continue; + } on ArgumentError { + continue; + } + } + } + return {'asserted': true, 'leakedPaths': leakedPaths.toList()..sort()}; + } + void _addPrepareFailureEvaluations({ required List evaluations, required List evaluators, diff --git a/app/lib/runner/run_provenance.dart b/app/lib/runner/run_provenance.dart index 00dabd5..8f79ae5 100644 --- a/app/lib/runner/run_provenance.dart +++ b/app/lib/runner/run_provenance.dart @@ -10,6 +10,7 @@ import 'package:dart_arena/core/evaluator_config.dart'; import 'package:dart_arena/core/model_identity.dart'; import 'package:dart_arena/core/scoring.dart'; import 'package:dart_arena/core/task_integrity.dart'; +import 'package:dart_arena/core/task_run_result.dart'; import 'package:dart_arena/providers/model_provider.dart'; import 'package:dart_arena/runner/resource_enforcement_policy.dart'; import 'package:dart_arena/runner/subprocess_environment.dart'; @@ -305,6 +306,44 @@ Future buildRunProvenanceJson({ return const JsonEncoder.withIndent(' ').convert(json); } +String appendResultProvenance( + String provenanceJson, + Iterable results, +) { + final decoded = jsonDecode(provenanceJson); + if (decoded is! Map) { + throw const FormatException('run provenance must be a JSON object'); + } + final resultProvenance = + [ + for (final result in results) + { + 'taskId': result.taskId, + 'taskVersion': result.taskVersion, + 'providerId': result.providerId, + 'modelId': result.modelId, + 'trialIndex': result.trialIndex, + 'benchmarkTrack': result.benchmarkTrack, + ...result.provenance, + }, + ]..sort((a, b) { + final task = (a['taskId']! as String).compareTo(b['taskId']! as String); + if (task != 0) return task; + final provider = (a['providerId']! as String).compareTo( + b['providerId']! as String, + ); + if (provider != 0) return provider; + final model = (a['modelId']! as String).compareTo( + b['modelId']! as String, + ); + if (model != 0) return model; + return (a['trialIndex']! as int).compareTo(b['trialIndex']! as int); + }); + return const JsonEncoder.withIndent( + ' ', + ).convert({...decoded, 'resultProvenance': resultProvenance}); +} + Map _taskJson(BenchmarkTask task) { final timeout = task.timeout; return { diff --git a/app/lib/runner/workdir_manager.dart b/app/lib/runner/workdir_manager.dart index 4222e64..72aa068 100644 --- a/app/lib/runner/workdir_manager.dart +++ b/app/lib/runner/workdir_manager.dart @@ -3,6 +3,7 @@ import 'dart:convert'; import 'dart:io'; import 'package:crypto/crypto.dart'; +import 'package:dart_arena/core/patch_capture.dart'; import 'package:dart_arena/core/path_safety.dart'; import 'package:dart_arena/core/task_workspace.dart'; import 'package:dart_arena/core/workspace_path.dart'; @@ -163,22 +164,63 @@ class WorkdirManager { taskPath, ), ); - await _recreateCleanRunDirectory(dir); + return _assembleAgenticWorkspace(dir, workspace); + } - final fixtureRootPath = workspace.fixtureRootPath; - if (fixtureRootPath != null) { - await _copyFixtureRoot(Directory(fixtureRootPath), dir); - } + Future createAgenticGradingWorkdir({ + required String runId, + required String providerId, + required String modelId, + required String taskId, + required TaskWorkspace workspace, + int trialIndex = 0, + }) { + final taskPath = p.join( + _workdirPathSegment(taskId), + 'trial_${trialIndex}_grading', + ); + final dir = Directory( + p.join( + root.path, + 'runs', + _workdirPathSegment(runId), + _workdirPathSegment(providerId), + _workdirPathSegment(modelId, prefix: 'model'), + taskPath, + ), + ); + return _assembleAgenticWorkspace(dir, workspace); + } - for (final entry in workspace.files.entries) { - final f = resolveWorkspaceFile(dir, entry.key); - if (_shouldExcludeWorkspacePath(entry.key)) continue; - await f.parent.create(recursive: true); - await f.writeAsString(entry.value); - } + Future applyCapturedPatch(Directory gradingDir, String patch) async { + if (patch.isEmpty) return; + await _runGit(gradingDir, [ + 'apply', + '--binary', + '--whitespace=nowarn', + '-', + ], stdin: patch); + await _sanitizeGradingWorkspace(gradingDir); + } - await _initializeBaselineGit(dir); - return dir; + Future _sanitizeGradingWorkspace(Directory dir) async { + final toRemove = []; + await for (final entity in dir.list(recursive: true, followLinks: false)) { + final relative = p + .relative(entity.path, from: dir.path) + .replaceAll('\\', '/'); + if (relative.split('/').first == '.git') continue; + if (entity is Link || _shouldExcludeWorkspacePath(relative)) { + toRemove.add(entity); + } + } + for (final entity in toRemove) { + try { + await entity.delete(recursive: true); + } on FileSystemException { + continue; + } + } } Future collectWorkspaceIsolationEvidence( @@ -318,7 +360,7 @@ class WorkdirManager { ); } - Future resetPatchBaseline(Directory workDir) { + Future resetPatchBaseline(Directory workDir) { return _initializeBaselineGit(workDir); } @@ -565,6 +607,28 @@ class WorkdirManager { } } + Future _assembleAgenticWorkspace( + Directory dir, + TaskWorkspace workspace, + ) async { + await _recreateCleanRunDirectory(dir); + + final fixtureRootPath = workspace.fixtureRootPath; + if (fixtureRootPath != null) { + await _copyFixtureRoot(Directory(fixtureRootPath), dir); + } + + for (final entry in workspace.files.entries) { + final f = resolveWorkspaceFile(dir, entry.key); + if (_shouldExcludeWorkspacePath(entry.key)) continue; + await f.parent.create(recursive: true); + await f.writeAsString(entry.value); + } + + await _initializeBaselineGit(dir); + return dir; + } + bool _isSameOrWithin(String parent, String child) { return p.equals(parent, child) || p.isWithin(parent, child); } @@ -604,13 +668,16 @@ class WorkdirManager { await dir.create(recursive: true); } - Future _initializeBaselineGit(Directory dir) async { + Future _initializeBaselineGit(Directory dir) async { await _ensureBaselineGitignore(dir); await _runGit(dir, ['init']); await _runGit(dir, ['config', 'user.email', 'dart-arena@example.invalid']); await _runGit(dir, ['config', 'user.name', 'dart_arena']); await _runGit(dir, ['add', '.']); await _runGit(dir, ['commit', '--allow-empty', '-m', 'baseline']); + await _runGit(dir, ['tag', '-f', patchBaselineRef]); + final head = await _runGit(dir, ['rev-parse', 'HEAD']); + return head.trim(); } Future _ensureBaselineGitignore(Directory dir) async { @@ -621,6 +688,8 @@ class WorkdirManager { '.config/tool_state', '.dartServer/', '.flutter', + '.flutter-plugins', + '.flutter-plugins-dependencies', 'AppData/', 'build/', '.packages', @@ -648,7 +717,11 @@ class WorkdirManager { await gitignore.writeAsString(buffer.toString()); } - Future _runGit(Directory dir, List args) async { + Future _runGit( + Directory dir, + List args, { + String? stdin, + }) async { if (gitTimeout.compareTo(Duration.zero) <= 0) { throw TimeoutException( 'baseline git initialization timed out', @@ -664,6 +737,10 @@ class WorkdirManager { environment: _baselineGitEnvironment(), includeParentEnvironment: false, ); + if (stdin != null) { + process.stdin.add(utf8.encode(stdin)); + await process.stdin.close(); + } final stdoutBuffer = _BoundedTextCollector(gitMaxOutputChars); final stderrBuffer = _BoundedTextCollector(gitMaxOutputChars); @@ -708,7 +785,7 @@ class WorkdirManager { signal.exitCode, ); } - return; + return stdoutBuffer.text; } await _terminateProcessTree(process.pid, ProcessSignal.sigterm); diff --git a/app/test/core/patch_capture_test.dart b/app/test/core/patch_capture_test.dart index fccef90..7ad2d1f 100644 --- a/app/test/core/patch_capture_test.dart +++ b/app/test/core/patch_capture_test.dart @@ -29,6 +29,7 @@ void main() { await _git(root, ['config', 'user.name', 'test']); await _git(root, ['add', '.']); await _git(root, ['commit', '-m', 'baseline']); + await _git(root, ['tag', patchBaselineRef]); await File(p.join(root.path, 'lib.dart')).writeAsString('int a = 2;\n'); await File(p.join(root.path, 'new.dart')).writeAsString('int b = 3;\n'); @@ -42,8 +43,59 @@ void main() { expect(result.patch, contains('+int b = 3;')); expect(result.status, contains('M lib.dart')); expect(result.status, contains(' A new.dart')); + expect(result.patchSha256, matches(RegExp(r'^[0-9a-f]{64}$'))); }); + test('captures staged changes relative to the baseline ref', () async { + final root = await Directory.systemTemp.createTemp('patch_capture_staged_'); + addTearDown(() async { + if (await root.exists()) await root.delete(recursive: true); + }); + + await File(p.join(root.path, 'lib.dart')).writeAsString('int a = 1;\n'); + await _git(root, ['init']); + await _git(root, ['config', 'user.email', 'test@example.invalid']); + await _git(root, ['config', 'user.name', 'test']); + await _git(root, ['add', '.']); + await _git(root, ['commit', '-m', 'baseline']); + await _git(root, ['tag', patchBaselineRef]); + await File(p.join(root.path, 'lib.dart')).writeAsString('int a = 2;\n'); + await _git(root, ['add', 'lib.dart']); + + final result = await const PatchCapture().capture(root); + + expect(result.hasMeaningfulDiff, isTrue); + expect(result.patch, contains('+int a = 2;')); + }); + + test( + 'captures a solution the agent committed on top of the baseline', + () async { + final root = await Directory.systemTemp.createTemp( + 'patch_capture_commit_', + ); + addTearDown(() async { + if (await root.exists()) await root.delete(recursive: true); + }); + + await File(p.join(root.path, 'lib.dart')).writeAsString('int a = 1;\n'); + await _git(root, ['init']); + await _git(root, ['config', 'user.email', 'test@example.invalid']); + await _git(root, ['config', 'user.name', 'test']); + await _git(root, ['add', '.']); + await _git(root, ['commit', '-m', 'baseline']); + await _git(root, ['tag', patchBaselineRef]); + await File(p.join(root.path, 'lib.dart')).writeAsString('int a = 2;\n'); + await _git(root, ['add', '.']); + await _git(root, ['commit', '-m', 'agent solution']); + + final result = await const PatchCapture().capture(root); + + expect(result.hasMeaningfulDiff, isTrue); + expect(result.patch, contains('+int a = 2;')); + }, + ); + test( 'scrubs sensitive environment variables from git subprocesses', () async { diff --git a/app/test/export/release_report_cli_runner_test.dart b/app/test/export/release_report_cli_runner_test.dart index 14f3205..db81131 100644 --- a/app/test/export/release_report_cli_runner_test.dart +++ b/app/test/export/release_report_cli_runner_test.dart @@ -3,8 +3,10 @@ import 'dart:io'; import 'package:crypto/crypto.dart'; import 'package:dart_arena/core/task_bundle_digest.dart'; +import 'package:dart_arena/core/task_integrity.dart'; import 'package:dart_arena/export/release_report_cli_runner.dart'; import 'package:dart_arena/storage/database.dart'; +import 'package:dart_arena/tasks/file_backed/file_backed_task.dart'; import 'package:drift/drift.dart'; import 'package:drift/native.dart'; import 'package:test/test.dart'; @@ -1930,6 +1932,9 @@ void main() { final taskQaSummaryPath = p.join(taskQaDir.path, 'admission_summary.json'); final taskBundle = Directory(p.join(taskQaDir.path, 'tasks', 'task.a')); final taskBundleDigest = await _writeReleaseTaskBundle(taskBundle); + final task = await FileBackedTask.load(taskBundle); + await task.ensureLoaded(); + final hiddenDigests = hiddenVerifierDigests(task); final reportPath = p.join(taskBundle.path, 'qa', 'admission_report.json'); await Directory(p.dirname(reportPath)).create(recursive: true); await File( @@ -1948,7 +1953,10 @@ void main() { _prettyJson(_taskQaReportJson(taskBundleDigest: taskBundleDigest)), ); final databasePath = p.join(tmp.path, 'dart_arena.sqlite'); - await _seedDatabase(databasePath); + await _seedDatabase( + databasePath, + resultProvenance: _cleanReplayResultProvenance(hiddenDigests, 2), + ); final artifactManifestPath = p.join(tmp.path, 'manifest.json'); await File( artifactManifestPath, @@ -2753,6 +2761,9 @@ void main() { ); final taskBundle = Directory(p.join(taskQaDir.path, 'tasks', 'task.a')); final taskBundleDigest = await _writeReleaseTaskBundle(taskBundle); + final task = await FileBackedTask.load(taskBundle); + await task.ensureLoaded(); + final hiddenDigests = hiddenVerifierDigests(task); final reportPath = p.join(taskBundle.path, 'qa', 'admission_report.json'); await Directory(p.dirname(reportPath)).create(recursive: true); await File( @@ -2771,7 +2782,11 @@ void main() { _prettyJson(_taskQaReportJson(taskBundleDigest: taskBundleDigest)), ); final databasePath = p.join(tmp.path, 'dart_arena.sqlite'); - await _seedDatabase(databasePath, runIds: const ['run-1', 'run-2']); + await _seedDatabase( + databasePath, + runIds: const ['run-1', 'run-2'], + resultProvenance: _cleanReplayResultProvenance(hiddenDigests, 2), + ); final firstBundleRoot = p.join(tmp.path, 'bundle_run_1'); final secondBundleRoot = p.join(tmp.path, 'bundle_run_2'); await _writeCompleteArtifactBundle(firstBundleRoot, runId: 'run-1'); @@ -10996,9 +11011,14 @@ Map _leaderboardJson({ 'taskSetId': 'taskset-test', 'evaluatorSchemaVersion': 2, 'preset': 'mvp', - 'selectedTasks': ['task.a'], - 'corpusManifestDigestSha256': - '0000000000000000000000000000000000000000000000000000000000000000', + 'selectedTasks': [ + { + 'taskId': 'task.a', + 'taskVersion': 1, + 'taskBundleDigest': _fixtureTaskBundleDigest, + }, + ], + 'corpusManifestDigestSha256': _fixtureCorpusManifestDigest, }, 'track': 'agentic', 'dataPolicy': 'aggregate-compatible', @@ -11088,6 +11108,7 @@ Map _leaderboardJson({ { 'taskId': 'task.a', 'taskVersion': 1, + 'taskBundleDigest': _fixtureTaskBundleDigest, 'benchmarkTrack': 'agentic', 'trialCount': sampleCount, 'sampleCount': sampleCount, @@ -12618,6 +12639,7 @@ Future _seedDatabase( bool includeSdkVersions = true, bool includeDependencySnapshot = true, bool includePricingRegistry = true, + List> resultProvenance = const [], }) async { final db = AppDatabase(NativeDatabase(File(databasePath))); try { @@ -12701,6 +12723,17 @@ Future _seedDatabase( }, }, ], + 'combos': [ + for (final result in resultProvenance) + { + 'taskId': result['taskId'], + 'providerId': result['providerId'], + 'modelId': result['modelId'], + 'trialIndex': result['trialIndex'], + }, + ], + if (resultProvenance.isNotEmpty) + 'resultProvenance': resultProvenance, }), ), ), @@ -12711,6 +12744,38 @@ Future _seedDatabase( } } +List> _cleanReplayResultProvenance( + Map hiddenVerifierDigests, + int count, +) => [ + for (var trialIndex = 0; trialIndex < count; trialIndex++) + { + 'taskId': 'task.a', + 'taskVersion': 1, + 'benchmarkTrack': 'agentic', + 'providerId': 'openai', + 'modelId': 'gpt-5', + 'trialIndex': trialIndex, + 'gradingMode': 'clean_replay', + 'hiddenFixtureIsolation': const { + 'asserted': true, + 'leakedPaths': [], + }, + 'hiddenVerifierDigests': hiddenVerifierDigests, + }, +]; + +const _fixtureTaskBundleDigest = + '0000000000000000000000000000000000000000000000000000000000000000'; + +final _fixtureCorpusManifestDigest = corpusManifestDigestSha256(const [ + CorpusManifestEntry( + taskId: 'task.a', + taskVersion: 1, + taskBundleDigest: _fixtureTaskBundleDigest, + ), +]); + String _prettyJson(Object? value) => '${const JsonEncoder.withIndent(' ').convert(value)}\n'; diff --git a/app/test/export/release_report_fresh_execution_test.dart b/app/test/export/release_report_fresh_execution_test.dart new file mode 100644 index 0000000..e9855d3 --- /dev/null +++ b/app/test/export/release_report_fresh_execution_test.dart @@ -0,0 +1,278 @@ +import 'package:dart_arena/core/task_bundle_digest.dart'; +import 'package:dart_arena/export/release_report.dart'; +import 'package:test/test.dart'; + +void main() { + test('blocks stale replay provenance and corpus manifest entries', () { + const taskBundleDigest = + 'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'; + final manifestDigest = corpusManifestDigestSha256(const [ + CorpusManifestEntry( + taskId: 'task.a', + taskVersion: 1, + taskBundleDigest: taskBundleDigest, + ), + ]); + final report = buildReleaseReport( + leaderboard: { + 'benchmark': { + 'dataPolicy': 'aggregate-compatible', + 'version': 'v1', + 'taskSetId': 'set', + 'evaluatorSchemaVersion': 2, + 'preset': 'official', + 'selectedTasks': [ + { + 'taskId': 'task.a', + 'taskVersion': 1, + 'taskBundleDigest': taskBundleDigest, + }, + ], + 'corpusManifestDigestSha256': manifestDigest, + }, + 'source': { + 'runIds': ['run-1'], + 'taskRunCount': 1, + 'runProvenance': const {}, + }, + 'models': const [], + 'tasks': [ + { + 'taskId': 'task.a', + 'taskVersion': 1, + 'taskBundleDigest': + 'bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb', + }, + ], + 'taskModelCells': const [], + 'trialSummaries': const [], + }, + taskQaSummary: const {}, + taskQaReports: const >[], + taskBundleDigestEvidence: const [ + { + 'taskId': 'task.a', + 'taskVersion': 1, + 'track': 'agentic', + 'hiddenVerifierDigests': { + 'hidden_test': + 'cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc', + }, + }, + ], + runProvenanceById: { + 'run-1': { + 'combos': const [ + { + 'taskId': 'task.a', + 'providerId': 'p', + 'modelId': 'm', + 'trialIndex': 0, + }, + ], + 'resultProvenance': const [ + { + 'taskId': 'task.a', + 'taskVersion': 1, + 'benchmarkTrack': 'agentic', + 'providerId': 'p', + 'modelId': 'm', + 'trialIndex': 0, + 'gradingMode': 'agent_workspace', + 'hiddenFixtureIsolation': { + 'asserted': true, + 'leakedPaths': ['test/_hidden/answer_hidden_test.dart'], + }, + 'hiddenVerifierDigests': { + 'hidden_test': + 'dddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd', + }, + }, + ], + }, + }, + options: const ReleaseReportOptions(releaseId: 'test'), + ); + + final blockers = (report['blockers']! as List).join('\n'); + expect( + blockers, + contains( + 'Result was graded in the agent workspace, not a clean replay baseline.', + ), + ); + expect( + blockers, + contains( + 'Hidden verifier fixtures were readable from the agent workspace.', + ), + ); + expect( + blockers, + contains( + 'Hidden verifier digests drifted from the corpus since the run.', + ), + ); + expect( + blockers, + contains( + 'Leaderboard frozen corpus manifest entries do not match leaderboard tasks.', + ), + ); + final provenance = report['provenance']! as Map; + expect(provenance['cleanReplayResultCount'], 0); + expect(provenance['hiddenFixtureIsolationLeakResultCount'], 1); + }); + + test('blocks when live hidden verifier evidence is absent', () { + final blockers = _provenanceBlockers( + taskBundleDigestEvidence: const >[], + hiddenVerifierDigests: const {'hidden_test': 'aa'}, + ); + expect( + blockers, + contains( + 'Could not recompute hidden verifier digests from the live task ' + 'bundle for a graded result.', + ), + ); + expect( + blockers, + isNot( + contains( + 'Hidden verifier digests drifted from the corpus ' + 'since the run.', + ), + ), + ); + }); + + test('does not block a task that legitimately has no hidden verifiers', () { + final blockers = _provenanceBlockers( + taskBundleDigestEvidence: const [ + { + 'taskId': 'task.a', + 'taskVersion': 1, + 'track': 'agentic', + 'hiddenVerifierDigests': {}, + }, + ], + hiddenVerifierDigests: const {}, + ); + expect( + blockers, + isNot( + contains( + 'Hidden verifier digests drifted from the corpus ' + 'since the run.', + ), + ), + ); + expect( + blockers, + isNot( + contains( + 'Could not recompute hidden verifier digests from the ' + 'live task bundle for a graded result.', + ), + ), + ); + }); + + test('blocks when digest evidence lacks a hiddenVerifierDigests field', () { + final blockers = _provenanceBlockers( + taskBundleDigestEvidence: const [ + {'taskId': 'task.a', 'taskVersion': 1, 'track': 'agentic'}, + ], + hiddenVerifierDigests: const {}, + ); + expect( + blockers, + contains( + 'Could not recompute hidden verifier digests from the live task ' + 'bundle for a graded result.', + ), + ); + }); + + test( + 'blocks an agentic result whose provenance omits the benchmark track', + () { + final blockers = _provenanceBlockers( + taskBundleDigestEvidence: const [ + { + 'taskId': 'task.a', + 'taskVersion': 1, + 'track': 'agentic', + 'hiddenVerifierDigests': {'hidden_test': 'aa'}, + }, + ], + hiddenVerifierDigests: const {'hidden_test': 'aa'}, + benchmarkTrack: null, + ); + expect( + blockers, + contains( + 'Result provenance has a missing or unrecognized benchmark track.', + ), + ); + }, + ); +} + +String _provenanceBlockers({ + required List> taskBundleDigestEvidence, + required Map hiddenVerifierDigests, + String? benchmarkTrack = 'agentic', +}) { + final report = buildReleaseReport( + leaderboard: { + 'benchmark': const { + 'dataPolicy': 'aggregate-compatible', + 'version': 'v1', + 'taskSetId': 'set', + 'evaluatorSchemaVersion': 2, + }, + 'source': { + 'runIds': const ['run-1'], + 'taskRunCount': 1, + 'runProvenance': const {}, + }, + 'models': const [], + 'tasks': const [], + }, + taskQaSummary: const {}, + taskQaReports: const >[], + taskBundleDigestEvidence: taskBundleDigestEvidence, + runProvenanceById: { + 'run-1': { + 'combos': const [ + { + 'taskId': 'task.a', + 'providerId': 'p', + 'modelId': 'm', + 'trialIndex': 0, + }, + ], + 'resultProvenance': [ + { + 'taskId': 'task.a', + 'taskVersion': 1, + if (benchmarkTrack != null) 'benchmarkTrack': benchmarkTrack, + 'providerId': 'p', + 'modelId': 'm', + 'trialIndex': 0, + 'gradingMode': 'clean_replay', + 'hiddenFixtureIsolation': const { + 'asserted': true, + 'leakedPaths': [], + }, + 'hiddenVerifierDigests': hiddenVerifierDigests, + }, + ], + }, + }, + options: const ReleaseReportOptions(releaseId: 'test'), + ); + return (report['blockers']! as List).join('\n'); +} diff --git a/app/test/runner/agentic_run_orchestrator_test.dart b/app/test/runner/agentic_run_orchestrator_test.dart index 8a09355..ad46007 100644 --- a/app/test/runner/agentic_run_orchestrator_test.dart +++ b/app/test/runner/agentic_run_orchestrator_test.dart @@ -5,6 +5,7 @@ import 'package:dart_arena/agent/agent_harness.dart'; import 'package:dart_arena/agent/agent_run_result.dart'; import 'package:dart_arena/core/benchmark_task.dart'; import 'package:dart_arena/core/category.dart'; +import 'package:dart_arena/core/patch_capture.dart'; import 'package:dart_arena/core/evaluation_context.dart'; import 'package:dart_arena/core/evaluation_result.dart'; import 'package:dart_arena/core/evaluator_blocking.dart'; @@ -21,6 +22,7 @@ import 'package:path/path.dart' as p; import '../support/headless_fakes.dart'; class _FakeHarness implements AgentHarness { + Directory? workspace; _FakeHarness(this.onRun); final Future Function(Directory workspace) onRun; @@ -38,6 +40,7 @@ class _FakeHarness implements AgentHarness { bool allowInternet = true, bool requireGeneratedCodeSandbox = false, }) async { + this.workspace = workspace; await onRun(workspace); return const AgentRunResult( status: AgentRunStatus.success, @@ -182,6 +185,29 @@ class _AnswerEvaluator implements Evaluator { } } +class _GradingWorkspaceEvaluator implements Evaluator { + Directory? workDir; + + @override + String get id => 'grading_workspace'; + + @override + Future evaluate(EvaluationContext ctx) async { + workDir = ctx.workDir; + final source = await File( + p.join(ctx.workDir.path, 'lib', 'answer.dart'), + ).readAsString(); + final passed = + source.contains('42') && + p.basename(ctx.workDir.path).endsWith('_grading'); + return EvaluationResult( + evaluatorId: id, + passed: passed, + score: passed ? 