Manifests

A manifest is the deterministic fingerprint of your agent at a point in time — its tools, prompts, models, sub-agents, and output schema. DecimalAI auto-detects manifests for OpenAI Agents and LangChain. Use register_manifest() only when you need full control or use a custom framework. See the Manifests guide for the conceptual model.

`decimalai.register_manifest()`

Explicitly register an agent’s configuration for version tracking.

result = decimalai.register_manifest(
    agent_name="travel-planner",
    tools=[
        {"name": "search_flights", "schema": {"type": "object", "properties": {...}}},
        {"name": "book_hotel"},
    ],
    prompts={"system": "You are a travel planning assistant."},
    models={"default": {"provider": "openai", "model": "gpt-4o"}},
    subagents=[
        {"name": "flight_agent"},
        {"name": "hotel_agent"},
    ],
    version_label="v2.1",
)

print(f"Manifest: {result['manifest_id']}")
print(f"New version: {result['is_new']}")  # True if a fresh manifest row was created

str

required

Name of the agent.

list[dict]

Tool descriptors: [{"name": "...", "schema": {...}}].

dict

Prompt templates: {"system": "..."}.

dict

Model configs: {"default": {"provider": "openai", "model": "gpt-4o"}}.

list[dict]

Sub-agent references: [{"name": "flight_agent"}].

dict

Output contract JSON schema.

str

Human-readable version label (e.g., "v2.1").

For OpenAI Agents and LangChain, manifests are auto-detected from your agent configuration. Use register_manifest() only when you need full control or use a custom framework.

Returns the backend registration response (a dict):

str

Always "ok" on a successful registration.

str

ID of the manifest row this config resolved to.

str

Deterministic content hash of the manifest — identical configs hash identically.

str

The human-readable version label, echoed back.

bool

true only when a fresh manifest row was created. A re-register of an unchanged config dedups and returns false.

int

Number of manifest components captured across all surfaces.

str | null

ID of the generated compatibility report, or null if none was produced.

`decimalai.flush_manifest_for_ci()`

Register the manifest as a regression-check candidate and write its ID for the next CI step to read. This is the helper your CI init script (typically init_for_decimal.py) calls under DECIMALAI_MODE=manifest_only, after building the agent. It requires a positional agent_name.

import decimalai

decimalai.init(api_key="dai_sk_...", openai_agents=True)
agent = build_agent()  # your existing agent factory

# agent_name is REQUIRED (positional). Calling with no args raises TypeError.
decimalai.flush_manifest_for_ci(
    "travel-planner",
    tools=[{"name": "search_flights", "schema": {"type": "object"}}],
    prompts={"system": SYSTEM_PROMPT},
    models={"default": {"provider": "openai", "model": "gpt-4o"}},
)

Components are taken from what you pass, not from global SDK state: supply chain= (below) or the explicit tools / prompts / models dicts, otherwise you register an empty manifest and every later PR diffs against nothing. The manifest ID is written to (in order): the output_path= you pass, else $GITHUB_OUTPUT if set (appended as decimal_manifest_id=<id>, the standard GitHub Actions mechanism), else ./decimal_manifest_id.txt in the current directory. An explicit output_path therefore overrides the GitHub Actions handoff — the Action itself only auto-discovers $GITHUB_OUTPUT and ./decimal_manifest_id.txt, so if you write somewhere else, pass that ID to the Action’s candidate-manifest-id input yourself. The path actually used comes back as output_path in the return value.

Inside GitHub Actions $GITHUB_OUTPUT is always set, so branch 2 always wins and ./decimal_manifest_id.txt is never written. And $GITHUB_OUTPUT is per-step — the file the next step sees is a fresh one, so the Action’s auto-discovery finds neither source and stops with “No candidate-manifest-id provided or discoverable”. Give the step an id: and pass candidate-manifest-id: ${{ steps.<id>.outputs.decimal_manifest_id }} to the Action explicitly.

You can also let flush_manifest_for_ci introspect a LangChain/LangGraph agent instead of passing component dicts:

decimalai.flush_manifest_for_ci("travel-planner", chain=agent)

See the Regression Check guide for the full CI setup.

What’s next

Evaluations

Push scores onto traces and read back the verdict.

Manifests guide

Conceptual deep-dive on what a manifest is and how diffs work.

Python SDK

CLI

`decimalai.register_manifest()`

`decimalai.flush_manifest_for_ci()`

What’s next

Evaluations

Manifests guide

​decimalai.register_manifest()

​decimalai.flush_manifest_for_ci()

​What’s next

Evaluations

Manifests guide

`decimalai.register_manifest()`

`decimalai.flush_manifest_for_ci()`

What’s next