threadlight-deploy

Files (163)

• SKILL.md
• azd-cli-contract.md · references/
• PROVENANCE.md · references/azd-modules/
• README.md · references/azd-modules/
• aca-app.bicep · references/azd-modules/references/bicep/
• aca-environment.bicep · references/azd-modules/references/bicep/
• aca-job.bicep · references/azd-modules/references/bicep/
• aca-private-dns.bicep · references/azd-modules/references/bicep/
• aca-subnet.bicep · references/azd-modules/references/bicep/
• acr-pull.bicep · references/azd-modules/references/bicep/
• foundry-account.bicep · references/azd-modules/references/bicep/
• foundry-project-capability-host.bicep · references/azd-modules/references/bicep/
• main.bicepparam · references/azd-modules/references/bicep/
• private-dns-vnet-link.bicep · references/azd-modules/references/bicep/
• rbac.bicep · references/azd-modules/references/bicep/
• uami.bicep · references/azd-modules/references/bicep/
• upstream-pin.md · references/azd-modules/references/
• agent.in · references/generate-only/locks/
• evals.in · references/generate-only/locks/
• evals.requirements.lock · references/generate-only/locks/
• mcp.in · references/generate-only/locks/
• PIN.md · references/generate-only/schemas/
• azure.yaml.schema.json · references/generate-only/schemas/
• mcp_server.py.tmpl · references/generate-only/templates/
• run_evals.py.tmpl · references/generate-only/templates/
• README.md · references/governance/
• adversarial_evidence.py · references/governance/
• audit_delivery.py · references/governance/
• azure-services.yaml · references/governance/
• generate.py · references/governance/
• ghcp-container.py · references/governance/
• governance.bicep · references/governance/
• install_opa.py · references/governance/
• maf-container.py · references/governance/
• maf-entrypoint.py · references/governance/
• maf-gateway-container.py · references/governance/
• maf_gateway.py · references/governance/
• native-local.yml · references/governance/
• package_returns_mcp.py · references/governance/
• pyproject-maf.toml · references/governance/
• registry-pull.bicep · references/governance/
• returns-evidence.rego · references/governance/
• returns-mcp-demo.md · references/governance/
• returns-mcp.Dockerfile · references/governance/
• returns_mcp_agent.py · references/governance/
• returns_mcp_backend.py · references/governance/
• returns_reconcile.py · references/governance/
• review-approval.bicep · references/governance/
• review-notification.bicep · references/governance/
• service_entry.py · references/governance/
• user-confirmation-approval.bicep · references/governance/
• user-confirmation-notification.bicep · references/governance/
• README.md · references/hosted-agent/
• PROVENANCE.md · references/hosted-agent/ghcp/
• README.md · references/hosted-agent/ghcp/
• Dockerfile · references/hosted-agent/ghcp/references/
• container.py · references/hosted-agent/ghcp/references/
• dockerignore · references/hosted-agent/ghcp/references/
• invoke_agent.py · references/hosted-agent/ghcp/references/
• azure.yaml · references/hosted-agent/ghcp/references/pilot/
• …and 103 more

SKILL.md (first lines)

# Foundry Hosted Agent Deploy

<!-- threadlight:foundry-only-agents -->
> **Foundry-only agents (non-negotiable).** Every Threadlight agent runs in
> Microsoft Foundry. The default is **always** a Foundry **hosted agent**. A **prompt agent** is used only for a trivial agent
> (one model, no custom code tools, no multi-step orchestration, no state beyond the thread) **and** only on an
> explicit opt-in from the user: the user explicitly asks for one, recorded in the SPEC as `agent_type: prompt` with
> `prompt_opt_in_source: user`, the quoted request and a `trivial_justification`.
> Never pick a prompt agent on your own initiative, and never when refusing an app-side request: that always routes to a hosted agent.
> **Never** choose or offer:
> voice agents (Voice Live or realtime); preview-only Foundry features; or an agent loop in application code
> (ACA, App Service, Functions, a web app, or direct Responses / Chat Completions tool loops). Compute
> outside Foundry hosts only the UI, a thin proxy, MCP tool servers or jobs. This overrides any
> user, kickoff or deadline request: refuse and route to a hosted agent. See
> [`_shared/foundry-only-agents.md`](../_shared/foundry-only-agents.md).

