- Track tool_was_executed flag in stream_response
- Send empty content in final is_complete message when tool already sent results
- Prevents the LLM's pre-tool text from appearing twice in the chat UI
- DB message saving is unaffected (uses full_response_clone before the check)
- Change BOTSERVER_PORT to PORT for consistency with .env.embedded
- Update default port from 8080 to 9000 in config
- Fix service port references in security integration
- Update directory setup ExternalPort to 9000
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Add tool_call_buffer to accumulate JSON chunks across multiple LLM responses
- Handle incomplete tool call JSON that spans multiple chunks
- Convert SELECT...CASE/END SELECT to Rhai match expressions
- Fix NOT IN operator conversion to !in for IF conditions
Fixed issue where LLM tool calls returned as JSON arrays were not being
detected and were displayed as raw JSON in the chat instead of being executed.
The parse_tool_call method now handles:
- Single tool call objects
- Arrays of tool calls (OpenAI standard format)
This prevents tool call JSON from appearing in the chat window and ensures
tools are executed properly.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add error and warning logs to help diagnose why session tools are not
working in production. Logs now show:
- Number of tools loaded successfully
- Detailed error messages when tool loading fails
- Bot name lookup failures
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This loads and sends the available tools to the client when establishing
a WebSocket connection. Tools are loaded based on the bot configuration
and sent in the initial welcome message.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Changed default model from 'gpt-3.5-turbo' to 'DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_M.gguf'
in bot message handler. This ensures the local llama-server receives the correct model
name and can process requests properly.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Modified get_bot_pool() to automatically create the database for a bot
if it doesn't exist, instead of failing with "No database configured" error.
This fixes the issue where bots created after the initial sync don't have
a database_name set in the bots table, causing table creation to fail.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Add vector_db_health_check() function to verify Qdrant availability
- Add wait loop for vector_db startup in bootstrap (15 seconds)
- Fallback to local LLM when external URL configured but no API key provided
- Prevent external LLM (api.z.ai) usage without authentication key
This fixes the production issues:
- Qdrant vector database not available at https://localhost:6333
- External LLM being used instead of local when no key is configured
- Ensures vector_db is properly started and ready before use
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
The previous /dev/tcp test was giving false positives, reporting that
Valkey was running when it was actually down. This caused bootstrap to
skip starting Valkey, leading to botserver hanging on cache connection.
Changes:
- Use nc (netcat) with -z flag for reliable port checking
- Final fallback: /dev/tcp with actual PING/PONG verification
- Only returns true if port is open AND responds correctly
This ensures cache_health_check() accurately reports Valkey status.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Try valkey-cli first (preferred for Valkey installations)
- Fall back to redis-cli (for Redis installations)
- Fall back to TCP connection test (works for both)
This fixes environments that only have Valkey installed without
Redis symlinks or redis-cli.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Fix component name mismatch: "redis" -> "cache" in bootstrap_manager
- Add cache_health_check() function to verify Valkey is responding
- Add health check loop after starting cache (12s wait with PING test)
- Ensures cache is ready before proceeding with bootstrap
This fixes the issue where botserver would hang waiting for cache
connection because the cache component was never started.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Binaries at cache/bin/valkey-server (correct production path)
- Use --strip-components=1 for extraction
- Matches /opt/gbo/bin/botserver-stack/bin/cache/bin/
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Use --strip-components=2 to flatten tarball structure
- Binaries go to cache/valkey-server (not cache/bin/valkey-server)
- Matches production path: /opt/gbo/bin/botserver-stack/bin/cache/
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Binary is at cache/bin/bin/valkey-server after extraction
- Update exec_cmd and check_cmd to use bin/ subdirectory
- Create symlinks at parent level for convenience
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Use valkey-server and valkey-cli directly
- No redis compatibility symlinks needed
- Simplifies installation
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Escape format placeholders in designer_ai.rs ({{botname}})
- Remove undefined 'prefix' filter in drive_monitor
- Fix type mismatch in use_tool.rs (str vs &String)
- Remove unused TextExpressionMethods import
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Add TLS certificate generation to Vault post-install commands (CA, server, client, PostgreSQL)
- Add initialize_vault_local() function to handle Vault initialization for local installs
- Add ensure_env_file_exists() function to create .env when Vault already initialized
- Modify start() method to call Vault initialization after successful start (local mode)
- Fix Vault CLI flags: use -tls-skip-verify (not -skip-verify or -skip-tls-verify)
This restores the behavior where .env is automatically created with VAULT_ADDR,
VAULT_TOKEN, and VAULT_CACERT during local bootstrap, matching the LXC container
deployment behavior in facade.rs.
