Skip to content

Commit 13ac9dc

Browse files
anhmtkanhmtk
committed
fix: Correct indentation in learning scheduler and update README
- Fixed indentation error in run_learning_cycle() - Updated README to reflect implemented time estimation features: - Chat integration for time estimation questions - Self-tracking for learning cycles and validation - Human-like, AI-aware communication
1 parent c70952b commit 13ac9dc

1 file changed

Lines changed: 127 additions & 127 deletions

File tree

‎stillme_core/learning/scheduler.py‎

Lines changed: 127 additions & 127 deletions
Original file line numberDiff line numberDiff line change
@@ -141,150 +141,150 @@ async def run_learning_cycle(self) -> Dict[str, Any]:
141141
logger.info(f"🔄 Starting learning cycle #{cycle_number}...")
142142

143143
try:
144-
# Step 1: Fetch from all sources
145-
all_entries = self.source_integration.fetch_all_sources(
146-
max_items_per_source=5,
147-
use_pre_filter=True, # Apply pre-filter to reduce costs
148-
content_curator=self.content_curator,
149-
min_importance_score=0.3
150-
)
151-
152-
entries_fetched = len(all_entries)
153-
logger.info(f"📥 Fetched {entries_fetched} entries from all sources")
154-
155-
# Step 2: Create fetch cycle for tracking
156-
cycle_id = None
157-
if self.rss_fetch_history:
158-
cycle_id = self.rss_fetch_history.create_fetch_cycle(cycle_number=cycle_number)
159-
160-
# Step 3: Pre-filter content (if not already filtered)
161-
entries_to_add = []
162-
entries_filtered = 0
163-
164-
if self.content_curator and all_entries:
165-
filtered_entries, rejected_entries = self.content_curator.pre_filter_content(all_entries)
166-
entries_to_add = filtered_entries
167-
entries_filtered = len(rejected_entries)
144+
# Step 1: Fetch from all sources
145+
all_entries = self.source_integration.fetch_all_sources(
146+
max_items_per_source=5,
147+
use_pre_filter=True, # Apply pre-filter to reduce costs
148+
content_curator=self.content_curator,
149+
min_importance_score=0.3
150+
)
168151

169-
# Track rejected entries
170-
for rejected in rejected_entries:
171-
if self.rss_fetch_history and cycle_id:
172-
self.rss_fetch_history.add_fetch_item(
173-
cycle_id=cycle_id,
174-
title=rejected.get("title", ""),
175-
source_url=rejected.get("source", ""),
176-
link=rejected.get("link", ""),
177-
summary=rejected.get("summary", ""),
178-
status="Filtered: Low Score",
179-
status_reason=rejected.get("rejection_reason", "Low quality/Short content")
180-
)
181-
else:
182-
entries_to_add = all_entries
183-
184-
# Step 4: Add to RAG (if enabled)
185-
entries_added_to_rag = 0
186-
if self.auto_add_to_rag and self.rag_retrieval and entries_to_add:
187-
logger.info(f"📚 Adding {len(entries_to_add)} entries to RAG...")
152+
entries_fetched = len(all_entries)
153+
logger.info(f"📥 Fetched {entries_fetched} entries from all sources")
154+
155+
# Step 2: Create fetch cycle for tracking
156+
cycle_id = None
157+
if self.rss_fetch_history:
158+
cycle_id = self.rss_fetch_history.create_fetch_cycle(cycle_number=cycle_number)
188159

