Agent Control Models
Shared Pydantic models used by the server and SDKs. These models define the API contract for agents, controls, evaluation requests, and responses.
What this package provides
- Strongly typed request/response schemas
- Consistent validation and serialization across server and SDKs
- A single source of truth for model changes
Usage
from agent_control_models import Agent, Step
agent = Agent(agent_name="support-bot", agent_description="Support agent")
step = Step(type="llm", name="chat", input="hello")
Control execution duration
Evaluation responses include an optional top-level execution_duration_ms on each
ControlMatch in matches, non_matches, and errors. It measures that control's
condition evaluation in wall-clock milliseconds, including the visited condition
leaves, evaluator work, and time waiting for an evaluator concurrency slot.
Control loading and request/response overhead are outside this measurement.
Completed evaluations include a nonnegative value, including evaluator failures.
Precheck failures have no duration, and canceled evaluations produce no result.
Older responses without the field remain valid. The Python SDK copies the value
to ControlExecutionEvent.execution_duration_ms; the TypeScript SDK exposes it as
executionDurationMs.
Tests
cd models
uv run pytest
Full guide: https://docs.agentcontrol.dev/components/models
1 maintainer
Metadata
1 maintainer
Release files for agent-control-models 8.14.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| agent_control_models-8.14.0.tar.gz | 34.2 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| agent_control_models-8.14.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 67.7 kB
Release files / agent_control_models-8.14.0.tar.gz
| Download URL | agent_control_models-8.14.0.tar.gz |
|---|---|
| Size | 34.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c0cf3fe08155eb15f586cfe9cd7ffb52aa6d8a8346059bdd45954cfc575d60d6
|
|
BLAKE2b-256 checksum How to use checksums |
d86c1ddca4a6522e3295d4edbb1107d0e822fd8b633b0677c1bc655c1411b07e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Release files / agent_control_models-8.14.0-py3-none-any.whl
| Download URL | agent_control_models-8.14.0-py3-none-any.whl |
|---|---|
| Size | 33.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e2937e5ea0a8afc1028c49309c04807735520500a2e3f6a13ce87cc947c68edf
|
|
BLAKE2b-256 checksum How to use checksums |
ecfd4e4e06ea95f0fc8d84003fe56e0b8c13f1f694f91fd6aa866d37fe51dce9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Security for agent-control-models 8.14.0
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
