bsiggel/motia-iii
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: ensure syncStatus is reset to 'synced' for unchanged files in Advoware sync process

Browse Source
This commit is contained in:
bsiggel
2026-03-31 10:40:14 +00:00
parent f9c8aa7c6d
commit 9639a375a6
3 changed files with 44 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
services/advoware_document_sync_utils.py
View File

@@ -333,13 +333,10 @@ class AdvowareDocumentSyncUtils:
if history_erstellung and history_erstellung != espo_erstellung: if history_erstellung and history_erstellung != espo_erstellung:
updates['advowareErstellungTimestamp'] = history_erstellung updates['advowareErstellungTimestamp'] = history_erstellung
# File is confirmed in-sync (SKIP = no file changes) → reset syncStatus if unclean
if espo_doc.get('syncStatus') != 'synced':
updates['syncStatus'] = 'synced'
# Always update lastSyncTimestamp when metadata changes (EspoCRM format) # Always update lastSyncTimestamp when metadata changes (EspoCRM format)
if len(updates) > 0: if len(updates) > 0:
updates['lastSyncTimestamp'] = datetime.now().strftime('%Y-%m-%d %H:%M:%S') now_str = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
updates['lastSyncTimestamp'] = now_str
needs_update = len(updates) > 0 needs_update = len(updates) > 0

21
src/steps/akte/akte_sync_event_step.py
View File

@@ -225,6 +225,7 @@ async def _run_advoware_sync(
all_hnrs = set(espo_by_hnr.keys()) | set(history_by_hnr.keys()) all_hnrs = set(espo_by_hnr.keys()) | set(history_by_hnr.keys())
ctx.logger.info(f" Unique HNRs : {len(all_hnrs)}") ctx.logger.info(f" Unique HNRs : {len(all_hnrs)}")
now = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
# ── 3-way merge per HNR ─────────────────────────────────────────── # ── 3-way merge per HNR ───────────────────────────────────────────
for hnr in all_hnrs: for hnr in all_hnrs:
@@ -247,12 +248,22 @@ async def _run_advoware_sync(
ctx.logger.info(f" [{action.action:12s}] {filename} (hnr={hnr}) – {action.reason}") ctx.logger.info(f" [{action.action:12s}] {filename} (hnr={hnr}) – {action.reason}")
if action.action == 'SKIP': if action.action == 'SKIP':
# Even for unchanged files: sync metadata from History (art, text, hnr, dat) # Even for unchanged files: sync metadata from History (art, text, dat)
if espo_doc and history_entry: # and always reset syncStatus if not already synced.
if espo_doc:
extra: Dict[str, Any] = {}
if history_entry:
needs_meta_update, meta_updates = sync_utils.should_sync_metadata(espo_doc, history_entry) needs_meta_update, meta_updates = sync_utils.should_sync_metadata(espo_doc, history_entry)
if needs_meta_update: else:
await espocrm.update_entity('CDokumente', espo_doc['id'], meta_updates) needs_meta_update, meta_updates = False, {}
ctx.logger.info(f" [META UPDATE ] {filename} (hnr={hnr}) – {list(meta_updates.keys())}") # File confirmed in-sync by 3-way merge → always ensure syncStatus=synced
if espo_doc.get('syncStatus') != 'synced':
extra['syncStatus'] = 'synced'
extra['lastSyncTimestamp'] = now
combined = {**meta_updates, **extra}
if combined:
await espocrm.update_entity('CDokumente', espo_doc['id'], combined)
ctx.logger.info(f" [META UPDATE ] {filename} (hnr={hnr}) – {list(combined.keys())}")
results['updated'] += 1 results['updated'] += 1
else: else:
results['skipped'] += 1 results['skipped'] += 1

