feat: Migrate LangGraph runner to AgentGraphRunnerResult; clean up legacy shape detection

[jsonbailey]

Summary

• Updates LangGraphAgentGraphRunner.run() to return AgentGraphRunnerResult (with GraphMetrics) instead of the legacy AgentGraphResult shape
• Adds collect_node_metrics() to LDMetricsCallbackHandler for pure data extraction (no LD tracker calls from the runner)
• Removes the transitional isinstance(raw_result, AgentGraphRunnerResult) detection branch from ManagedAgentGraph — now that both OpenAI and LangGraph runners return the new shape, the bridge is dead code
• All graph-level and per-node tracking events are driven exclusively by ManagedAgentGraph._flush_graph_tracking()
• Updates test_langgraph_agent_graph_runner.py to verify runner returns AgentGraphRunnerResult and does NOT call graph tracker directly
• Updates test_tracking_langgraph.py to verify events via handler flush() or result shape; removes direct runner → graph tracker assertions

Stack position

This is PR 11-langchain, stacked on:

• PR feat: Add ManagedGraphResult, GraphMetricSummary, and AgentGraphRunnerResult types #151 (ManagedGraphResult types)
• PR feat: Graph tracking refactor — ManagedAgentGraph drives tracking for new runner shape #154 (graph tracking refactor — transitional bridge)
• PR feat: Update OpenAI graph runner to return AgentGraphRunnerResult with GraphMetrics #155 (OpenAI runner returns AgentGraphRunnerResult)

After this PR, the legacy AgentGraphResult shape is fully retired from production code.

Test plan

• make test passes in packages/ai-providers/server-ai-langchain (81 tests)
• uv run pytest packages/sdk/server-ai/tests/ passes (149 tests)
• make test passes in packages/ai-providers/server-ai-openai (40 tests)

🤖 Generated with Claude Code

---

Note

Medium Risk
Medium risk because it changes the LangGraph runner’s public result shape and shifts when/where tracking metrics are produced, which could break callers or alter emitted metrics if assumptions differ.

Overview
Updates LangGraphAgentGraphRunner.run() to return the new AgentGraphRunnerResult with GraphMetrics (content, duration, path, aggregated usage, and per-node metrics) instead of the legacy AgentGraphResult/direct tracker calls.

Refactors LDMetricsCallbackHandler to build per-node LDAIMetrics incrementally and expose them via node_metrics, removing the old flush() path that emitted LaunchDarkly events.

Tests are updated to assert the new result shape and that graph-level tracking is driven via ManagedAgentGraph (runner no longer calls graph trackers directly), with callback-handler tests now validating pure metric accumulation.

^{Reviewed by Cursor Bugbot for commit 95442cd. Bugbot is set up for automated code reviews on this repo. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, have a team admin enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit ba4b5dd. Configure here.}