1 : 0, + ); + } +} + class _AgenticAnswerTask extends BenchmarkTask { @override String get id => 'agent.answer'; @@ -407,6 +433,96 @@ void main() { timeout: const Timeout(Duration(minutes: 2)), ); + test('grades the replayed patch in the sibling grading workspace', () async { + final root = await Directory.systemTemp.createTemp( + 'agentic_orch_clean_replay_', + ); + addTearDown(() async { + if (await root.exists()) await root.delete(recursive: true); + }); + final evaluator = _GradingWorkspaceEvaluator(); + final task = _AgenticBlockingTask([evaluator]); + final harness = _FakeHarness((workspace) async { + await File( + p.join(workspace.path, 'lib', 'answer.dart'), + ).writeAsString('int answer() => 42;\n'); + }); + + final result = + await AgenticRunOrchestrator( + workdirManager: NoOpPrepareWorkdirManager(root: root), + ).run( + runId: 'run-clean-replay', + task: task, + harness: harness, + providerId: 'fake_agent', + modelId: 'm', + trialIndex: 0, + evaluatorConfig: const EvaluatorConfig(), + ); + + expect( + result.evaluations + .singleWhere((e) => e.evaluatorId == evaluator.id) + .passed, + isTrue, + ); + expect(evaluator.workDir, isNotNull); + expect(p.basename(evaluator.workDir!.path), 'trial_0_grading'); + expect( + p.dirname(evaluator.workDir!.path), + p.dirname(harness.workspace!.path), + ); + expect( + p.isWithin(harness.workspace!.path, evaluator.workDir!.path), + isFalse, + ); + expect(result.provenance['gradingMode'], 'clean_replay'); + expect(result.provenance['patchApplied'], isTrue); + expect( + result.provenance['patchSha256'], + matches(RegExp(r'^[0-9a-f]{64}$')), + ); + }); + + test('records hidden fixture leaks from the agent workspace', () async { + final root = await Directory.systemTemp.createTemp( + 'agentic_orch_fixture_leak_', + ); + addTearDown(() async { + if (await root.exists()) await root.delete(recursive: true); + }); + final task = _AgenticBlockingTask(const []); + final result = + await AgenticRunOrchestrator( + workdirManager: NoOpPrepareWorkdirManager(root: root), + ).run( + runId: 'run-fixture-leak', + task: task, + harness: _FakeHarness((workspace) async { + final hidden = File( + p.join( + workspace.path, + 'test', + '_hidden', + 'answer_hidden_test.dart', + ), + ); + await hidden.parent.create(recursive: true); + await hidden.writeAsString('leaked'); + }), + providerId: 'fake_agent', + modelId: 'm', + trialIndex: 0, + evaluatorConfig: const EvaluatorConfig(), + ); + + final isolation = + result.provenance['hiddenFixtureIsolation'] as Map; + expect(isolation['asserted'], isTrue); + expect(isolation['leakedPaths'], ['test/_hidden/answer_hidden_test.dart']); + }); + test( 'passes denied environment keys to the agent harness', () async { @@ -654,4 +770,37 @@ void main() { } }, ); + + test('blocks grading when patch capture fails', () async { + final root = await Directory.systemTemp.createTemp( + 'agentic_capture_failure_', + ); + addTearDown(() async { + if (await root.exists()) await root.delete(recursive: true); + }); + + final answer = _SpyEvaluator('answer_spy'); + final result = + await AgenticRunOrchestrator( + workdirManager: NoOpPrepareWorkdirManager(root: root), + patchCapture: const PatchCapture( + gitExecutable: 'dart-arena-nonexistent-git', + ), + now: () => DateTime(2026, 6, 2), + ).run( + runId: 'run-capture-failure', + task: _AgenticBlockingTask([answer]), + harness: _FakeHarness((workspace) async {}), + providerId: 'fake_agent', + modelId: 'm', + trialIndex: 0, + evaluatorConfig: const EvaluatorConfig(), + ); + + expect(answer.calls, 0); + final environment = result.evaluations.singleWhere( + (evaluation) => evaluation.evaluatorId == 'environment', + ); + expect(environment.details['phase'], 'patch_capture'); + }); } diff --git a/app/test/runner/workdir_manager_test.dart b/app/test/runner/workdir_manager_test.dart index 9f37916..ce6e4b4 100644 --- a/app/test/runner/workdir_manager_test.dart +++ b/app/test/runner/workdir_manager_test.dart @@ -2,6 +2,7 @@ import 'dart:async'; import 'dart:convert'; import 'dart:io'; +import 'package:dart_arena/core/patch_capture.dart'; import 'package:dart_arena/core/path_safety.dart'; import 'package:dart_arena/core/task_workspace.dart'; import 'package:dart_arena/runner/workdir_manager.dart'; @@ -390,6 +391,215 @@ environment: ); }); + test( + 'replays captured patches into a clean agentic grading workdir', + () async { + final root = await Directory.systemTemp.createTemp( + 'dart_arena_agentic_grading_', + ); + addTearDown(() async { + if (await root.exists()) await root.delete(recursive: true); + }); + const workspace = TaskWorkspace( + files: { + 'lib/answer.dart': 'int answer() => 41;\n', + 'test/_hidden/answer_hidden_test.dart': 'hidden', + }, + ); + final manager = WorkdirManager(root: root); + final agentWorkspace = await manager.createAgenticTaskWorkdir( + runId: 'r', + providerId: 'p', + modelId: 'm', + taskId: 't', + workspace: workspace, + ); + await File( + p.join(agentWorkspace.path, 'lib', 'answer.dart'), + ).writeAsString('int answer() => 42;\n'); + final capturedPatch = await const PatchCapture().capture(agentWorkspace); + + final gradingWorkspace = await manager.createAgenticGradingWorkdir( + runId: 'r', + providerId: 'p', + modelId: 'm', + taskId: 't', + workspace: workspace, + ); + + expect(p.basename(gradingWorkspace.path), 'trial_0_grading'); + expect(p.isWithin(agentWorkspace.path, gradingWorkspace.path), isFalse); + expect( + await File( + p.join(gradingWorkspace.path, 'lib', 'answer.dart'), + ).readAsString(), + 'int answer() => 41;\n', + ); + expect( + await File( + p.join( + gradingWorkspace.path, + 'test', + '_hidden', + 'answer_hidden_test.dart', + ), + ).exists(), + isFalse, + ); + + await manager.applyCapturedPatch(gradingWorkspace, capturedPatch.patch); + + expect( + await File( + p.join(gradingWorkspace.path, 'lib', 'answer.dart'), + ).readAsString(), + 'int answer() => 42;\n', + ); + }, + ); + + test('strips restricted paths reintroduced by a captured patch', () async { + final root = await Directory.systemTemp.createTemp( + 'dart_arena_grading_strip_', + ); + addTearDown(() async { + if (await root.exists()) await root.delete(recursive: true); + }); + const workspace = TaskWorkspace( + files: {'lib/answer.dart': 'int answer() => 41;\n'}, + ); + final manager = WorkdirManager(root: root); + final agentWorkspace = await manager.createAgenticTaskWorkdir( + runId: 'r', + providerId: 'p', + modelId: 'm', + taskId: 't', + workspace: workspace, + ); + await File( + p.join(agentWorkspace.path, 'test', '_hidden', 'leaked_test.dart'), + ).create(recursive: true); + await File( + p.join(agentWorkspace.path, 'test', '_hidden', 'leaked_test.dart'), + ).writeAsString('leaked'); + final capturedPatch = await const PatchCapture().capture(agentWorkspace); + expect(capturedPatch.patch, contains('_hidden/leaked_test.dart')); + + final gradingWorkspace = await manager.createAgenticGradingWorkdir( + runId: 'r', + providerId: 'p', + modelId: 'm', + taskId: 't', + workspace: workspace, + ); + await manager.applyCapturedPatch(gradingWorkspace, capturedPatch.patch); + + expect( + await File( + p.join(gradingWorkspace.path, 'test', '_hidden', 'leaked_test.dart'), + ).exists(), + isFalse, + ); + }); + + test( + 'removes symlinks a captured patch would reintroduce into grading', + () async { + final root = await Directory.systemTemp.createTemp( + 'dart_arena_grading_symlink_', + ); + final outside = await Directory.systemTemp.createTemp( + 'dart_arena_symlink_target_', + ); + addTearDown(() async { + if (await root.exists()) await root.delete(recursive: true); + if (await outside.exists()) await outside.delete(recursive: true); + }); + await File(p.join(outside.path, 'secret.txt')).writeAsString('secret'); + const workspace = TaskWorkspace( + files: {'lib/answer.dart': 'int answer() => 41;\n'}, + ); + final manager = WorkdirManager(root: root); + final agentWorkspace = await manager.createAgenticTaskWorkdir( + runId: 'r', + providerId: 'p', + modelId: 'm', + taskId: 't', + workspace: workspace, + ); + await Link( + p.join(agentWorkspace.path, 'lib', 'leak.txt'), + ).create(p.join(outside.path, 'secret.txt')); + final capturedPatch = await const PatchCapture().capture(agentWorkspace); + expect(capturedPatch.patch, contains('lib/leak.txt')); + + final gradingWorkspace = await manager.createAgenticGradingWorkdir( + runId: 'r', + providerId: 'p', + modelId: 'm', + taskId: 't', + workspace: workspace, + ); + await manager.applyCapturedPatch(gradingWorkspace, capturedPatch.patch); + + expect( + await Link(p.join(gradingWorkspace.path, 'lib', 'leak.txt')).exists(), + isFalse, + ); + expect( + await File(p.join(gradingWorkspace.path, 'lib', 'leak.txt')).exists(), + isFalse, + ); + }, + ); + + test( + 'captures against the recorded baseline even after the tag is retargeted', + () async { + final root = await Directory.systemTemp.createTemp( + 'dart_arena_baseline_sha_', + ); + addTearDown(() async { + if (await root.exists()) await root.delete(recursive: true); + }); + const workspace = TaskWorkspace( + files: {'lib/answer.dart': 'int answer() => 41;\n'}, + ); + final manager = WorkdirManager(root: root); + final agentWorkspace = await manager.createAgenticTaskWorkdir( + runId: 'r', + providerId: 'p', + modelId: 'm', + taskId: 't', + workspace: workspace, + ); + final baselineSha = await manager.resetPatchBaseline(agentWorkspace); + expect(baselineSha, matches(RegExp(r'^[0-9a-f]{40}$'))); + + await File( + p.join(agentWorkspace.path, 'lib', 'answer.dart'), + ).writeAsString('int answer() => 42;\n'); + Future git(List args) async { + final result = await Process.run( + 'git', + args, + workingDirectory: agentWorkspace.path, + ); + expect(result.exitCode, 0, reason: result.stderr.toString()); + } + + await git(['add', '.']); + await git(['commit', '-m', 'agent solution']); + await git(['tag', '-f', 'arena_baseline']); + + final captured = await const PatchCapture().capture( + agentWorkspace, + baselineRef: baselineSha, + ); + expect(captured.patch, contains('+int answer() => 42;')); + }, + ); + test( 'createAgenticTaskWorkdir does not follow fixture symlinks', () async { diff --git a/docs/archive/deepswe-manual-replay/README.md b/docs/archive/deepswe-manual-replay/README.md new file mode 100644 index 0000000..c2ea154 --- /dev/null +++ b/docs/archive/deepswe-manual-replay/README.md @@ -0,0 +1,10 @@ +# Archived: manual DeepSWE replay artifacts + +These per-task directories (`README.md`, `replay_log.md`, `replay_manifest.json`, +`solver_runs/`, `flake_report.json`, `leakage_audit.md`, telemetry, etc.) were the +hand-run replay/QA evidence produced while building the benchmark's grading path. + +They are superseded by runner behaviour: the orchestrator now replays the captured +patch into a fresh clean baseline as the official grading path, and the release gate +verifies fresh execution (see #6). Kept here for provenance; not read by any code and +not part of the task-bundle digest. diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/README.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/README.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/README.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/README.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/command_telemetry/command_telemetry_result.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/command_telemetry/command_telemetry_result.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/command_telemetry/command_telemetry_result.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/command_telemetry/command_telemetry_result.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/f2p_checklist.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/f2p_checklist.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/f2p_checklist.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/f2p_checklist.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_report.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_report.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_report.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_report.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/README.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/README.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/README.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/README.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/baseline_expected_failure_summary.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/baseline_expected_failure_summary.