OBSERVABILITY PLATFORM · Profile revision 1
Langfuse
An OpenTelemetry-rooted observability platform with typed generation, agent, tool, retriever, evaluator, and guardrail observations plus export and privacy controls.
Why it is in the map
Langfuse contributes a typed observation model and concrete masking, retention, deletion, API, and self-hosting evidence.
Tracevity boundary
A documented field can support reconstruction, but its presence alone does not prove completeness, authenticity, authorization, or external settlement.
Profile findings
What the documentation can—and cannot—establish
Each row distinguishes source evidence from Tracevity's bounded interpretation. “Not documented” describes the reviewed sources; it does not prove an implementation cannot record the artifact.
System identity
DocumentedTrace, session, observation hierarchy, user, and release metadata support execution correlation.
Tracevity interpretation
This does not guarantee a stable agent-instance or agent-definition version across arbitrary integrations.
Limit
Canonical agent instance and definition/version fields are not mandatory for every observation.
Primary evidence (1)
- Langfuse: Observability data model Traces, observations, and sessions
Principal and delegation
Partially documentedUser attribution is representable, but authenticated principal and delegation semantics are not standardized.
Tracevity interpretation
A user ID and agent nesting must not be presented as authentication or an authority chain.
Limit
Delegated identity, credential type/scope/expiry, and elevation are not canonical fields.
Primary evidence (1)
- Langfuse: Observability data model Trace user_id and metadata
Instruction and context
DocumentedInstruction and retrieval context can be recorded in typed or generic observation payloads.
Tracevity interpretation
Recorded payloads do not prove that all selected context or source versions survived.
Limit
Context fingerprint, source authenticity, and explicit missing-context representation are not universal.
Primary evidence (1)
- Langfuse: Observation types Generation and retriever observations
Decision artifacts
Partially documentedEvaluator and guardrail outputs are representable as recorded decision evidence.
Tracevity interpretation
They do not expose hidden reasoning or guarantee a plan, selected alternative, or policy rationale.
Limit
Plan, decision summary, selected alternative, calibrated confidence, and refusal reason are not universal typed fields.
Primary evidence (1)
- Langfuse: Observation types Evaluator and guardrail observation types
Model activity
DocumentedCore model request/response, identity, usage, cost, and latency evidence is representable.
Tracevity interpretation
Actual coverage and exact provider model version depend on instrumentation.
Limit
Provider-specific version, cache, error, and content completeness are not guaranteed for every integration.
Primary evidence (1)
- Langfuse: Observation types Generation observation
Tool and MCP activity
DocumentedTool identity, arguments/results, error, latency, and trace hierarchy can be represented.
Tracevity interpretation
A tool observation is execution telemetry, not proof of authority or downstream settlement.
Limit
MCP server identity, credential context, retry, and downstream provider correlation are not universal.
Primary evidence (1)
- Langfuse: Observation types Tool observation type
Effects
Not documentedSome read/action semantics exist, but a first-class external-effect settlement model does not.
Tracevity interpretation
Successful tool output cannot establish external state change.
Limit
Requested effect, acceptance, transaction settlement, external effect state, and state delta are not canonical.
Primary evidence (1)
- Langfuse: Observation types Retriever and tool observation semantics
Human control
Partially documentedHuman review artifacts can be retained.
Tracevity interpretation
Review or annotation is not necessarily pre-action authorization or intervention.
Limit
Approval, rejection, edit, interruption, takeover, rollback request, identity, and authority are not universal.
Primary evidence (1)
- Langfuse: Observability data model Scores and trace/session grouping
Outcome
Partially documentedReported success/failure and evaluation evidence can be reconstructed from retained observations.
Tracevity interpretation
Observation outcome does not independently verify destination state.
Limit
External verification, partial/ambiguous settlement, rollback, and compensation are not canonical outcomes.
Primary evidence (1)
- Langfuse: Observability data model Observation output, level, status, and scores
Trace integrity
Not documentedLangfuse records have lifecycle controls but no documented universal integrity guarantee.
Tracevity interpretation
Trace IDs and timestamps support correlation, not independent verifiability.
Limit
Clock provenance, immutability, append-only behavior, signature, tamper evidence, and independent verification are absent.
Primary evidence (1)
- Langfuse: Data deletion Trace and project deletion
Portability
DocumentedOTel foundations and native API/export surfaces provide multiple portability paths.
Tracevity interpretation
Typed vendor observation meaning may not survive every destination or conversion.
Limit
Complete schema versioning, import coverage, documented conversion, and exact semantic loss remain unknown.
Primary evidence (1)
- Langfuse: API and Data Platform Data access and export surfaces
Privacy
DocumentedSensitive prompt, output, tool, PII, code, and metadata capture can be reduced through documented controls.
Tracevity interpretation
Control availability does not prove that an integration enabled masking or minimized every sensitive field.
Limit
Coverage, hashing, screenshots, deployment-specific retention, and customer capture defaults remain implementation dependent.
Primary evidence (1)
- Langfuse: Masking Client-side and collector masking
Reconstruction reading
Do not collapse these findings into one score.
This profile describes documented evidence surfaces. Whether they are sufficient depends on the reconstruction question and the other identity, authorization, tool, and destination records available.
Potentially useful evidence
- Identity: Trace, session, observation hierarchy, user, and release metadata support execution correlation.
- Principal: User attribution is representable, but authenticated principal and delegation semantics are not standardized.
- Context: Instruction and retrieval context can be recorded in typed or generic observation payloads.
- Decisions: Evaluator and guardrail outputs are representable as recorded decision evidence.
- Models: Core model request/response, identity, usage, cost, and latency evidence is representable.
Explicit gaps or uncertainty
- Effects: Requested effect, acceptance, transaction settlement, external effect state, and state delta are not canonical.
- Integrity: Clock provenance, immutability, append-only behavior, signature, tamper evidence, and independent verification are absent.
Source register
8 reviewed primary sources
- Observability data modelLangfuse · OFFICIAL DOCUMENTATION · observed August 28, 2026 · currentOpen source ↗
- Observation typesLangfuse · OFFICIAL DOCUMENTATION · observed August 28, 2026 · currentOpen source ↗
- Observations APILangfuse · OFFICIAL DOCUMENTATION · observed August 28, 2026 · currentOpen source ↗
- API and Data PlatformLangfuse · OFFICIAL DOCUMENTATION · observed August 28, 2026 · currentOpen source ↗
- MaskingLangfuse · OFFICIAL DOCUMENTATION · observed August 28, 2026 · currentOpen source ↗
- Data deletionLangfuse · OFFICIAL POLICY · observed August 28, 2026 · currentOpen source ↗
- Privacy FAQLangfuse · OFFICIAL POLICY · observed August 28, 2026 · currentOpen source ↗
- Agent graphsLangfuse · OFFICIAL DOCUMENTATION · observed August 28, 2026 · currentOpen source ↗
Next question
What evidence does your use case require?
Move from documented field presence to an explicit reconstruction target, or examine selected directional format mappings without changing this system's documentation posture.
Trace Reconstruction Requirements Explore compatibility evidence