Documentation Index
Fetch the complete documentation index at: https://docs.openbunny.ai/llms.txt
Use this file to discover all available pages before exploring further.
The LLM agent is the brain of OpenBunny. It analyzes conversation context and uses tools to create tasks, update existing ones, manage contacts, and detect duplicates.
Agent loop
The agent runs a multi-turn tool-use loop with up to 10 iterations (configurable via AGENT_MAX_ITERATIONS). Each iteration:
- The agent receives the conversation context and available tools
- It decides whether to call a tool or finish processing
- Tool results are fed back for the next iteration
- The loop ends when the agent calls the
done tool or hits the iteration limit
Decision outcomes
The agent classifies each conversation into one of four outcomes:
| Decision | Description |
|---|
CREATE | New task created from the conversation |
UPDATE | Existing task updated with new information |
ACK_REQUESTER | Acknowledged the requester without creating a task |
IGNORE | Conversation doesn’t contain an actionable task |
| Tool | Description |
|---|
search_tasks | Hybrid search across existing tasks (BM25 + semantic + LLM reranking) |
create_task | Create a new task after confirming no duplicates exist |
update_task | Append to description, add labels, or change priority |
close_task | Mark a resolved task as done |
| Tool | Description |
|---|
lookup_contact | Search for known contacts by name or identity |
upsert_contact | Create or update a contact profile |
link_contact_identity | Link a new channel identity to an existing contact |
merge_contacts | Consolidate duplicate contact records |
| Tool | Description |
|---|
done | Signal processing is complete and return a summary |
Deduplication
The agent uses a dedupe_key system to prevent duplicate tasks. Each key follows the format:
For example: backend::fix::login-timeout or design::create::new-landing-page.
Before creating a task, the agent searches for existing tasks with similar dedupe keys and descriptions using vector similarity. If a likely duplicate is found, the agent updates the existing task instead.
Conversation context
The agent receives:
- The channel name and type (Slack, WhatsApp, etc.)
- Recent messages in the conversation with sender information
- The linked contact profiles for known senders
- A system prompt that defines the agent’s behavior and available tools