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/baseline_expected_failure_summary.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/baseline_expected_failure_summary.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/flake_loop_10_result.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/flake_loop_10_result.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/flake_loop_10_result.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/flake_loop_10_result.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/glm_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/glm_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/glm_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/glm_fresh_rerun_summary.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/gpt_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/gpt_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/gpt_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/gpt_fresh_rerun_summary.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/kimi_failed_rerun_summary.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/kimi_failed_rerun_summary.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/kimi_failed_rerun_summary.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/kimi_failed_rerun_summary.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/minimax_failed_rerun_summary.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/minimax_failed_rerun_summary.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/minimax_failed_rerun_summary.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/minimax_failed_rerun_summary.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/opus_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/opus_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/opus_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/opus_fresh_rerun_summary.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/reference_solution_summary.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/reference_solution_summary.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/flake_runs_10/reference_solution_summary.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/flake_runs_10/reference_solution_summary.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/leakage_audit.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/leakage_audit.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/leakage_audit.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/leakage_audit.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/leakage_scan_result.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/leakage_scan_result.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/leakage_scan_result.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/leakage_scan_result.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/model_audit.yaml b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/model_audit.yaml similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/model_audit.yaml rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/model_audit.yaml diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/p2p_checklist.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/p2p_checklist.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/p2p_checklist.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/p2p_checklist.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/prompt_verifier_bijection.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/prompt_verifier_bijection.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/prompt_verifier_bijection.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/prompt_verifier_bijection.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/qa_repetition/qa_repetition_result.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/qa_repetition/qa_repetition_result.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/qa_repetition/qa_repetition_result.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/qa_repetition/qa_repetition_result.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/qa_repetition/run_1_summary.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/qa_repetition/run_1_summary.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/qa_repetition/run_1_summary.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/qa_repetition/run_1_summary.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/qa_repetition/run_2_summary.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/qa_repetition/run_2_summary.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/qa_repetition/run_2_summary.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/qa_repetition/run_2_summary.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/qa_repetition/run_3_summary.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/qa_repetition/run_3_summary.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/qa_repetition/run_3_summary.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/qa_repetition/run_3_summary.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/qa_repetition/run_4_summary.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/qa_repetition/run_4_summary.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/qa_repetition/run_4_summary.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/qa_repetition/run_4_summary.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/qa_repetition/run_5_summary.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/qa_repetition/run_5_summary.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/qa_repetition/run_5_summary.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/qa_repetition/run_5_summary.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/replay_log.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/replay_log.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/replay_log.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/replay_log.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/replay_manifest.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/replay_manifest.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/replay_manifest.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/replay_manifest.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/summary.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/summary.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/glm/summary.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/glm/summary.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/summary.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/summary.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/gpt/summary.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/gpt/summary.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/summary.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/summary.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/kimi/summary.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/kimi/summary.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/summary.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/summary.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/minimax/summary.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/minimax/summary.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/lib/quantity_stepper.dart diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/test/quantity_stepper_test.dart diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/summary.md b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/summary.md similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/solver_runs/opus/summary.md rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/solver_runs/opus/summary.md diff --git a/tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/telemetry_report.json b/docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/telemetry_report.json similarity index 100% rename from tasks/flutter/accessibility.quantity_stepper_semantics/deepswe/telemetry_report.json rename to docs/archive/deepswe-manual-replay/accessibility.quantity_stepper_semantics/telemetry_report.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/README.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/README.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/README.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/README.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/command_telemetry/command_telemetry_result.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/command_telemetry/command_telemetry_result.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/command_telemetry/command_telemetry_result.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/command_telemetry/command_telemetry_result.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/f2p_checklist.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/f2p_checklist.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/f2p_checklist.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/f2p_checklist.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_report.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_report.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_report.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_report.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/README.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/README.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/README.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/README.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/baseline_expected_failure_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/baseline_expected_failure_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/baseline_expected_failure_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/baseline_expected_failure_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/flake_loop_result.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/flake_loop_result.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/flake_loop_result.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/flake_loop_result.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/kimi_replay_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/kimi_replay_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/kimi_replay_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/kimi_replay_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/minimax_replay_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/minimax_replay_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/minimax_replay_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/minimax_replay_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/reference_solution_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/reference_solution_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/reference_solution_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/reference_solution_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/targets.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/targets.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs/targets.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs/targets.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/README.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/README.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/README.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/README.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/baseline_expected_failure_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/baseline_expected_failure_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/baseline_expected_failure_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/baseline_expected_failure_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/flake_loop_10_result.