feat(langchain): Set gen_ai.operation.name and gen_ai.pipeline.name on LLM spans

[ericapisani]

Set gen_ai.operation.name and gen_ai.pipeline.name span attributes on spans created by on_llm_start in the LangChain integration.

on_llm_start handles non-chat LLM calls (e.g. completion models). It was already setting span attributes for model, system, and token usage, but was missing the operation name and pipeline name attributes that other handlers set. This adds:

• gen_ai.operation.name = "generate_text" to align with the span op (gen_ai.generate_text)
• gen_ai.pipeline.name from the name kwarg passed by LangChain, when present

Tests are updated in test_langchain_message_truncation and test_langchain_response_model_extraction to assert these attributes are set correctly.

Part of SDK-669, is the second part of changes that are being pulled out of #5705

[linear-code]

SDK-669 Investigate use of `gen_ai.pipeline` span op across SDKs

[github-actions]

Semver Impact of This PR

🟡 Minor (new features)

📋 Changelog Preview

This is how your changes will appear in the changelog.
Entries from this PR are highlighted with a left border (blockquote style).

---

New Features ✨

Langchain

• Set gen_ai.operation.name and gen_ai.pipeline.name on LLM spans by ericapisani in #5849

• Update LLM span operation to gen_ai.generate_text by ericapisani in #5796

Internal Changes 🔧

• (langchain) Consolidate available tools assertion by alexander-alderman-webb in #5721

---

_{🤖 This preview updates automatically when you update the PR.}

[github-actions]

Codecov Results 📊

✅ 13 passed | Total: 13 | Pass Rate: 100% | Execution Time: 9.21s

All tests are passing successfully.

❌ Patch coverage is 0.00%. Project has 14385 uncovered lines.

Files with missing lines (1)

File	Patch %	Lines
langchain.py	3.26%	⚠️ 594 Missing

---

Generated by Codecov Action