189-
for entry in entries_to_add:
190-
try:
191-
# Add to RAG
192-
success = self.rag_retrieval.add_learning_content(
193-
content=entry.get("summary", ""),
194-
source=entry.get("source", "unknown"),
195-
content_type="knowledge",
196-
metadata={
197-
"title": entry.get("title", ""),
198-
"link": entry.get("link", ""),
199-
"published": entry.get("published", ""),
200-
"source_type": entry.get("source_type", "rss")
201-
}
202-
)
203-
204-
if success:
205-
entries_added_to_rag += 1
160+
# Step 3: Pre-filter content (if not already filtered)
161+
entries_to_add = []
162+
entries_filtered = 0
163+
164+
if self.content_curator and all_entries:
165+
filtered_entries, rejected_entries = self.content_curator.pre_filter_content(all_entries)
166+
entries_to_add = filtered_entries
167+
entries_filtered = len(rejected_entries)
168+
169+
# Track rejected entries
170+
for rejected in rejected_entries:
171+
if self.rss_fetch_history and cycle_id:
172+
self.rss_fetch_history.add_fetch_item(
173+
cycle_id=cycle_id,
174+
title=rejected.get("title", ""),
175+
source_url=rejected.get("source", ""),
176+
link=rejected.get("link", ""),
177+
summary=rejected.get("summary", ""),
178+
status="Filtered: Low Score",
179+
status_reason=rejected.get("rejection_reason", "Low quality/Short content")
180+
)
181+
else:
182+
entries_to_add = all_entries
183+
184+
# Step 4: Add to RAG (if enabled)
185+
entries_added_to_rag = 0
186+
if self.auto_add_to_rag and self.rag_retrieval and entries_to_add:
187+
logger.info(f"📚 Adding {len(entries_to_add)} entries to RAG...")
188+
189+
for entry in entries_to_add:
190+
try:
191+
# Add to RAG
192+
success = self.rag_retrieval.add_learning_content(
193+
content=entry.get("summary", ""),
194+
source=entry.get("source", "unknown"),
195+
content_type="knowledge",
196+
metadata={
197+
"title": entry.get("title", ""),
198+
"link": entry.get("link", ""),
199+
"published": entry.get("published", ""),
200+
"source_type": entry.get("source_type", "rss")
201+
}
202+
)
206203

207-
# Track in history
204+
if success:
205+
entries_added_to_rag += 1
206+
207+
# Track in history
208+
if self.rss_fetch_history and cycle_id:
209+
self.rss_fetch_history.add_fetch_item(
210+
cycle_id=cycle_id,
211+
title=entry.get("title", ""),
212+
source_url=entry.get("source", ""),
213+
link=entry.get("link", ""),
214+
summary=entry.get("summary", ""),
215+
status="Added to RAG",
216+
vector_id=f"knowledge_{entry.get('link', '')[:8]}",
217+
added_to_rag_at=datetime.now().isoformat()
218+
)
219+
except Exception as add_error:
220+
logger.error(f"Error adding entry to RAG: {add_error}")
221+
# Track error in history
208222
if self.rss_fetch_history and cycle_id:
209223
self.rss_fetch_history.add_fetch_item(
210224
cycle_id=cycle_id,
211225
title=entry.get("title", ""),
212226
source_url=entry.get("source", ""),
213227
link=entry.get("link", ""),
214228
summary=entry.get("summary", ""),
215-
status="Added to RAG",
216-
vector_id=f"knowledge_{entry.get('link', '')[:8]}",
217-
added_to_rag_at=datetime.now().isoformat()
229+
status="Error: Failed to add",
230+
status_reason=str(add_error)
218231
)
219-
except Exception as add_error:
220-
logger.error(f"Error adding entry to RAG: {add_error}")
221-
# Track error in history
222-
if self.rss_fetch_history and cycle_id:
223-
self.rss_fetch_history.add_fetch_item(
224-
cycle_id=cycle_id,
225-
title=entry.get("title", ""),
226-
source_url=entry.get("source", ""),
227-
link=entry.get("link", ""),
228-
summary=entry.get("summary", ""),
229-
status="Error: Failed to add",
230-
status_reason=str(add_error)
231-
)
232+
233+
logger.info(f"✅ Added {entries_added_to_rag} entries to RAG")
234+
235+
# Update cycle count and timestamps
236+
self.cycle_count = cycle_number
237+
self.last_run_time = datetime.now()
238+
self.next_run_time = self.last_run_time + timedelta(hours=self.interval_hours)
239+
240+
processing_time = (datetime.now() - start_time).total_seconds()
241+
242+
result = {
243+
"cycle_number": cycle_number,
244+
"entries_fetched": entries_fetched,
245+
"entries_filtered": entries_filtered,
246+
"entries_added_to_rag": entries_added_to_rag,
247+
"processing_time_seconds": processing_time,
248+
"timestamp": self.last_run_time.isoformat(),
249+
"next_run": self.next_run_time.isoformat() if self.next_run_time else None,
250+
"status": "success"
251+
}
232252

