- Add kb_indexed_folders set to track successfully indexed KB folders
- Skip re-queuing KB for indexing if already indexed and files unchanged
- Remove kb_key from indexed set when files change (forces re-index)
- Clear indexed set on KB folder deletion
- Fix hardcoded salesianos in drive_monitor prompt key (from previous commit)
- drive_monitor: replace hardcoded salesianos.gbot with dynamic bot_name
- llm/mod.rs: stop falling back to reasoning_content as content
- llm/claude.rs: same fix for Claude handler
- deepseek_r3: export strip_think_tags for reuse
- gpt_oss_20b: use strip_think_tags so all models strip tags
- gpt_oss_120b: use strip_think_tags so all models strip tags
ETag in MinIO is an MD5 content hash, so re-uploading the same content
preserves the ETag. Add last_modified comparison so config.csv changes
that don't alter content hash still get synced. Also fixes EmbeddingConfig
fallback from previous commit.
Root cause: file_states.write().await was held while trying to acquire
file_states.read().await for KB backoff check. Tokio RwLock is not
reentrant - this caused permanent deadlock.
Fix: Removed the file_states.read() backoff check. KB processor now
just checks files_being_indexed set and queues to pending_kb_index.
Backoff is handled by the KB processor itself based on fail_count.
This fixes salesianos DriveMonitor hanging for 5+ minutes every cycle.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Added debug logging at key points in check_gbkb_changes:
- ENTER with bot ID and prefix
- Object listing results
- File states lock acquisition
- New/modified file detection
- PDF detection
- File download batches
- Final remaining files download
- EXIT confirmation
This will help identify exactly where the 5-minute timeout occurs.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Added stub start_kb_processor() for non-llm builds
- Added _pending_kb_index field for non-llm builds
- Extracted KB processor logic into start_kb_processor_inner()
- Removed unused is_embedding_server_ready import
This ensures DriveMonitor compiles and runs correctly in production
where CI builds without --features llm.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Added start_kb_processor() method: long-running background task per bot
- check_gbkb_changes now queues KB folders to pending_kb_index (non-blocking)
- KB processor polls pending_kb_index and processes one at a time per bot
- Removed inline tokio::spawn from check_gbkb_changes that was causing 5min timeouts
- Added pending_kb_index field to DriveMonitor struct
This fixes salesianos DriveMonitor timeout - check_for_changes now completes
in seconds instead of hanging on KB embedding/indexing.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Added prefix filter to list_objects_v2 call: only scans {bot}.gbot/
- Removed scanning of .gbkb and .gbdialog paths which caused 5min timeouts
- This fixes salesianos DriveMonitor timeout and embed/index failure
Also fixed header detection for name,value CSV format.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Removed unconditional .skip(1) that was skipping first config line
- Added header detection: skips first line only if it looks like 'key,value' header
- Added validation to skip empty keys
- Also fixed indentation in drive_monitor gbkb file processing
This fixes the issue where config.csv changes on Drive weren't being
synced to bot_configuration database table for salesianos bot.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Add ETag tracking for config.csv files in DriveMonitor
- Only download and sync config.csv when ETag changes
- Prevents unnecessary database updates on every check
- Uses __config__ prefix for config.csv state keys
When a .gbkb file is deleted from the bucket, DriveMonitor now:
- Deletes the downloaded file from work directory
- When entire KB folder is empty, removes the folder too
- Prevents disk accumulation of orphaned knowledge base files
When a .bas file is deleted from the bucket, DriveMonitor now:
- Deletes the corresponding .ast compiled file
- Deletes .bas, .mcp.json, .tool.json files from work directory
- Removes the path from file_states tracking
This prevents stale compiled files from accumulating in production.
Fixed bug where DriveMonitor would overwrite indexed=true status after
successful compilation, causing files to be recompiled on every cycle.
Changes:
- Track successful compilations in HashSet before acquiring write lock
- Set indexed=true for successfully compiled files in merge loop
- Preserve indexed status for unchanged files
- Handle compilation failures with proper fail_count tracking
This ensures new .bas files are compiled to .ast once and the indexed
status is preserved, preventing unnecessary recompilation.
