kazen-event-schema

Canonical KazenEvent schema shared across KazenAI services (orchestrator, FinOps, AgentLens, kazenai).

Install: PyPI · kazen-event-schema · Products: kazenai.com

python -m pip install kazen-event-schema

Published on PyPI as kazen-event-schema 0.6.2. Editable pip install -e ./kazen-event-schema remains available for workspace contributors.

Canonical event types

Model invocation: use model.call (not llm.call; legacy llm.call is normalized at ingest).
Human gates: gate.decision, human_gate, human.gate
FinOps: finops.trajectory, finops.circuit_breaker.opened, finops.pause, finops.resumed
Run lifecycle: run.started, run.completed, run.failed

from kazen_event_schema import KazenEvent, normalize_event_type, is_model_call

assert normalize_event_type("llm.call") == "model.call"
assert is_model_call("model.call")

Required / recommended fields (v1.2)

Field	Required	Purpose
`schema_version`	yes	`1.0`, `1.1`, or `1.2`
`event_id`	yes	UUID; idempotent ingest
`ts_ms`	yes	Unix ms timestamp
`event_type`	yes	Dotted lowercase (e.g. `model.call`)
`org_id`	yes	Tenant
`workspace_id` / `project_id`	yes	Workspace scope (alias: `project_id` → workspace)
`run_id`	recommended	Correlates all steps in a run
`step_id`	recommended	Step within run
`parent_step_id`	optional	Multi-agent tree
`agent_role`	recommended	planner, coder, brain, etc.
`tokens` / `tokens_used`	optional	Token count (synced if one set)
`cost_usd`	optional	Step cost
`gate_decision`	optional	proceed, rejected, retry_plan, …
`gate_latency_s`	optional	Human gate wait time
`payload`	optional	Tool names, model id, I/O refs

Service ports

See ../PORTS.md when working from a full KazenAI workspace checkout.

License

Apache License 2.0. See LICENSE and NOTICE.

Metadata

Release files for kazen-event-schema 0.6.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for kazen-event-schema 0.6.2
File	Size	Uploaded
kazen_event_schema-0.6.2.tar.gz	37.9 kB	Sep 28, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for kazen-event-schema 0.6.2
File	Interpreter	ABI	Platform	Reset
kazen_event_schema-0.6.2-py3-none-any.whl 27.9 kB Sep 28, 2026	Python 3	none	any	Details

Total release size: 65.9 kB

Release files / kazen_event_schema-0.6.2.tar.gz

Download URL	kazen_event_schema-0.6.2.tar.gz
Size	37.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`4981061e06486ff1cb09a5ce1a1ead8586428698c789666a6807ed1155fe4740`
BLAKE2b-256 checksum How to use checksums	`a537c8e1319ac758dc736858dbccae633c8af2dcb7433ba245f9ae9d9a344c9d`
Upload date	Sep 28, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kazenai-ai/kazen-event-schema
Publishing commit: github.com/kazenai-ai/kazen-event-schema/tree/3e0c226a84d6b8f8f825d31638d8ac36f6030500

Workflow

Publishing configuration: github.com/kazenai-ai/kazen-event-schema/blob/3e0c226a84d6b8f8f825d31638d8ac36f6030500/.github/workflows/publish.yml
Publishing logs: github.com/kazenai-ai/kazen-event-schema/actions/runs/36478770632/attempts/1

Artifact

Subject: kazen_event_schema-0.6.2.tar.gz
SHA-256 checksum: 4981061e06486ff1cb09a5ce1a1ead8586428698c789666a6807ed1155fe4740 Verifying attestations

Release files / kazen_event_schema-0.6.2-py3-none-any.whl

Download URL	kazen_event_schema-0.6.2-py3-none-any.whl
Size	27.9 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`7d333c966eb761ac1b56fbb60022d4430e238365cd8a64b841263a4483dad41d`
BLAKE2b-256 checksum How to use checksums	`ce708be64b9068a46cd8b661b56ffcdd76b411b7a4d068b94a783b819005ec68`
Upload date	Sep 28, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/kazenai-ai/kazen-event-schema
Publishing commit: github.com/kazenai-ai/kazen-event-schema/tree/3e0c226a84d6b8f8f825d31638d8ac36f6030500

Workflow

Publishing configuration: github.com/kazenai-ai/kazen-event-schema/blob/3e0c226a84d6b8f8f825d31638d8ac36f6030500/.github/workflows/publish.yml
Publishing logs: github.com/kazenai-ai/kazen-event-schema/actions/runs/36478770632/attempts/1

Artifact

Subject: kazen_event_schema-0.6.2-py3-none-any.whl
SHA-256 checksum: 7d333c966eb761ac1b56fbb60022d4430e238365cd8a64b841263a4483dad41d Verifying attestations