OpenAI Agents
- Response spans: A streamed Responses call records the model, the system instructions, the output messages, the tools, and the request settings from the response object.
- History roles: Tool calls and reasoning items are recorded as assistant messages. Tool results are recorded as tool messages. A message that already has a role keeps it.
- Reply text: The trace output and the model span store the reply text. A streamed response with no
output_textstill yields that text, and encrypted reasoning stays out of the preview. - Agent spans: Agent, task, and turn spans record the input and output of their own child model calls when the span itself has none.
- Prompt once: The OpenAI Agents span snapshot no longer repeats the input history or the response message body already stored on the span.
LangChain
- Callback handler:
LemmaLangChainCallbackHandleraccepts LangChain 1.x callback arguments and setsrun_inline,raise_error, and theignore_*flags.
Vercel AI
- Telemetry types: The Vercel AI telemetry object is assignable to the AI SDK
Telemetrytype without a cast.
Mastra
- Exporter types:
exportTracingEventaccepts the framework event shape, so you can pass the exporter without a cast.
Tracing
- One turn, two processes: startTurn,
attachTurn, andapplyrecord a host and a sandbox as one trace. The child keeps a journal and does not call ingest. The host sends once.turn.end()still raises on failure.
Ingest
- Fail open:
trace()andTraceHandle.end()catch HTTP and network errors, log them, and do not rethrow. ingest() still raises. A delivery failure does not replace your agent’s error.
Generations
- Token usage: LangChain, OpenAI Agents, Vercel AI SDK, and Mastra record token usage, including cache and reasoning tokens from Agents SDK and AI SDK 7 shapes.
- Provider: Generation spans set the provider system from the model provider.
Tracing
- Release: Pass
releaseto the client, or setLEMMA_RELEASE, to stamp the running revision on each trace. - Provenance: Spans record the SDK language and integration so missing usage is distinct from a real zero.
Tool calls
- User-facing text: Set
userFacingMessagewhen a tool sends text directly to the person. Lemma shows that text as the message they received.
Vercel AI
- Trace contract: One integration owns one in-flight run. The root records the current turn, thread, and user, with wall-clock times and structured output.
OpenAI Agents
- Trace contract: The processor records current-turn input and output, terminal errors, and span-bounded times. Soft tool errors match the Python SDK.
LangChain
- Trace contract: Owned runs keep current-turn input, output, and errors. Tool calls stay nested under one root until the final answer. LangGraph uses the LangChain adapter.
Tracing
- First public release:
@uselemma/tracingsends traces to Lemma, with debug mode and experiment mode.
LangChain
- Callback handler: A LangChain callback handler records chains, model calls, and tools.
OpenAI Agents
- Processor: An OpenAI Agents processor records agent runs.
Vercel AI
- Telemetry: A Vercel AI SDK telemetry integration records model and tool calls.