- Add Redis-backed message queue with per-recipient tracking
- Enforce 1 message per 6 seconds per recipient (0.17 msg/s)
- Support burst mode: up to 45 messages in 6-second window
- Implement proportional cooldown after burst
- Add exponential backoff retry on error 131056 (4^X seconds)
- Update botbook with official Meta rate limits
- Add unit tests for burst mode and rate limiting
- Fix config inheritance bug: delete all keys before sync
- Add resolve_bot_by_phone_number_id function for automatic routing
- Webhooks now route to correct bot based on whatsapp-phone-number-id
- Enables multiple WhatsApp numbers to use single webhook URL
- Falls back to default bot if no match found
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Move system_prompt retrieval inside spawn_blocking closure
- Include system_prompt in the return tuple to fix scope issue
- Add trace logging for debugging system-prompt loading
- GLM-5 and other LLM providers now correctly receive custom system prompts
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Split list detection into numbered and bullet list items
- Add looks_like_list_start() to detect when list is beginning
- Add looks_like_list_end() to detect when list has ended
- Add split_text_before_list() to separate text before list
- Add split_list_from_text() to separate list from text after
- Update streaming logic to send lists as isolated messages
- Add code block removal (triple backticks and inline backticks)
- Add comprehensive unit tests for list detection functions
Resolves: Lists being mixed with other text in WhatsApp messages
Resolves: JavaScript/C# code leaking into WhatsApp messages
- Add /clear command handler to allow users to clear their conversation history
- Implement clear_session_history() function using diesel delete
- Remove dead code (unused list processing functions)
- Add message deduplication using Redis cache
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Accumulate all content before sending (no chunking)
- Only send when is_final = true
- Fixes list (li/ul) handling - lists sent as one complete message
- Improves WhatsApp user experience by sending complete formatted responses
- Removes complex chunked logic in favor of simplicity
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Lower score_threshold in kb_indexer.rs from 0.5 to 0.3
- Lower website search threshold in kb_context.rs from 0.6 to 0.4
- Lower KB search threshold in kb_context.rs from 0.7 to 0.5
- Add Cloudflare AI (/ai/run/) URL detection in cache.rs
- Add Cloudflare AI request format ({"text": ...}) in cache.rs
- Add Cloudflare AI response parsing (result.data) in cache.rs
This fixes the issue where KB search returned 0 results even with
114 chunks indexed. The high thresholds were filtering out all results.
- Lower score_threshold in kb_indexer.rs from 0.5 to 0.3
- Lower website search threshold in kb_context.rs from 0.6 to 0.4
- Lower KB search threshold in kb_context.rs from 0.7 to 0.5
- Add Cloudflare AI (/ai/run/) URL detection in cache.rs
- Add Cloudflare AI request format ({"text": ...}) in cache.rs
- Add Cloudflare AI response parsing (result.data) in cache.rs
This fixes the issue where KB search returned 0 results even with
114 chunks indexed. The high thresholds were filtering out all results.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added api_key field to LocalEmbeddingService for authentication
- Added embedding-key config parameter support in bootstrap
- Smart URL handling: doesn't append /embedding for full URLs (HuggingFace, OpenAI, etc.)
- Detects HuggingFace URLs and uses correct request format (inputs instead of input/model)
- Handles multiple response formats:
- HuggingFace: direct array [0.1, 0.2, ...]
- Standard/OpenAI: {"data": [{"embedding": [...]}]}
- Added Authorization header with Bearer token when api_key is provided
- Improved error messages with full response details
Fixes embedding errors when using HuggingFace Inference API
- Enhanced error messages in LocalEmbeddingService to show actual HTTP status and response
- Added semantic-cache-enabled config parameter to disable semantic matching when embedding service unavailable
- Improved error logging with full response details for debugging production issues
- Prevents 'Invalid embedding response' errors by allowing graceful fallback
- Updated get_tool_bas_path to look in /opt/gbo/data (source) first
- Then check botserver-stack/data/system/work (compiled) second
- Removed incorrect $HOME/data and $HOME/gb/work paths
- Fixes 'Tool file not found' error when executing inscricao tool
According to AGENTS.md architecture:
- Bots are in /opt/gbo/data primary
- They are compiled into work directory by local_file_monitor
- tool_executor was looking in wrong directories
- Add API endpoints to deployment/mod.rs:
- GET /api/deployment/targets - List available deployment targets
- POST /api/deployment/deploy - Deploy application to selected target
- Register deployment routes in main application router
- Support for internal GB Platform and external Forgejo deployments
- Proper error handling with ErrorSanitizer
- SQL injection protection with sql_guard
Phase 0: Deployment Infrastructure - COMPLETE ✅
Phase 1: Code Editor Integration
- Add Monaco Editor to vendor directory
- Create editor.html component with full Monaco integration
- Create API endpoints for file operations (editor.rs)
- GET /api/editor/file/:file_path - Read file
- POST /api/editor/file/:file_path - Save file
- GET /api/editor/files - List files
- Features:
- File tree sidebar
- Multi-file tabs
- Syntax highlighting for 10+ languages
- Auto-save with WebSocket sync preparation
- Keyboard shortcuts (Ctrl+S, Ctrl+P)
- Status bar with language, encoding, cursor position
- Custom GB dark theme
- Publish integration with deployment modal
- Add detailed logging for all 5 pipeline stages (PLAN, BUILD, REVIEW, DEPLOY, MONITOR)
- Log stage start/complete events with agent IDs and progress details
- Add resource creation/deletion logging in drive_handlers
- Improve pipeline summary logging with task ID, nodes, resources, and URL
This addresses the requirement for textual progress in console logs.
