Repository navigation
Commit 557d553
feat(ocsf): emit AI inference events via ai_operation profile on HttpActivity
Apply the official OCSF ai_operation profile (introduced in v1.8.0) to
HttpActivity [4002] events when the inference proxy routes a model call
through inference.local. Attaches an ai_model object (name, ai_provider)
and puts token counts and latency in unmapped fields.
Changes:
- Add AiModel object and ai_model field on BaseEventData
- Add .ai_model() method on HttpActivityBuilder (includes ai_operation
in metadata.profiles when set)
- Add emit_ai_inference in proxy.rs to build HttpActivity with the
ai_operation profile after inference calls complete
- Vendor OCSF v1.8.0 schemas with ai_operation profile and ai_model
object definitions
- Bump OCSF_VERSION to 1.8.0
- Update schema validation to skip profile-gated required fields
Shorthand output: HTTP:POST [INFO] [ai:claude-3-haiku via anthropic 123ms]
Splunk/SIEM backward compatibility (v1.1/v1.3 CIM mapping) is tracked
separately in NVIDIA#2662 as a configurable serialization concern.
Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>1 parent 4cb77a9 commit 557d553
51 files changed
Lines changed: 12980 additions & 46 deletions
File tree
- crates
- openshell-ocsf
- schemas/ocsf
- v1.8.0
- classes
- objects
- profiles
- src
- builders
- enums
- events
- format
- objects
- tracing_layers
- validation
- openshell-supervisor-network/src
Some content is hidden
Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.
0 commit comments