Agent harness approvals and checkpoints

Six harnesses pause a tool call six ways: the Claude Agent SDK through hooks and a callback, Deep Agents through interrupt_on, Google ADK through confirmation, LangGraph through interrupt(), Microsoft Agent Framework through approval requests and OpenAI Agents SDK through interruptions. A traced CVE-2026-0322 firewall change shows the record. Docs read 19 Nov 2026.

How each harness pauses a call

Approval is a harness feature, not a policy: a tool pauses only if its harness was told to. The table lists the pause mechanism of six harnesses, alphabetically, from each project's own documentation. For the surrounding parts see what an agent harness is and logging and evidence, which records each decision.

Package versions from PyPI; mechanisms from the Claude Agent SDK permissions and hooks pages, Deep Agents and LangGraph pages on docs.langchain.com, Google ADK tool confirmation page, Microsoft Learn tool approval page and OpenAI Agents SDK human-in-the-loop page, all read 19 Nov 2026.
Harness and version readDeclare a pauseWhat the caller getsHow the answer goes backWhat holds the paused run
Claude Agent SDK, Python 0.2.185A canUseTool callback, ask rules, or a PreToolUse hook returning permissionDecision allow, deny, ask or deferYour callback runs only if hooks, deny rules, ask rules, the permission mode and allow rules have not decided the callThe callback or hook return; a hook can also set updatedInputWith defer the turn ends with stop_reason "tool_deferred" and the call can be resumed later; the session is a JSONL file on disk
Deep Agents 0.7.40interrupt_on maps tool names to a config; True enables the defaultsA LangGraph interruptapprove, edit, reject or respond, as far as allowed_decisions permitsA checkpointer, which the docs mark required
Google ADK 2.14.1FunctionTool with require_confirmation=True, or a function returning a booleanAn adk_request_confirmation function call with a hint and payloadA function_response with the same id and confirmed true or falseThe session; the docs list DatabaseSessionService and VertexAiSessionService as unsupported for this feature
LangGraph 1.2.23interrupt(value) in a node or toolThe value, on stream.interrupts or under interruptCommand(resume=value) on the same thread_idA checkpointer; the graph "waits indefinitely"
Microsoft Agent Framework 1.26.0approval_mode="always_require" in Python; ApprovalRequiredAIFunction in .NETThe run completes with user_input_requests (Python) or ToolApprovalRequestContent (.NET)to_function_approval_response(True or False), sent as a new messageThe same AgentSession; by default a response authorizes a call only if it matches a pending request in that session
OpenAI Agents SDK 0.25.0needs_approval set to True or to a function that decides per callRunResult.interruptions, a list of ToolApprovalItem entriesstate.approve() or state.reject(), then Runner.run(agent, state)A serializable RunState (to_string, to_json) that can sit in a database or queue

Defaults and edge cases to test

  • Local shell and file edits run without approval unless you switch it on. In the OpenAI Agents SDK, ShellTool and ApplyPatchTool default to needs_approval=False, so "the SDK can invoke your executor or editor without requesting approval", and the docs state that "SDK approval does not provide a sandbox": your executor must enforce the resource permissions. To review calls, set needs_approval=True or give a callable policy; without an on_approval callback the run then pauses and lists the requests in result.interruptions. Setting on_approval alone does not enable approval. Hosted shell environments do not support needs_approval or on_approval.
  • Bad arguments fail closed. For a callable approval rule in the OpenAI SDK, if arguments are missing, empty, malformed JSON, not an object, or contain NaN or Infinity, "the callable is not invoked and the call requires manual approval".
  • Standing approvals outlive the call. OpenAI's always_approve keeps a decision for the same tool identity; for local shell and apply_patch tools the sticky decision matches tool type and name, not the owning agent. Microsoft's standing approvals persist in the AgentSession and "aren't bound to the agent or tool instance that created them", so a replacement tool with the same name, including an MCP tool, can match a saved rule.
  • Code before the pause runs twice in LangGraph. "The node restarts from the beginning of the node where the interrupt was called when resumed, so any code before the interrupt runs again." Put side effects after interrupt().
  • Approval is not exactly-once. OpenAI's docs: approval "permits a tool call to execute; it does not guarantee exactly-once execution". If the process stops before the run state is saved, resuming from the older snapshot can run the tool again, so give each consequential action a stable idempotency key.
  • A saved pause is only as trustworthy as its storage. OpenAI's RunState.from_json() and from_string() "do not authenticate the snapshot or the person submitting it"; keep snapshots on the server and take the reviewer's identity from your session, not the request body. Microsoft binds a response to a pending request in the same session by default and warns that disabling the binding can let a fabricated response approve a privileged call.
  • Hooks do not override denials. In the Claude Agent SDK a hook that returns allow "doesn’t skip the deny-rule and ask-rule steps".
  • Nested agents share one queue. An approval raised inside an Agent.as_tool() run surfaces on the outer run and is approved on the outer RunState.
  • Google ADK confirmation is experimental in the TypeScript, Go and Kotlin versions; Python support starts at v1.14.0, TypeScript at v0.2.0, Go at v0.3.0 and Kotlin at v0.1.0.

Each bullet is a behavior to confirm in your own deployment; the docs describe the versions listed above. Tools and permissions covers which tools a harness should offer at all.

Worked trace: a firewall change on CVE-2026-0322

CVE-2026-0322 is a code-execution flaw in the PAN-OS management interface (CVSS 4.0 base score 8.6). An attacker needs network access to that interface and a valid high-privilege account. Palo Alto published the advisory on 14 Oct 2026 and rates exploit maturity ATTACKED. The case is constructed: the firewall name, its build and the addresses are illustrative; the CVE facts, the build ranges and the mitigation cost come from the record.

  1. 14 Oct 2026. CISA adds CVE-2026-0322 to the Known Exploited Vulnerabilities catalog with a due date of 17 Oct 2026, three days away. The task opens: triage firewall fw-edge-3. Record: task id, CVE, KEV dates.
  2. Read, no pause. The agent runs show system info and reads sw-version 11.2.13-h2. The record's version table puts 11.2.13-h* builds below h3 in the affected range, with 11.2.13-h3 or 11.2.16 as fixed builds. Record: the command and its output.
  3. Read, no pause. The agent reads Device > Setup > Interfaces > Management Interface Settings > Permitted IP Addresses. In this constructed case the list allows addresses outside the company. Palo Alto's advisory says risk is highest when the management interface is reachable from the internet. Record: the list as read.
  4. Read, no pause. Forensic triage is marked required by CISA for this entry, so the agent searches management-interface and firewall logs for the three addresses Palo Alto ties to limited exploit attempts (66[.]42[.]72[.]14, 208[.]83[.]239[.]114, 149[.]248[.]47[.]234). Record: query, time range, match count.
  5. Proposed change, pause. The agent calls set_mgmt_permitted_ips for fw-edge-3 with the single jump-box address 203.0.113.10 (a documentation address). The tool is declared as needing approval, so the run stops before it executes. The request shows the device, the current list, the proposed list and the cost from the record: administrators must connect through that host, and Palo Alto rates the jump-box case 8.5 instead of 8.6, so the risk drops only a little. No workaround exists; the fix is the upgrade. Record: request id, arguments, time requested, advisory version seen.
  6. 15 Oct 2026, decision. Palo Alto updated the advisory that day, so the agent re-reads it before the paused run resumes; an approval given against the 14 Oct text is not assumed to cover the 15 Oct text (the OpenAI docs advise storing a version marker with a pending run for the same reason). The approver rejects the first proposal with the message "Panorama also needs access; add 203.0.113.20". Record: decision, approver, time, message.
  7. Second proposal, second pause. The agent proposes 203.0.113.10 and 203.0.113.20. A new request id is created; the first rejection stays on file. The approver approves on 15 Oct 2026. Record: both decisions, linked by task id.
  8. Resume and verify. The tool executes once. The agent re-reads Permitted IP Addresses and compares it with the approved list. Record: execution time, result, the verification read.
  9. The ticket stays open. Restricting access does not remove the flaw. The upgrade to 11.2.13-h3 or 11.2.16 is a change ticket for a person to schedule and run; the agent has no upgrade tool. Record: the open item and its 17 Oct 2026 due date.