- Fix PAT extraction timing with retry loop (waits up to 60s for PAT in logs)
- Add sync command to flush filesystem buffers before extraction
- Improve logging with progress messages and PAT verification
- Refactor setup code into consolidated setup.rs module
- Fix YAML indentation for PatPath and MachineKeyPath
- Change Zitadel init parameter from --config to --steps
The timing issue occurred because:
1. Zitadel writes PAT to logs at startup (~18:08:59)
2. Post-install extraction ran too early (~18:09:35)
3. PAT file wasn't created until ~18:10:38 (63s after installation)
4. OAuth client creation failed because PAT file didn't exist yet
With the retry loop:
- Waits for PAT to appear in logs with sync+grep check
- Extracts PAT immediately when found
- OAuth client creation succeeds
- directory_config.json saved with valid credentials
- Login flow works end-to-end
Tested: Full reset.sh and login verification successful
- Updated error message to explain when credentials are found but invalid
- Clarified that credentials might be from a previous installation
- Added step-by-step solution for resetting credentials
- Removed misleading 'No admin credentials found' message
The error now accurately reflects the actual problem: authentication
failure rather than missing credentials.
- Added OAuth client creation to the 'already running' branch
- Previously, OAuth client was only created when Zitadel was started
- This fixes the issue where OAuth client wasn't created on subsequent runs
Fixes the OAuth client creation issue discovered during testing.
- Updated setup_directory() to read credentials from saved file
- Added read_saved_credentials() to parse ~/.gb-setup-credentials
- Added get_admin_credentials() to try multiple sources
- Removed default credentials approach (doesn't work)
- Improved error messages with solution steps
This matches the working approach from commit 86cfccc2 where
credentials were saved during first bootstrap and reused for
OAuth client creation on subsequent runs.
Fixed compilation errors by adding .await to all ensure_admin_token() calls:
- create_organization()
- create_user()
- save_config()
The method was made async but the calls weren't updated.
- Add password grant authentication support in DirectorySetup
- Extract initial admin credentials from Zitadel log file
- Fix race condition in Zitadel startup (wait for health check before starting)
- Create parent directories before saving config
- Add retry logic for OAuth client creation
- Improve error handling with detailed messages
Fixes authentication service not configured error after bootstrap.
Updated all hardcoded work/ directory references to use the correct
relative path from the current working directory:
- botserver-stack/data/system/work
This ensures consistent file location resolution regardless of where
botserver is run from (/home/rodriguez/src/gb/ or /opt/gbo/bin/).
Changes:
- local_file_monitor.rs: Use std::env::current_dir() for work_root
- drive_monitor/mod.rs: Use work_root PathBuf for tool compilation
- website_crawler_service.rs: Use std::env::current_dir() for work_path
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Added logic to create botserver-stack/data/system/work directory
if it doesn't exist. This ensures production deployments work
without manual directory setup.
Changes:
- Added fs::create_dir_all() in use_tool.rs
- Added fs::create_dir_all() in tool_context.rs
- Logs when directory is created
- Fixes production deployment where /system/work may not exist
This ensures the tool loading works in fresh production environments
where the work folder hasn't been populated yet.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changed tool loading to use relative path from current directory instead
of hardcoded HOME/gb path. This makes the code portable across different
deployment environments.
- Updated use_tool.rs to use std::env::current_dir()
- Updated tool_context.rs to use std::env::current_dir()
- Added PathBuf import to both files
- Tools now load from botserver-stack/data/system/work/
Fixes issue where tools weren't being loaded because .mcp.json files
were in a different location than expected.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fixed RCE vulnerability in trusted_shell_script_arg execution
- Fixed SSRF vulnerability in GET command with internal IP blocking
- Updated SafeCommand to use explicit positional arguments
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- 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)
- Support # as comment marker like ' in BASIC preprocessor
- Remove hardcoded column lists from get_table_field_names()
- Let runtime use database schema dynamically via get_table_columns()
- Fix SELECT/CASE conversion to add semicolons to body statements
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- 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>
Remove actions/checkout with custom path that causes multiple workspace
roots error. Clone botserver repository directly in Setup Workspace step
instead of using checkout action.
Fixes error: "multiple workspace roots found in the same workspace"
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>
