D1 · Agentic Architecture › Cluster 2 · Stop Reasons

2.4 · pause_turn & Server-Side Tool Loops

Resume, don't restart — and never say "Continue."

CONCEPT The server runs its own loop

Some tools — server-side tools like web search and code execution — run on Anthropic's infrastructure, not in your code. When the model uses one, the server enters its own sampling loop (roughly ~10 iterations), calling the tool and feeding results back to the model without any round-trip to you. If that internal loop is still going when a limit is reached, the response comes back with stop_reason == "pause_turn".

🔑 pause_turn means "I'm not done, but I paused." Your job is to let the server resume — re-send the assistant turn as-is and call again. The server picks up where it left off.
AspectClient-side tool (2.2)Server-side tool (this page)
Runs whereYour codeAnthropic infra
Stop signaltool_usepause_turn (when its loop pauses)
What you send backA user turn with tool_resultThe assistant turn as-is (no tool_result, no new user text)
Who loops the toolYouThe server (~10 iters)
⚠️ Do NOT append a "Continue." user message. That injects a new user turn and derails the resume. Re-send the same assistant content and call the API again.

DIAGRAM Pausing and resuming a server-side tool

flowchart TD A([call with server-side tool]) --> B{"server runs its own
loop (~10 iters)"} B -->|finished| C["🟢 stop_reason == end_turn → done"] B -->|paused| D["🟣 stop_reason == pause_turn"] D --> E["append response.content
(assistant turn) AS-IS"] E --> F{"continuations < cap?"} F -->|Yes| G["call messages.create again
NO 'Continue.' user msg"] G --> B F -->|No| H["🔴 stop: hit continuation cap"] classDef done fill:#d4edda,stroke:#28a745,color:#155724; classDef pause fill:#e2d4f0,stroke:#764ba2,color:#3d1a5b; classDef stop fill:#f8d7da,stroke:#dc3545,color:#721c24; class C done; class D,E,G pause; class H stop;

CODE The pause_turn branch (resume, capped)

Re-send the assistant content unchanged, and cap the number of continuations so a runaway server loop can't spin forever.

# Server-side tools (web search, code execution) run on Anthropic infra.
messages = [{"role": "user", "content": question}]
resp = client.messages.create(
    model="claude-opus-4-8", max_tokens=4096,
    tools=[{"type": "web_search_20250305", "name": "web_search"}],
    messages=messages,
)

MAX_CONTINUATIONS = 5
continuations = 0
while resp.stop_reason == "pause_turn":
    if continuations >= MAX_CONTINUATIONS:
        break                                  # cap runaway loops
    # Re-send the assistant turn AS-IS. No "Continue." user message!
    messages.append({"role": "assistant", "content": resp.content})
    resp = client.messages.create(
        model="claude-opus-4-8", max_tokens=4096,
        tools=[{"type": "web_search_20250305", "name": "web_search"}],
        messages=messages,
    )
    continuations += 1

# Server resumed until it finished → now handle end_turn (or another reason).
The resume pattern is: append response.content, call again, repeat while pause_turn, with a continuation cap. The server does the tool work; you just keep the loop turning.

TRADE-OFFS Server-side tools vs. client-side tools

✅ Server-side (pause_turn model)

  • Anthropic runs the tool loop — less orchestration code
  • Fewer round-trips to your service per sub-step
  • Built-in capabilities (search, code execution)

⚠️ Costs / caveats

  • You must handle pause_turn and cap continuations
  • Less direct control over each tool step
  • A wrong "Continue." message breaks resumption

EXAM TRAPS

Trap: Appending a "Continue." user message on pause_turn. → Wrong. Re-send the assistant turn as-is; the server resumes. A new user message derails it.
Trap: Treating pause_turn like tool_use and sending a tool_result. → Server-side tools already ran on Anthropic infra; there's no client tool_result to supply. Just resume.
Trap: No continuation cap. → A paused loop could ping-pong indefinitely. Cap it (e.g. 5) and break out.
Trap: Assuming pause_turn means the model is finished. → It is the opposite — it paused mid-work and expects to be resumed.

PRACTICE

Q1 · You get pause_turn after enabling web search. What exactly do you send next?

Append response.content as an assistant turn (unchanged) and call messages.create again with the same tools. No "Continue." user message and no tool_result — the server resumes its own loop.

Q2 · Why cap continuations on pause_turn?

The server-side loop can pause repeatedly. Without a cap (e.g. 5) a pathological run could keep pausing and resuming, burning tokens and latency. The cap bounds the worst case.

Q3 · How is handling pause_turn different from handling tool_use?

tool_use: you run the tool and reply with a user tool_result. pause_turn: the server already ran the tool on Anthropic infra; you just re-send the assistant turn as-is so it resumes. Different roles, different payloads.