Repository intelligence

Python SDK reference for repository intelligence — capabilities, snapshots, triage, decision plans, graph queries, simulate, and apply.

These methods drive Algenta's repository intelligence: index a repository into a snapshot, triage where to act, query its code graph, simulate a proposed change, and apply an approved one. They are available on both AlgentaClient and AsyncAlgentaClient (await the async calls). Each takes a repository_id and a request dict, except get_repository_intelligence_capabilities. See the repository intelligence guide for the end-to-end workflow.

Method reference

Method	Purpose
get_repository_intelligence_capabilities()	List the repository intelligence this instance supports (RepositoryIntelligenceCapabilitiesResult). Reads /v1/repositories/capabilities.
create_repository_snapshot(repository_id, request)	Index a repository into a snapshot (RepositorySnapshotResult). Posts to /v1/repositories/{repository_id}/snapshots.
get_repository_snapshot(repository_id, snapshot_id)	Fetch a stored snapshot (RepositorySnapshotResult). Reads /v1/repositories/{repository_id}/snapshots/{snapshot_id}.
triage_repository(repository_id, request)	Rank likely-relevant files and propose where to act (RepositoryTriageResult). Posts to /v1/repositories/{repository_id}/triage.
create_repository_decision_plan(repository_id, request)	Produce a decision-plan revision for a repository change (RepositoryDecisionPlanRevisionResult). Posts to /v1/repositories/{repository_id}/decision-plans.
query_repository_graph(repository_id, request)	Query the repository's code graph (RepositoryGraphQueryResult). Posts to /v1/repositories/{repository_id}/graph-query.
simulate_repository(repository_id, request)	Simulate a proposed change and return a DecisionEnvelope. Posts to /v1/repositories/{repository_id}/simulate.
apply_repository(repository_id, request)	Apply an approved change and return the result (RepositoryApplyResult). Posts to /v1/repositories/{repository_id}/apply.

Example: snapshot and triage a repository

import os
from decision_engine import AlgentaClient

client = AlgentaClient(api_key=os.environ["ALGENTA_API_KEY"])

# Confirm what the instance supports.
caps = client.get_repository_intelligence_capabilities()
print(caps.supported_languages)

# Index the repository, then rank where to act.
snapshot = client.create_repository_snapshot(
    "$REPOSITORY_ID",
    {"ref": "main"},
)

triage = client.triage_repository(
    "$REPOSITORY_ID",
    {
        "snapshot_id": snapshot.snapshot_id,
        "signals": {"failing_tests": ["test_checkout_totals"]},
    },
)
for item in triage.evidence_items:
    print(item.file_path, item.score)

Example: simulate then apply a change

import os
from decision_engine import AlgentaClient

client = AlgentaClient(api_key=os.environ["ALGENTA_API_KEY"])

# Simulate the proposed change -> DecisionEnvelope.
sim = client.simulate_repository(
    "$REPOSITORY_ID",
    {"decision_plan_id": "$DECISION_PLAN_ID"},
)
print(sim.recommended_action, sim.confidence)

# Apply the approved change.
applied = client.apply_repository(
    "$REPOSITORY_ID",
    {
        "decision_plan_id": "$DECISION_PLAN_ID",
        "simulation_id": "$SIMULATION_ID",
        "mode": "patch_only",
    },
)
print(applied.applied, applied.mode)

apply_repository can write to your repository. Use mode: "patch_only" to only return the diff; local_branch and remote_pr write, and require write_permission: true to authorize the engine to create a branch or open a pull request.

Related pages

Triage a repositorySimulations & queriesAPI endpoint reference