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/flake_loop_10_result.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/flake_loop_10_result.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/flake_loop_10_result.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/gpt_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/gpt_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/gpt_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/gpt_fresh_rerun_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/kimi_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/kimi_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/kimi_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/kimi_fresh_rerun_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/minimax_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/minimax_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/minimax_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/minimax_fresh_rerun_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/reference_solution_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/reference_solution_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/flake_runs_10/reference_solution_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/flake_runs_10/reference_solution_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/leakage_audit.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/leakage_audit.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/leakage_audit.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/leakage_audit.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/leakage_scan_result.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/leakage_scan_result.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/leakage_scan_result.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/leakage_scan_result.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/model_audit.yaml b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/model_audit.yaml similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/model_audit.yaml rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/model_audit.yaml diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/p2p_checklist.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/p2p_checklist.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/p2p_checklist.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/p2p_checklist.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/prompt_verifier_bijection.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/prompt_verifier_bijection.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/prompt_verifier_bijection.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/prompt_verifier_bijection.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/qa_repetition/qa_repetition_result.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/qa_repetition/qa_repetition_result.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/qa_repetition/qa_repetition_result.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/qa_repetition/qa_repetition_result.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/qa_repetition/run_1_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/qa_repetition/run_1_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/qa_repetition/run_1_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/qa_repetition/run_1_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/qa_repetition/run_2_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/qa_repetition/run_2_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/qa_repetition/run_2_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/qa_repetition/run_2_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/qa_repetition/run_3_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/qa_repetition/run_3_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/qa_repetition/run_3_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/qa_repetition/run_3_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/qa_repetition/run_4_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/qa_repetition/run_4_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/qa_repetition/run_4_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/qa_repetition/run_4_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/qa_repetition/run_5_summary.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/qa_repetition/run_5_summary.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/qa_repetition/run_5_summary.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/qa_repetition/run_5_summary.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/replay_log.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/replay_log.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/replay_log.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/replay_log.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/replay_manifest.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/replay_manifest.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/replay_manifest.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/replay_manifest.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_session.jsonl b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_session.jsonl similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_session.jsonl rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_session.jsonl diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/feed_refresh_controller.dart b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/feed_refresh_controller.dart similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/feed_refresh_controller.dart rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/feed_refresh_controller.dart diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/feed_refresh_controller_test.dart b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/feed_refresh_controller_test.dart similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/feed_refresh_controller_test.dart rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/feed_refresh_controller_test.dart diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/summary.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/summary.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/gpt/summary.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/gpt/summary.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/replay_result.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/replay_result.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/replay_result.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/replay_result.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_session.jsonl b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_session.jsonl similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_session.jsonl rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_session.jsonl diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/feed_refresh_controller.dart b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/feed_refresh_controller.dart similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/feed_refresh_controller.dart rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/feed_refresh_controller.dart diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/feed_refresh_controller_test.dart b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/feed_refresh_controller_test.dart similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/feed_refresh_controller_test.dart rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/feed_refresh_controller_test.dart diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/solver.patch b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/solver.patch similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/solver.patch rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/solver.patch diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/summary.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/summary.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/summary.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/summary.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/trajectory/subagent_input.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/trajectory/subagent_meta.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/kimi/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/kimi/trajectory/subagent_output.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/replay_result.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/replay_result.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/replay_result.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/replay_result.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_session.jsonl b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_session.jsonl similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_session.jsonl rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_session.jsonl diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/feed_refresh_controller.dart b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/feed_refresh_controller.dart similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/feed_refresh_controller.dart rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/feed_refresh_controller.dart diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/feed_refresh_controller_test.dart b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/feed_refresh_controller_test.dart similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/feed_refresh_controller_test.dart rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/feed_refresh_controller_test.dart diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/solver.patch b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/solver.patch similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/solver.patch rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/solver.patch diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/summary.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/summary.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/summary.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/summary.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/trajectory/subagent_input.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/trajectory/subagent_meta.json diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/solver_runs/minimax/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/solver_runs/minimax/trajectory/subagent_output.md diff --git a/tasks/flutter/async.refresh_deduplicator/deepswe/telemetry_report.json b/docs/archive/deepswe-manual-replay/async.refresh_deduplicator/telemetry_report.json similarity index 100% rename from tasks/flutter/async.refresh_deduplicator/deepswe/telemetry_report.json rename to docs/archive/deepswe-manual-replay/async.refresh_deduplicator/telemetry_report.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/README.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/README.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/README.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/README.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/command_telemetry/command_telemetry_result.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/command_telemetry/command_telemetry_result.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/command_telemetry/command_telemetry_result.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/command_telemetry/command_telemetry_result.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/f2p_checklist.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/f2p_checklist.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/f2p_checklist.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/f2p_checklist.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_report.