--- updatedAt: 2026-04-14T09:45:29.000Z agentTools: projectIndex: https://developers.newo.ai/llms.txt --- # The turn pipeline The turn pipeline is the processing loop that runs every time a user sends a message. It is the foundation that connects all other systems in the Agent Framework — the Observer, the Tool Caller, and V2V backward prompting are all components of this pipeline. Understanding it makes every other article in this section easier to follow. ## How the turn pipeline works ``` User sends a message │ ▼ CAMainFlow assembles prompt and generates response │ ▼ broadcast_analyze_conversation event fires │ ├──► CAObserverFlow (queue) │ Extracts user info, evaluates quality │ ├──► CAThoughtsFlow (interrupt) │ Generates KEY DIRECTIVES for the next turn │ └──► CANewoToolCaller (queue) Detects action commitments, fires tools ▼ (outputs stored as attributes) Next turn: CAMainFlow reads updated directives and context ``` ## Step-by-step walkthrough ### 1. Event received When a user sends a message on any channel — phone, chat, Telegram, WhatsApp, or webcall — the platform fires a `user_message` event. For new conversations, a `conversation_started` event fires first and initializes the session. ### 2. CAMainFlow assembles the prompt and generates a response The ConvoAgent's primary flow (`CAMainFlow`) picks up the incoming event and assembles a full context prompt from multiple sources: * The agent's business context, scenarios, and procedures * The compiled intent type map (working-hours or non-working-hours variant) * KEY DIRECTIVES generated by the Observer on the previous turn * Current booking and calendar action states * RAG context, if enabled With this context assembled, the ConvoAgent generates a response and sends it back to the user. ### 3. broadcast\_analyze\_conversation fires After the ConvoAgent generates its response, `CAMainFlow` fires the `broadcast_analyze_conversation` system event. This event has three subscribers that all run at the same time. ### 4. Three flows run in parallel | **Flow** | **Interrupt mode** | **What it does** | | :----------------- | :----------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------- | | `CAObserverFlow` | queue | Extracts user information (name, phone, email, language, opt-in preferences) from the latest exchange. Evaluates conversation quality on voice channels. | | `CAThoughtsFlow` | interrupt | Assembles the full supervisor context and generates KEY DIRECTIVES — structured step-by-step instructions for what the ConvoAgent should do next. | | `CANewoToolCaller` | queue | Analyzes the ConvoAgent's latest response for action commitments. Detects matching tools, resolves conflicts, and fires execution flows. | **Queue vs interrupt mode:** `CAThoughtsFlow` runs in **interrupt** mode, meaning if a new `broadcast_analyze_conversation` event arrives before thought generation finishes, the in-progress run is cancelled and restarted with the latest conversation state. This ensures KEY DIRECTIVES always reflect the most recent exchange. The other two flows run in **queue** mode — they complete the current run before processing a new event. ### 5. Outputs feed into the next turn Each flow's outputs become inputs for the following turn: **CAObserverFlow outputs:** * Extracted user information (name, phone, email, language, opt-in status) stored as persona attributes * Working hours status * Conversation quality flag (triggers recovery actions if score ≤ 3) **CAThoughtsFlow outputs:** * KEY DIRECTIVES stored as a persona attribute. On the next turn, `CAMainFlow` reads these and injects them into the ConvoAgent's prompt as `` — telling the agent exactly which scenario step to execute next. **CANewoToolCaller outputs:** * Tool execution flows fire (e.g., `CACheckingAvailabilityFlow`, `CAActionSendSMSInformationFlow`, `CAActionCallTransferFlow`). These flows perform backend operations and may inject results back into the conversation via urgent messages or updated persona attributes. ## Waiting mode When a tool execution flow performs an operation that takes time — such as checking booking availability — the system enters **waiting mode** to prevent the ConvoAgent from acting on stale directives: 1. `convoagent_activate_waiting_mode` event fires, pausing thought generation 2. If the user sends another message while waiting, the ConvoAgent responds without updated KEY DIRECTIVES 3. When the tool result arrives, an `urgent_message` event re-enables thought generation, and the next turn's directives incorporate the result This prevents the Observer from generating directives that don't yet account for a pending tool result. ## How the pipeline shapes agent behavior Each turn is self-contained. The ConvoAgent generates a response based on whatever directives and context existed at the start of that turn. The parallel flows then update those directives for the next turn. This creates a continuously updated guidance loop: | **Turn** | **ConvoAgent response** | **Parallel output** | | :------- | :--------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------- | | 1 | Greets user, identifies intent | Observer detects language; Thoughts set Scenario 0 → Scenario 1 routing | | 2 | Asks for phone number (Step 1.1) | Observer stores phone number; Thoughts advance to Step 1.2 | | 3 | Asks for name (Step 1.2) | Observer stores name; Thoughts advance to Step 1.3 | | 4 | Says code-phrase: "Let me check availability for Friday at 7 PM" | Tool Caller detects `check_availability_tool`; fires `CACheckingAvailabilityFlow`; waiting mode activates | | 5 | Receives availability result | Observer updates availability context; Thoughts instruct ConvoAgent to confirm or offer alternatives | ## See also * **The Observer system** — Full reference for `CAObserverFlow` and `CAThoughtsFlow`, including KEY DIRECTIVES format, field tracking, and quality scoring * **The Supervisor and Tool Caller system** — Full reference for `CANewoToolCaller`, tool compilation, condition detection, and execution pipeline * **V2V backward prompting** — How KEY DIRECTIVES are injected into voice-to-voice models mid-conversation