The record in step 5 to 8, as the log holds it after the second approval (the format follows the fields listed on logging and evidence; values are illustrative):

record_id: appr-0002 (the second request; appr-0001 is the rejected first one) task_id: cve-2026-0322-fw-edge-3 cve: CVE-2026-0322 tool: set_mgmt_permitted_ips arguments: device=fw-edge-3; allow=203.0.113.10/32, 203.0.113.20/32 current_state_read: Device > Setup > Interfaces > Management Interface Settings > Permitted IP Addresses, as read in step 3 advisory_seen: Palo Alto advisory CVE-2026-0322, Updated 15 Oct 2026 cost_shown_to_approver: admins connect through the listed hosts; CVSS 4.0 8.6 -> 8.5 only; no workaround, fix is the upgrade requested_at: 15 Oct 2026 decision: approve decided_by: <named approver, by authenticated identity, not typed into the request> decided_at: 15 Oct 2026 executed_at: 15 Oct 2026 verified_by_read: yes, list equals approved list open_item: upgrade to 11.2.13-h3 or 11.2.16, due 17 Oct 2026

Download the template: .docx PDF CC BY 4.0

Three points make the trace hold. The reviewer sees the cost of the change, not just its name. The first rejection is kept, so the log shows the agent was corrected. Reads need no approval, so the pause occurs once per consequential change rather than once per command. How many pauses are tolerable is a design question for human approval design and the human approval points checklist.

What the standards add

OWASP LLM06:2025 advises to "require a human to approve high-impact actions before they are taken". MITRE ATLAS mitigation AML.M0029, Human In-the-Loop for AI Agent Actions (release 2026.10), adds that "Human In-the-Loop policies should follow the degree of consequence of the task at hand". In the trace, a read of the permitted-address list is low consequence and a change to a production firewall is high, which is the split the quotes describe. Turning that split into a rule is a team decision; this page covers only what the harness can enforce.

Sources

  1. OpenAI Agents SDK, Human-in-the-loop, read 19 Nov 2026
  2. OpenAI Agents SDK, Tools, Approval for local shell and file edits, read 19 Nov 2026
  3. PyPI, openai-agents 0.25.0, read 19 Nov 2026
  4. LangChain, Deep Agents, Human-in-the-loop, read 19 Nov 2026
  5. PyPI, deepagents 0.7.40, read 19 Nov 2026
  6. LangChain, LangGraph, Interrupts, read 19 Nov 2026
  7. PyPI, langgraph 1.2.23, read 19 Nov 2026
  8. Microsoft Learn, Agent Framework, function tools with human in the loop approvals, read 19 Nov 2026
  9. PyPI, agent-framework 1.26.0, read 19 Nov 2026
  10. Google ADK, Get action confirmation for ADK Tools, read 19 Nov 2026
  11. PyPI, google-adk 2.14.1, read 19 Nov 2026
  12. Anthropic, Claude Agent SDK, Configure permissions, read 19 Nov 2026
  13. Anthropic, Claude Agent SDK, Intercept and control agent behavior with hooks, read 19 Nov 2026
  14. PyPI, claude-agent-sdk 0.2.185, read 19 Nov 2026
  15. OWASP, LLM06:2025 Excessive Agency, read 19 Nov 2026
  16. MITRE ATLAS data release 2026.10, mitigation AML.M0029, read 19 Nov 2026
  17. Palo Alto Networks, security advisory CVE-2026-0322, read 19 Nov 2026
  18. CISA KEV entry for CVE-2026-0322, read 19 Nov 2026
  19. NVD record for CVE-2026-0322, read 19 Nov 2026

Last reviewed 19 Nov 2026