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_report.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_report.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_report.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/README.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/README.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/README.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/README.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/baseline_expected_failure_summary.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/baseline_expected_failure_summary.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/baseline_expected_failure_summary.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/baseline_expected_failure_summary.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/flake_loop_10_result.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/flake_loop_10_result.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/flake_loop_10_result.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/flake_loop_10_result.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/glm_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/glm_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/glm_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/glm_fresh_rerun_summary.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/gpt_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/gpt_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/gpt_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/gpt_fresh_rerun_summary.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/kimi_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/kimi_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/kimi_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/kimi_fresh_rerun_summary.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/minimax_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/minimax_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/minimax_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/minimax_fresh_rerun_summary.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/reference_solution_summary.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/reference_solution_summary.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/flake_runs_10/reference_solution_summary.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/flake_runs_10/reference_solution_summary.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/leakage_audit.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/leakage_audit.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/leakage_audit.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/leakage_audit.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/leakage_scan_result.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/leakage_scan_result.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/leakage_scan_result.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/leakage_scan_result.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/model_audit.yaml b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/model_audit.yaml similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/model_audit.yaml rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/model_audit.yaml diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/p2p_checklist.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/p2p_checklist.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/p2p_checklist.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/p2p_checklist.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/prompt_verifier_bijection.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/prompt_verifier_bijection.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/prompt_verifier_bijection.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/prompt_verifier_bijection.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/qa_repetition/qa_repetition_result.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/qa_repetition/qa_repetition_result.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/qa_repetition/qa_repetition_result.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/qa_repetition/qa_repetition_result.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/qa_repetition/run_1_summary.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/qa_repetition/run_1_summary.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/qa_repetition/run_1_summary.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/qa_repetition/run_1_summary.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/qa_repetition/run_2_summary.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/qa_repetition/run_2_summary.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/qa_repetition/run_2_summary.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/qa_repetition/run_2_summary.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/qa_repetition/run_3_summary.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/qa_repetition/run_3_summary.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/qa_repetition/run_3_summary.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/qa_repetition/run_3_summary.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/qa_repetition/run_4_summary.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/qa_repetition/run_4_summary.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/qa_repetition/run_4_summary.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/qa_repetition/run_4_summary.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/qa_repetition/run_5_summary.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/qa_repetition/run_5_summary.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/qa_repetition/run_5_summary.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/qa_repetition/run_5_summary.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/replay_log.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/replay_log.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/replay_log.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/replay_log.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/replay_manifest.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/replay_manifest.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/replay_manifest.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/replay_manifest.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/summary.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/summary.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/glm/summary.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/glm/summary.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/summary.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/summary.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/gpt/summary.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/gpt/summary.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/summary.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/summary.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/kimi/summary.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/kimi/summary.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/offline_feed_preferences.dart diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/offline_feed_preferences_test.dart diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/summary.md b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/summary.md similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/solver_runs/minimax/summary.md rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/solver_runs/minimax/summary.md diff --git a/tasks/flutter/persistence.offline_feed_preferences/deepswe/telemetry_report.json b/docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/telemetry_report.json similarity index 100% rename from tasks/flutter/persistence.offline_feed_preferences/deepswe/telemetry_report.json rename to docs/archive/deepswe-manual-replay/persistence.offline_feed_preferences/telemetry_report.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/README.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/README.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/README.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/README.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/command_telemetry/command_telemetry_result.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/command_telemetry/command_telemetry_result.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/command_telemetry/command_telemetry_result.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/command_telemetry/command_telemetry_result.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/f2p_checklist.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/f2p_checklist.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/f2p_checklist.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/f2p_checklist.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/flake_report.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_report.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/flake_report.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_report.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/README.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/README.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/README.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/README.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/baseline_expected_failure_summary.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/baseline_expected_failure_summary.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/baseline_expected_failure_summary.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/baseline_expected_failure_summary.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/flake_loop_10_result.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/flake_loop_10_result.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/flake_loop_10_result.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/flake_loop_10_result.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/glm_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/glm_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/glm_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/glm_fresh_rerun_summary.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/gpt_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/gpt_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/gpt_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/gpt_fresh_rerun_summary.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/kimi_failed_rerun_summary.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/kimi_failed_rerun_summary.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/kimi_failed_rerun_summary.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/kimi_failed_rerun_summary.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/minimax_fresh_rerun_summary.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/minimax_fresh_rerun_summary.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/minimax_fresh_rerun_summary.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/minimax_fresh_rerun_summary.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/reference_solution_summary.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/reference_solution_summary.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/flake_runs_10/reference_solution_summary.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/flake_runs_10/reference_solution_summary.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/leakage_audit.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/leakage_audit.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/leakage_audit.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/leakage_audit.