> For the complete documentation index, see [llms.txt](https://docs.algenta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.algenta.ai/sdks/python/repositories.md).

# Repository intelligence

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](/guides/repository-intelligence.md) 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

```python
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

```python
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)
```

{% hint style="danger" %}
`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.
{% endhint %}

## Related pages

{% content-ref url="/pages/hZmJuyqdj0q8UZ8iGpGe" %}
[Triage a repository](/guides/repository-intelligence.md)
{% endcontent-ref %}

{% content-ref url="/pages/l0mqGrhl5ic9OfaGy52Q" %}
[Simulations & queries](/sdks/python/simulations-and-queries.md)
{% endcontent-ref %}

{% content-ref url="/pages/dbMexAzWYilfd77tn3O8" %}
[API endpoint reference](/http-api/reference.md)
{% endcontent-ref %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.algenta.ai/sdks/python/repositories.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.