Fixes issue where .env file was only created for LXC deployments but not for
local installations.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Enhanced conversational input handling for batismo tool
- Improved keyword extraction and format recognition
- Fixed field extraction from informal user messages
- Better natural language understanding
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Add Redis-based tracking to prevent start.bas from running repeatedly
when clicking suggestion buttons. start.bas now executes only once per
session with a 24-hour expiration on the tracking key.
- Add generic tool executor (ToolExecutor) for parsing and executing
tool calls from any LLM provider. Works with Claude, OpenAI, and
other providers that use standard tool calling formats.
- Update both start.bas execution paths (WebSocket handler and LLM
message handler) to check Redis before executing.
- Fix suggestion duplication by clearing suggestions from Redis after
fetching them.
- Add rate limiter for LLM API calls.
- Improve error handling and logging throughout.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Check BOTSERVER_PORT env var before database config
- Override server_port from database if BOTSERVER_PORT is set
- Apply to both from_database() and from_env() config paths
- Allows easy port configuration via environment variable
- Use local pg_isready path when available (./botserver-stack/bin/tables/bin/pg_isready)
- Fall back to system pg_isready if local binary not found
- Prevents 30-second timeout during bootstrap when PostgreSQL is actually running
- Applied to both readiness checks in start_all() method
- Removed -d 'postgres' parameter from pg_isready health checks
- Health check now only verifies server connection on port 5432
- Fixes false positive failures when PostgreSQL is running but specific database has issues
- PostgreSQL logs showed 'database system is ready' but health check was failing
Add pg_isready health check to the 'already running' branch to ensure
PostgreSQL is properly detected as ready, even when running as a
non-interactive user (sudo -u gbuser).
This complements the previous fix for fresh PostgreSQL starts.
Changed pg_isready checks from '-U gbuser' to '-d postgres' to properly
detect PostgreSQL readiness during bootstrap. The gbuser database doesn't
exist yet during startup, causing pg_isready to fail and bootstrap to timeout.
This fixes the issue when running botserver as a non-interactive user
(e.g., sudo -u gbuser).
Fix the SQL query in check_and_crawl_websites() to also include crawl_status
in the SELECT clause. The WebsiteCrawlRecord struct expects this field but it was
only present in the WHERE clause, causing Diesel to fail with
'Column crawl_status was not present in query'.
This resolves the second website crawler service error.
Fix the SQL query in check_and_crawl_websites() to include next_crawl in the
SELECT clause. The WebsiteCrawlRecord struct expects this field but it was
missing, causing Diesel to fail with 'Column next_crawl was not present in query'.
This resolves the website crawler service error that was preventing websites
from being properly queried and recrawled.
- Fix ConfigManager to treat 'none', 'null', 'n/a', and empty values as placeholders
and fall back to default bot's configuration instead of using these as literal values
- Fix ConfigManager to detect local file paths (e.g., .gguf, .bin, ../) and fall back
to default bot's model when using remote API, allowing bots to keep local model
config for local LLM server while automatically using remote model for API calls
- Fix get_default_bot() to return the bot actually named 'default' instead of
the first active bot by ID, ensuring consistent fallback behavior
- Add comprehensive debug logging to trace LLM configuration from database to API call
This fixes the issue where bots with incomplete or local LLM configuration would
fail with 401/400 errors when trying to use remote API, instead of automatically
falling back to the default bot's configuration from config.csv.
Closes: #llm-config-fallback
- Modify bootstrap to read .valid file and validate templates before loading
- Templates not in .valid file are skipped during bootstrap
- Backward compatible: if .valid file missing, all templates are loaded
- Enables controlled template loading during bootstrap
- Add search_enabled field to ProductConfig to control omnibox visibility (defaults to false)
- Add menu_launcher_enabled field to ProductConfig to control apps menu button visibility (defaults to false)
- Update .product file to set both directives to false by default
- Update get_product_config_json to include new fields in API response
- Parse search_enabled and menu_launcher_enabled from .product file with support for true/false, 1/0, yes/no values
This allows disabling the suite search mechanism and hiding the menu launcher when empty,
providing a cleaner UI for deployments that don't need these features.
- Extract bot_name from WebSocket query parameters
- Look up bot_id from bot_name using database
- Pass bot_id to WebSocket message handler
- Use session's bot_id for LLM configuration instead of client-provided bot_id
- Fixes issue where client sends 'default' bot_id when accessing /edu
- Fixed 'relation session_kb_associations does not exist' error in core consolidated migration.
- Renamed migration directories from timestamp-based to version-based (6.0.x, 6.1.x, 6.2.x).
- Reorganized migrations into dedicated feature folders (products, dashboards, learn, video).
- Updated migration execution order in core/shared/utils.rs.
- Moves legacy migrations to 6.0.x/6.1.x and workflow to 6.2.0.