- Do not mark .bas files as indexed unconditionally
- Only set indexed=true when compile_tool() completes successfully
- Reset fail_count and last_failed_at on successful compilation
- Retry failed compilations automatically on next cycle
- Fixes permanent compilation failure state for salesianos start.bas
- Filter states by kb_folder_pattern (e.g. 'cartas/', 'proc/')
- Only apply backoff based on files in that specific KB folder
- Each KB folder has independent retry timing
- Skip re-indexing files that failed 3+ times within 1 hour
- Update file_states on indexing success (indexed=true, fail_count=0)
- Update file_states on indexing failure (fail_count++, last_failed_at=now)
- Don't skip KB indexing when embedding server not marked ready yet
- Embedding server health will be detected via wait_for_server() in kb_indexer
- Remove drive_monitor bypass of embedding check - let kb_indexer handle it
- Remove hardcoded URL list for remote API detection
- Try /health first, then probe with HEAD if 404/405
- Re-enable embedding server ready check in drive_monitor
- No more embedding_key hack that skipped health checks entirely
- Bug 1: check_gbkb_changes now preserves indexed=true from previous
state when etag matches, preventing redundant re-indexing every cycle
- Bug 2: USE KB fallback uses bot_id_short (8 chars) instead of random
UUID, matching the collection name convention used by DriveMonitor
- Bug 3: handle_gbkb_change now upserts into kb_collections table after
successful indexing, so USE KB can find the collection at runtime
- Changed ON CONFLICT DO NOTHING to DO UPDATE for kb_collections inserts
- Changed process_gbkb_folder return type to Result<IndexingResult>
File states were stored under /opt/gbo/work/{UUID}/file_states.json
but should be under /opt/gbo/work/{bucket_name}/file_states.json
like other bot data (e.g. /opt/gbo/work/salesianos.gbai/)
Also fixed file_states_static signature to use bucket_name consistently.
- get_work_path_default/get_stack_path no longer rely on CWD-relative botserver-stack check which caused wrong output path in production when CI left that directory
- DriveMonitor now marks .bas file states as indexed=true after list+compile cycle
- Added compile_tool logging for work_dir path
- Removed duplicate file_state_path() and load_file_states() methods
- Kept only new save_file_states_static() helper
- Original methods still exist at lines 79-84 and 87-128
- Fixes compilation errors from previous commit
- Added static save_file_states_static() helper method
- Changed tokio::spawn calls to use Arc::clone instead of Arc::new(self.clone())
- This prevents double Arc wrapping which causes 'dispatch failure' errors
- Fixes config.csv not syncing from bucket to database for salesianos/default bots
- website_crawler_service: use QdrantConfig::from_config instead of default
- local_file_monitor: use QdrantConfig::from_config with DbPool
- kb_indexer: KbFolderMonitor now uses SecretsManager for Qdrant config
This fixes the issue where Qdrant URL was hardcoded to localhost:6333
instead of reading from Vault (gbo/vectordb).
- Update get_work_path_default() to check for .env in /opt/gbo/bin/.env
- Update get_stack_path() to check for .env in /opt/gbo/bin/.env
- Update DriveMonitor::new() to use get_work_path() instead of hardcoded path
- Update start_config_watcher() to use get_work_path() instead of hardcoded path
This fixes the issue where botserver was using development paths
(/home/rodriguez/src/gb/botserver-stack/data/system/work) in production
instead of production paths (/opt/gbo/work).
- When system-prompt-file is configured in config.csv, download the file from MinIO
- Save to {bot}.gbai/{bot}.gbot/ folder in work directory
- Config loaded from MinIO (gbo-* buckets)
- Without local-files feature: only MinIO/Drive is used as bot source
- With local-files feature: scans /opt/gbo/data for bots (default behavior)
- Bucket filtering (gbo-*) only active when local-files is NOT enabled
- LocalFileMonitor and ConfigWatcher only start with local-files feature
- Disable LocalFileMonitor and ConfigWatcher - use S3/MinIO only
- Filter S3 buckets to gbo-*.gbai prefix
- Auto-create bots in database when new S3 buckets discovered
- Change file paths to use work directory instead of /opt/gbo/data
- Add RunQueryDsl import for Diesel queries
- Remove LocalFileMonitor and ConfigWatcher for /opt/gbo/data
- Remove /opt/gbo/data from mount_all_bots() scanning
- Change start.bas, tables.bas, and tool paths to use work directory
- Filter drive buckets to only gbo-* prefix
- Remove unused create_bot_simple method
- Fix all warnings (unused imports, variables, dead code)
- Adds get_stack_path() helper: returns /opt/gbo in production (.env without botserver-stack), ./botserver-stack in dev
- Adds get_work_path() helper: returns /opt/gbo/work in production, ./botserver-stack/data/system/work in dev
- Updated 35+ files to use dynamic path resolution
- Production system container no longer needs botserver-stack directory
- Work files go to /opt/gbo/work instead of /opt/gbo/bin/botserver-stack
- Fix double_ended_iterator_last: use next_back() instead of last()
- Fix manual_clamp: use .clamp() instead of min().max()
- Fix too_many_arguments: create KbInjectionContext struct
- Fix needless_borrow: remove unnecessary & reference
- Fix let_and_return: return value directly
- Fix await_holding_lock: drop guard before await
- Fix collapsible_else_if: collapse nested if-else
All changes verified with cargo clippy (0 warnings, 0 errors)
Note: Local botserver crashes with existing panic during LocalFileMonitor initialization
This panic exists in original code too, not caused by these changes
- Remove all std::env::var calls except VAULT_* and PORT
- get_from_env returns hardcoded defaults only (no env var reading)
- Auth config, rate limits, email, analytics, calendar all use Vault
- WORK_PATH replaced with get_work_path() helper reading from Vault
- .env on production cleaned to only VAULT_ADDR, VAULT_TOKEN, VAULT_CACERT, PORT
- All service IPs/credentials stored in Vault secret/gbo/*
