Skip to content

ci: sync sample catalog from foundry-samples (yimin/catalog-review-correction-e2e-20260928) #836

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
foundry-toolkit-sync-bot wants to merge 2 commits into from
Closed

ci: sync sample catalog from foundry-samples (yimin/catalog-review-correction-e2e-20260928) #836

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8572518
ci: sync sample catalog from foundry-samples (yimin/catalog-review-co…
Yimin-Jin Sep 28, 2026
9045400
fix(samples): apply skill-reviewed catalog corrections
foundry-toolkit-sync-bot[bot] Sep 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 19 additions & 8 deletions samples/hosted-agent/sample-catalog.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"commitSha": "be4706c76acfe44e2ae99c2818efdc4c5ab25bd9",
"commitSha": "5642c45da33220d5bb95bbe08fa67f34373bd96d",
"repo": "https://github.com/microsoft-foundry/foundry-samples/",
"generatedAt": "2026-09-23T05:22:25Z",
"generatedAt": "2026-09-28T05:42:37Z",
"dimensions": {
"language": {
"title": "Select a Language",
Expand Down Expand Up @@ -1155,6 +1155,15 @@
"description": "Agent that uses custom persistence stores for conversation chains and response records.",
"path": "samples/python/hosted-agents/langgraph/responses/13-custom-store",
"requiresModel": true
},
{
"language": "python",
"framework": "agent-framework",
"protocol": "invocations",
"displayName": "Content Safety Guardrail",
"description": "Hosted Python agent using an RAI content safety guardrail (Invocations protocol).",
"path": "samples/python/hosted-agents/agent-framework/invocations/02-content-safety-guardrail",
"requiresModel": true
}
],
"patterns": [
Expand Down Expand Up @@ -2090,23 +2099,25 @@
"title": "Content Safety Guardrail",
"categoryId": "security-governance-ops",
"details": {
"summary": "Apply a Responsible AI policy to check prompts and responses in the hosting platform.",
"whatItDoes": "Associates an RAI policy with the hosted agent so the platform applies configured input and output checks. These checks reduce risk but do not guarantee safe outputs.",
"summary": "Apply a Responsible AI policy to check prompts and responses in the hosting platform. Supports both Responses and Invocations protocols; the Invocations protocol requires additional invocationsModeration configuration to locate text fields.",
"whatItDoes": "Associates an RAI policy with the hosted agent so the platform applies configured input and output checks. These checks reduce risk but do not guarantee safe outputs. On the Responses protocol the platform can find message text automatically; on the Invocations protocol you must supply an invocationsModeration block (inputPaths, outputPaths, streamSelectors, etc.) so the platform knows which fields to screen.",
"whyUseIt": "Explore definition-level safety configuration separately from application code.",
"exampleScenario": "Compare how the configured policy handles permitted and blocked test prompts.",
"exampleScenario": "Compare how the configured policy handles permitted and blocked test prompts. For Invocations, also test that inputPaths/outputPaths/streamSelectors match your request/response shape so the policy actually screens the intended fields.",
"bestFit": "Teams evaluating platform safety configuration for hosted agents.",
"capabilities": [
"References an RAI policy",
"Applies configured platform checks",
"Separates policy setup from basic chat code"
"Separates policy setup from basic chat code",
"Requires invocationsModeration to screen custom request/response shapes (Invocations only)"
],
"whatItGenerates": "A Python chat agent with policy-aware hosting configuration. Merely copying the code does not activate a cloud policy.",
"whatItGenerates": "A Python chat agent project that declares an RAI policy in its hosting configuration. The Invocations protocol variant in this set includes an invocationsModeration example showing how to map request/response fields and streamed frames; the Responses variant relies on the platform's known message shape.",
"requirements": [
"Model deployment, RAI policy"
]
},
"templatePaths": [
"samples/python/hosted-agents/agent-framework/responses/16-content-safety-guardrail"
"samples/python/hosted-agents/agent-framework/responses/16-content-safety-guardrail",
"samples/python/hosted-agents/agent-framework/invocations/02-content-safety-guardrail"
]
},
{
Expand Down