Streaming plus token accounting: stream_events v3 with usage callbacks

TL;DR: Stream an agent with the v3 event-streaming API for typed projections, and collect token usage with UsageMetadataCallbackHandler so you know what every run cost. Log it per run; it is your cost ledger. - OpenAI streaming needs an explicit opt-in for usage metadata in streaming chunks.

The fix

1. stream.messages is the text projection; stream.output is the final state. Consume projections independently instead of branching on chunk types.
2. Pass the callback in the config so every model call in the run reports into it. get_usage_metadata_callback gives you the same as a context manager.
3. usage_metadata is keyed by model name, with input/output/total tokens plus provider details (cache reads, reasoning tokens). Log it per run; it is your cost ledger.
4. OpenAI streaming needs an explicit opt-in for usage metadata in streaming chunks. If usage is empty on OpenAI streams, that is the missing step.

When to use this

• This covers exactly what the title says: Streaming plus token accounting.
• You are setting this up for the first time, or auditing an existing setup.
• You want the key gotchas in one place before you start.

When not to use this

• You are doing a different workflow with Streaming; these steps are specific to the title above.
• You need the full reference docs; this is the short path, not the manual.

Compatibility

• Not pinned to a specific version; follows current Streaming behavior.

Workflow grounded in the official event-streaming and models (token usage) docs, verified 2026-09-26. Event streaming: https://docs.langchain.com/oss/python/langchain/event-streaming ; models: https://docs.langchain.com/oss/python/langchain/models