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/leakage_scan_result.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/leakage_scan_result.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/leakage_scan_result.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/leakage_scan_result.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/model_audit.yaml b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/model_audit.yaml similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/model_audit.yaml rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/model_audit.yaml diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/p2p_checklist.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/p2p_checklist.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/p2p_checklist.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/p2p_checklist.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/prompt_verifier_bijection.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/prompt_verifier_bijection.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/prompt_verifier_bijection.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/prompt_verifier_bijection.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/qa_repetition/qa_repetition_result.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/qa_repetition/qa_repetition_result.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/qa_repetition/qa_repetition_result.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/qa_repetition/qa_repetition_result.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/qa_repetition/run_1_summary.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/qa_repetition/run_1_summary.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/qa_repetition/run_1_summary.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/qa_repetition/run_1_summary.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/qa_repetition/run_2_summary.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/qa_repetition/run_2_summary.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/qa_repetition/run_2_summary.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/qa_repetition/run_2_summary.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/qa_repetition/run_3_summary.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/qa_repetition/run_3_summary.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/qa_repetition/run_3_summary.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/qa_repetition/run_3_summary.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/qa_repetition/run_4_summary.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/qa_repetition/run_4_summary.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/qa_repetition/run_4_summary.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/qa_repetition/run_4_summary.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/qa_repetition/run_5_summary.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/qa_repetition/run_5_summary.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/qa_repetition/run_5_summary.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/qa_repetition/run_5_summary.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/replay_log.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/replay_log.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/replay_log.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/replay_log.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/replay_manifest.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/replay_manifest.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/replay_manifest.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/replay_manifest.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/summary.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/summary.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/glm/summary.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/glm/summary.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/summary.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/summary.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/gpt/summary.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/gpt/summary.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/summary.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/summary.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/kimi/summary.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/kimi/summary.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/cart_line_price_row.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/checkout_price_summary.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/price_label_formatter.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/product_price_tile.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/price_labels_test.dart diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/summary.md b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/summary.md similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/solver_runs/minimax/summary.md rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/solver_runs/minimax/summary.md diff --git a/tasks/flutter/refactor.price_label_formatter/deepswe/telemetry_report.json b/docs/archive/deepswe-manual-replay/refactor.price_label_formatter/telemetry_report.json similarity index 100% rename from tasks/flutter/refactor.price_label_formatter/deepswe/telemetry_report.json rename to docs/archive/deepswe-manual-replay/refactor.price_label_formatter/telemetry_report.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/README.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/README.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/README.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/README.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/README.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/README.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/README.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/README.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/command_telemetry/command_telemetry_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/command_telemetry/command_telemetry_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/command_telemetry/command_telemetry_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/command_telemetry/command_telemetry_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/f2p_checklist.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/f2p_checklist.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/f2p_checklist.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/f2p_checklist.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_report.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_report.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_report.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_report.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/README.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/README.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/README.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/README.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/baseline_expected_failure_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/baseline_expected_failure_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/baseline_expected_failure_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/baseline_expected_failure_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/flake_loop_10_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/flake_loop_10_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/flake_loop_10_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/flake_loop_10_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/glm_failed_rerun_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/glm_failed_rerun_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/glm_failed_rerun_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/glm_failed_rerun_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/gpt_failed_rerun_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/gpt_failed_rerun_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/gpt_failed_rerun_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/gpt_failed_rerun_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/kimi_failed_rerun_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/kimi_failed_rerun_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/kimi_failed_rerun_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/kimi_failed_rerun_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/minimax_failed_rerun_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/minimax_failed_rerun_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/minimax_failed_rerun_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/minimax_failed_rerun_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/opus_failed_rerun_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/opus_failed_rerun_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/opus_failed_rerun_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/opus_failed_rerun_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/reference_solution_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/reference_solution_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/reference_solution_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/flake_runs_10/reference_solution_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/leakage_audit.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/leakage_audit.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/leakage_audit.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/leakage_audit.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/leakage_scan_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/leakage_scan_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/leakage_scan_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/leakage_scan_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/model_audit.yaml b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/model_audit.yaml similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/model_audit.yaml rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/model_audit.yaml diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/p2p_checklist.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/p2p_checklist.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/p2p_checklist.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/p2p_checklist.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/prompt_verifier_bijection.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/prompt_verifier_bijection.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/prompt_verifier_bijection.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/prompt_verifier_bijection.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/qa_repetition_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/qa_repetition_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/qa_repetition_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/qa_repetition_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_1_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_1_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_1_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_1_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_2_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_2_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_2_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_2_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_3_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_3_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_3_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_3_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_4_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_4_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_4_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_4_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_5_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_5_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_5_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/qa_repetition/run_5_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/replay_log.