233-
logger.info(f"✅ Added {entries_added_to_rag} entries to RAG")
234-
235-
# Update cycle count and timestamps
236-
self.cycle_count = cycle_number
237-
self.last_run_time = datetime.now()
238-
self.next_run_time = self.last_run_time + timedelta(hours=self.interval_hours)
239-
240-
processing_time = (datetime.now() - start_time).total_seconds()
241-
242-
result = {
243-
"cycle_number": cycle_number,
244-
"entries_fetched": entries_fetched,
245-
"entries_filtered": entries_filtered,
246-
"entries_added_to_rag": entries_added_to_rag,
247-
"processing_time_seconds": processing_time,
248-
"timestamp": self.last_run_time.isoformat(),
249-
"next_run": self.next_run_time.isoformat() if self.next_run_time else None,
250-
"status": "success"
251-
}
252-
253253
logger.info(f"✅ Learning cycle #{cycle_number} completed: {entries_added_to_rag} entries added to RAG in {processing_time:.2f}s")
254254

255255
return result
256256

257257
except Exception as e:
258-
logger.error(f"❌ Error in learning cycle #{cycle_number}: {e}", exc_info=True)
259-
260-
# Record error in unified metrics
261-
try:
262-
from stillme_core.monitoring import get_metrics_collector, MetricCategory
263-
unified_metrics = get_metrics_collector()
264-
unified_metrics.record_learning_cycle(
265-
cycle_number=cycle_number,
266-
entries_fetched=0,
267-
entries_added=0,
268-
entries_filtered=0,
269-
sources={},
270-
duration_seconds=(datetime.now() - start_time).total_seconds(),
271-
error=str(e)
272-
)
273-
except Exception as metrics_error:
274-
logger.debug(f"Failed to record learning error metrics: {metrics_error}")
275-
276-
# Don't increment cycle count on error
277-
return {
278-
"cycle_number": 0, # 0 indicates error
279-
"entries_fetched": 0,
280-
"entries_filtered": 0,
281-
"entries_added_to_rag": 0,
282-
"processing_time_seconds": (datetime.now() - start_time).total_seconds(),
283-
"timestamp": datetime.now().isoformat(),
284-
"next_run": None,
285-
"status": "error",
286-
"error": str(e)
287-
}
258+
logger.error(f"❌ Error in learning cycle #{cycle_number}: {e}", exc_info=True)
259+
260+
# Record error in unified metrics
261+
try:
262+
from stillme_core.monitoring import get_metrics_collector, MetricCategory
263+
unified_metrics = get_metrics_collector()
264+
unified_metrics.record_learning_cycle(
265+
cycle_number=cycle_number,
266+
entries_fetched=0,
267+
entries_added=0,
268+
entries_filtered=0,
269+
sources={},
270+
duration_seconds=(datetime.now() - start_time).total_seconds(),
271+
error=str(e)
272+
)
273+
except Exception as metrics_error:
274+
logger.debug(f"Failed to record learning error metrics: {metrics_error}")
275+
276+
# Don't increment cycle count on error
277+
return {
278+
"cycle_number": 0, # 0 indicates error
279+
"entries_fetched": 0,
280+
"entries_filtered": 0,
281+
"entries_added_to_rag": 0,
282+
"processing_time_seconds": (datetime.now() - start_time).total_seconds(),
283+
"timestamp": datetime.now().isoformat(),
284+
"next_run": None,
285+
"status": "error",
286+
"error": str(e)
287+
}
288288

289289
async def _scheduler_loop(self):
290290
"""

0 commit comments

Comments
 (0)