33
src/steps/crm/akte/akte_sync_event_step.py
View File

@@ -264,12 +264,22 @@ async def _run_advoware_sync(
ctx.logger.info(f" [{action.action:12s}] {filename} (hnr={hnr}) – {action.reason}") ctx.logger.info(f" [{action.action:12s}] {filename} (hnr={hnr}) – {action.reason}")
if action.action == 'SKIP': if action.action == 'SKIP':
# Even for unchanged files: sync metadata from History (art, text, hnr, dat) # Even for unchanged files: sync metadata from History (art, text, dat)
if espo_doc and history_entry: # and always reset syncStatus if not already synced.
if espo_doc:
extra: Dict[str, Any] = {}
if history_entry:
needs_meta_update, meta_updates = sync_utils.should_sync_metadata(espo_doc, history_entry) needs_meta_update, meta_updates = sync_utils.should_sync_metadata(espo_doc, history_entry)
if needs_meta_update: else:
await espocrm.update_entity('CDokumente', espo_doc['id'], meta_updates) needs_meta_update, meta_updates = False, {}
ctx.logger.info(f" [META UPDATE ] {filename} (hnr={hnr}) – {list(meta_updates.keys())}") # File confirmed in-sync by 3-way merge → always ensure syncStatus=synced
if espo_doc.get('syncStatus') != 'synced':
extra['syncStatus'] = 'synced'
extra['lastSyncTimestamp'] = now
combined = {**meta_updates, **extra}
if combined:
await espocrm.update_entity('CDokumente', espo_doc['id'], combined)
ctx.logger.info(f" [META UPDATE ] {filename} (hnr={hnr}) – {list(combined.keys())}")
results['updated'] += 1 results['updated'] += 1
else: else:
results['skipped'] += 1 results['skipped'] += 1
@@ -361,10 +371,10 @@ async def _run_advoware_sync(
if erstellung_dat: if erstellung_dat:
update_data['advowareErstellungTimestamp'] = erstellung_dat update_data['advowareErstellungTimestamp'] = erstellung_dat
# Mark for re-sync to xAI only if file content actually changed # Mark for re-sync to AI if file content actually changed
# (USN can change without content change, e.g. metadata-only updates) # (USN can change without content change, e.g. metadata-only updates)
content_changed = blake3_hash != espo_doc.get('syncedHash', '') content_changed = blake3_hash != espo_doc.get('syncedHash', '')
if content_changed and espo_doc.get('aiSyncStatus') == 'synced': if content_changed and espo_doc.get('aiSyncStatus') in ('synced', 'failed'):
update_data['aiSyncStatus'] = 'unclean' update_data['aiSyncStatus'] = 'unclean'
await espocrm.update_entity('CDokumente', espo_doc['id'], update_data) await espocrm.update_entity('CDokumente', espo_doc['id'], update_data)
results['updated'] += 1 results['updated'] += 1
@@ -786,13 +796,18 @@ async def _run_ragflow_sync(
ctx.logger.info(f" ✅ RAGflow-ID: {new_ragflow_id}") ctx.logger.info(f" ✅ RAGflow-ID: {new_ragflow_id}")
now_str = datetime.now().strftime('%Y-%m-%d %H:%M:%S') now_str = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
await espocrm.update_entity('CDokumente', doc_id, { # Reset aiParsingStatus so the parsing cron re-polls the new upload
is_new_upload = new_ragflow_id != (ragflow_doc.get('id') if ragflow_doc else None)
espo_update: Dict[str, Any] = {
'aiFileId': new_ragflow_id, 'aiFileId': new_ragflow_id,
'aiCollectionId': dataset_id, 'aiCollectionId': dataset_id,
'aiSyncHash': blake3_hash, 'aiSyncHash': blake3_hash,
'aiSyncStatus': 'synced', 'aiSyncStatus': 'synced',
'aiLastSync': now_str, 'aiLastSync': now_str,
}) }
if is_new_upload:
espo_update['aiParsingStatus'] = 'unknown'
await espocrm.update_entity('CDokumente', doc_id, espo_update)
synced += 1 synced += 1
except Exception as e: except Exception as e: