ax-cpp-agent

AxAgent For C++

This skill helps an agent write C++ code with the generated Ax package axllm. Use the generated package API, examples, and manifests; do not import TypeScript-only APIs unless you are editing the TypeScript package.

When To Use

• Create an RLM agent with tools, child agents, or MCP clients.
• Use clarification, discovery, recall, final, or respond envelopes.
• Require evidence citations, attach a persistent playbook, or add stage-owned actor instructions.
• Harvest run-end failures into the playbook and observe citation or playbook updates.
• Skip the executor stage for no-tool tasks with a distiller respond envelope (directResponse, on by default).
• Save and restore agent runtime state around long-running tasks.

Package Facts

• Language: C++.
• Package: axllm.
• Package API docs: API.md and axir-api.json.
• Capability manifest: axir-capabilities.json.
• Runnable examples: examples/.
• Real network support: yes.
• Scripted no-key transport support: yes.
• Runtime profiles: javascript-quickjs, python-pyodide.

Core Pattern

auto helper = axllm::agent("question:string -> answer:string");
auto out = helper.forward(llm, { {"question", "How should I proceed?"} });

Astra Session Work

Select gpt-6-astra through the ordinary OpenAI factory. The adapter chooses Responses automatically; existing model defaults are unchanged. Use low reasoning and standard processing. Portable minimal reasoning maps to low; none is rejected. EU residency does not support priority processing.

Keep applications on their generation, agent, and flow entrypoints. Declare only independent tools as background; ordinary and imported MCP tools stay blocking unless the application explicitly changes their declaration. A promise, thread, or MCP hint is not a background declaration. Set asyncMode to off for the ordinary tool loop; chat-only services retain that loop automatically.

Declared-background native agent tools retain the imported MCP schema, handler, namespace, and raw result. Discovery must expose the tool before the model can call it. Invalid arguments are corrected before handler execution; the responder waits for the incorporated result. Native calls appear in action logs and must not be repeated through actor code. Owned child agents inherit selected MCP clients at delegation. Parent stages keep their own clients; none or an empty namespace list passes no parent clients. Explicit child context wins over inherited context. Each run refreshes protocol modules without serializing live client handles into model requests. Cancellation propagates through a delegated child into its pending MCP tool; completed child work is not replayed. Imported MCP tools forward cancellation to context-aware transports, including built-in HTTP. Custom transports using the older send method receive cancellation checks before and after their call; noncooperative work may finish later and its result is discarded. Cancellation does not undo an external action or replay a request. MCP host policy applies to native background calls too. Configure authorizeToolCall in Python, Go, and Java client options, or set_tool_authorizer on C++ and Rust clients before exposing their tools. The callback receives the client and call metadata; returning false denies the call before a tool request is sent. Use shared application policy state when permissions must change during a run.