feat(openai-agents)!: emit invoke_agent, chat and execute_tool spans

[apucacao]

Replaces one flat span per call with the tree the TypeScript SDK emits, for openai-agents.

invoke_agent                     one per call, carries the LD identity and the run total
├── chat {model}                 one per model turn, with that turn's own tokens
└── execute_tool {name}          one per tool call, a sibling of chat

The per-turn data was already in hand: this handler walked the Runner's raw responses to sum usage, and simply never opened a span per turn.

Abandoning the stream was costing money

The old path iterated the Runner's event stream with no cleanup at all. Breaking out of that loop only stops us reading: the Runner's own background task keeps calling the model and spending tokens until told to stop.

Teardown now cancels the streamed run as well as closing the span tree.

Two things specific to this handler

1. gen_ai.response.model stays the requested name, on both the root and the chat spans, which is deliberately different from openai-messages (feat(openai-messages)!: emit invoke_agent, chat and execute_tool spans #32). The TypeScript twin has never resolved the answering model here and no test pins it, so reporting one would invent behaviour rather than match it.

2. Finish reasons are derived from the Responses API's status rather than mapped through the shared table, which does not apply: there is no finish_reason field to map. A function call in the output takes precedence over status, because a live capture put completed on every turn including the six that stopped to call a tool.

Other changes

Cached tokens are now reported, read from the cached-tokens detail and left out of the input total, because OpenAI already counts them inside it. Cache creation is always zero.

Breaking change

The span is renamed from openai.agent.run to invoke_agent. Queries selecting on the old name will not match. Prompt and completion content is no longer on spans unless the caller passes capture_content=True.

Where this sits

Needs the usage layer (#28) and the content layer (#29). Independent of the other five handler PRs; the stack orders them only because gh stack is linear.

Tests: 781 to 799.

---

Note

Overview
Replaces the flat openai.agent.run span with the TypeScript-aligned tree: an invoke_agent root, one chat {model} child per model turn, and sibling execute_tool {name} spans per tool call—driven via agents.RunHooks rather than a Model wrapper.

Breaking: span rename (openai.agent.run → invoke_agent), and prompt/completion/tool content is off by default unless capture_content=True.

Also cancels abandoned streamed runs (previously the Runner kept spending tokens after the consumer stopped), reports cached-token usage, and writes failed-run spend onto the root without double-counting the SDK aggregate.

^{Reviewed by Cursor Bugbot for commit 169ab0c. Bugbot is set up for automated code reviews on this repo. Configure here.}

[apucacao]

bugbot run

[apucacao]

bugbot run

[apucacao]

bugbot run

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit 60c2410. Configure here.}

[apucacao]

bugbot run

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit 169ab0c. Configure here.}

[apucacao]

bugbot run

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit 169ab0c. Configure here.}