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/replay_log.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/replay_log.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/replay_log.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/replay_manifest.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/replay_manifest.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/replay_manifest.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/replay_manifest.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/summary.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/summary.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/summary.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/glm/summary.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/summary.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/summary.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/summary.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/gpt/summary.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/summary.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/summary.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/summary.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/kimi/summary.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/summary.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/summary.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/summary.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/minimax/summary.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/summary.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/summary.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/summary.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/solver_runs/opus/summary.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/telemetry_report.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/telemetry_report.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/archive/failed_candidate_pre_contract_repair_2026_06_19/telemetry_report.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/archive/failed_candidate_pre_contract_repair_2026_06_19/telemetry_report.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/command_telemetry/command_telemetry_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/command_telemetry/command_telemetry_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/command_telemetry/command_telemetry_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/command_telemetry/command_telemetry_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/f2p_checklist.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/f2p_checklist.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/f2p_checklist.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/f2p_checklist.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/flake_report.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_report.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/flake_report.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_report.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/README.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/README.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/README.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/README.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/baseline_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/baseline_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/baseline_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/baseline_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/flake_loop_10_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/flake_loop_10_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/flake_loop_10_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/flake_loop_10_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/glm_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/glm_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/glm_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/glm_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/gpt_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/gpt_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/gpt_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/gpt_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/kimi_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/kimi_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/kimi_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/kimi_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/minimax_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/minimax_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/minimax_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/minimax_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/reference_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/reference_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/flake_runs_10/reference_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/flake_runs_10/reference_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/leakage_audit.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/leakage_audit.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/leakage_audit.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/leakage_audit.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/leakage_scan_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/leakage_scan_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/leakage_scan_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/leakage_scan_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/model_audit.yaml b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/model_audit.yaml similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/model_audit.yaml rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/model_audit.yaml diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/p2p_checklist.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/p2p_checklist.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/p2p_checklist.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/p2p_checklist.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/prompt_verifier_bijection.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/prompt_verifier_bijection.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/prompt_verifier_bijection.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/prompt_verifier_bijection.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/qa_repetition/qa_repetition_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/qa_repetition/qa_repetition_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/qa_repetition/qa_repetition_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/qa_repetition/qa_repetition_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/qa_repetition/run_1_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/qa_repetition/run_1_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/qa_repetition/run_1_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/qa_repetition/run_1_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/qa_repetition/run_2_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/qa_repetition/run_2_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/qa_repetition/run_2_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/qa_repetition/run_2_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/qa_repetition/run_3_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/qa_repetition/run_3_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/qa_repetition/run_3_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/qa_repetition/run_3_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/qa_repetition/run_4_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/qa_repetition/run_4_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/qa_repetition/run_4_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/qa_repetition/run_4_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/qa_repetition/run_5_summary.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/qa_repetition/run_5_summary.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/qa_repetition/run_5_summary.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/qa_repetition/run_5_summary.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/replay_log.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/replay_log.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/replay_log.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/replay_log.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/replay_manifest.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/replay_manifest.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/replay_manifest.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/replay_manifest.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/summary.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/summary.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/glm/summary.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/glm/summary.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/summary.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/summary.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/gpt/summary.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/gpt/summary.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/summary.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/summary.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/kimi/summary.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/kimi/summary.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/rerun_result.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/rerun_result.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/rerun_result.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/rerun_result.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/solver.patch b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/solver.patch similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/solver.patch rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/solver.patch diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_input.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_meta.json diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/trajectory/subagent_output.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/instruction.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/lib/responsive_action_bar.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/pubspec.yaml diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/solver_report.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/rerun_2026_06_19/workspace_snapshot/test/responsive_action_bar_test.dart diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/summary.md b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/summary.md similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/solver_runs/minimax/summary.md rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/solver_runs/minimax/summary.md diff --git a/tasks/flutter/ui.action_bar_overflow/deepswe/telemetry_report.json b/docs/archive/deepswe-manual-replay/ui.action_bar_overflow/telemetry_report.json similarity index 100% rename from tasks/flutter/ui.action_bar_overflow/deepswe/telemetry_report.json rename to docs/archive/deepswe-manual-replay/ui.action_bar_overflow/telemetry_report.json