LangGraph - Sakshi Documentation

LangGraph agents are graphs of nodes. Sakshi witnesses them at two levels, and neither imports langgraph. watch_langgraph brackets a whole run. witness_node records a single node. Combine them with a provider middleware, and the model calls inside each node are recorded as llm_call steps in order, nested under the graph and node steps.

Install

pip install sakshi-sdk langgraph

Bracket a compiled graph

watch_langgraph wraps a compiled graph’s invoke and stream so each run is bracketed by graph_start and graph_end steps, with latency and, for streams, the chunk count.

graph = builder.compile()

result = graph.invoke({"application": application})

from sakshi.middleware import watch_langgraph

graph = watch_langgraph(builder.compile())

with sakshi.witness(agent_id, client_ref="APP-2026-04471") as decision:
    result = graph.invoke({"application": application})
    decision.action(outcome="approved", mode="auto")

The optional name labels the graph in the evidence. If you do not pass it, the graph’s own name or its type name is used.

graph = watch_langgraph(builder.compile(), name="loan-decision-graph")

Witness individual nodes

witness_node wraps a node callable so each execution lands a graph_node step: the node name, the latency, which state keys the node updated, and the error if it raised. Failures are evidence too, so the exception is re-raised after it is recorded. The state values themselves are not captured, only the keys.

from sakshi.middleware import witness_node

def assess(state):
    ...
    return {"risk_band": "low", "score": 0.92}

# Bare, wrapping an existing callable:
builder.add_node("assess", witness_node(assess))

# Or as a decorator, with an optional name override:
@witness_node(name="assess")
def assess(state):
    ...

Both the sync and async node signatures are supported, including the state and state, config forms.

Combine with a provider middleware

The graph and node steps describe the control flow. To also record the model calls, wrap the provider client that your nodes use with the matching middleware, for example OpenAI or Anthropic. Because every step attaches to the same active witness session, the llm_call steps land in order under the node that made them.

Recording is fail-open across all three surfaces: a problem writing a graph, node, or model step never breaks the run. With no active witness session, calls pass through untouched.

Full SDK reference

The client, the witness session, and enforcement.

​Install

​Bracket a compiled graph

​Witness individual nodes

​Combine with a provider middleware

Full SDK reference

Install

Bracket a compiled graph

Witness individual nodes

Combine with a provider middleware