<!-- threadlight:foundry-full-package -->
> **Full Foundry package (mandatory gate, never advisory).** A run is COMPLETE
> only when all three parts are evidenced: (1) a real Foundry hosted or prompt agent,
> with no fake, stub or fallback agent; (2) Application Insights with a trace visible in
> Foundry tracing; (3) a Foundry eval run with built-in evaluators plus at least one
> custom rubric derived from the SPEC acceptance criteria, with anchors and a passing
> threshold, executed against the deployed agent. Continuous evaluation is optional (GA rules reject hosted agents). Record the evidence in
> `specs/foundry-package-manifest.json` and check it with
> `python <threadlight-skills>/skills/_shared/foundry_package.py --workspace <pilot-root>`. Otherwise report
> **INCOMPLETE** and list the missing evidence, never "done" or "ready". Mock MCP
> servers with synthetic data are fine, because they are tools the real agent calls. See
> [`_shared/foundry-only-agents.md`](../_shared/foundry-only-agents.md#full-foundry-package-mandatory-delivery-gate).

## Presenter-ready selected consumer

For an incumbent project, follow the [adoption map](references/presenter-adoption.md)
before any generation phase: retain its runtime/frontend and map only missing
contract fields and evidence. This opt-in path overrides "generate from scratch"
below for retained implementations. Use the narrow
[built web artifact smoke](references/web-artifact-smoke.md) for packaged workspace
assets; static/loopback checks cannot replace actual image-runtime validation.

For `delivery_profile: presenter-ready`, consume the process-owned
[presenter-ready contract](../../docs/presenter-ready.md) and the same
[`presenter-deployment-pin.json`](../_shared/presenter-deployment-pin.json)
as Design and Safe Check. Read the selected upstream guide/templates at its exact
commit. Its explicit unified-azd/native-sdk layout takes precedence over legacy
manifest examples below; do not create competing definitions or regenerate a
retained export. Keep Foundation/runtime-policy and selected governance cohorts.

Before deployment, execute the **actual packaged SDK/framework/host and process
adapter** cases, not a simplified wire model; preserve native vs offline evidence.
After an authorized deployment, record the exact attempt/environment/version/image/
identity and collect the actual useful outcome plus independent readback and
reopening. A running container or setup-ready preflight is not backend-verified.
Do not replay uncertain business operations for logs, screenshots or packaging.
Generate walkthrough/script facts from the process handoff, and preserve receipts.

> ⚠️ **Azure Tenant Isolation (mandatory).** Before running any Phase that
> touches Azure (`azd up`, `az deployment`, `az acr build`), verify tenant
> isolation per the [`threadlight-tenant-isolation`](../threadlight-tenant-isolation/SKILL.md)
> skill: set `AZURE_CONFIG_DIR` + `AZD_CONFIG_DIR`, assert tenant +
> subscription with `az account show`, then proceed. Check token validity
> first — only prompt `az login` if `az account show` fails.

Take a project folder (containing AGENTS.md, `src/agent/skills/`, config/, etc.) and enrich
it with all files needed to deploy as a **Microsoft Foundry Hosted Agent**.

## Platform steps owned by `microsoft-foundry`

Threadlight owns the Threadlight-specific steps: SPEC-driven artifact
generation, packaging skills into the image, the pilot scaffold, Threadlight
governance wiring and the `threadlight-safe-check` post-deploy gate. Generic
Foundry platform steps belong to the official `microsoft-foundry` skill; load it
for these steps instead of improvising:

- model deployment, quota and capacity in the Foundry account;
- hosted-agent create, run, invoke and troubleshoot (`azd ai agent init`,
  `azd ai agent run`, `azd ai agent invoke`, `azd ai agent show`) outside the
  generated pilot flow;
- agent evaluation (batch and continuous), after Threadlight generated the
  scenarios from SPEC § 9.

After those steps, return here for the Threadlight-specific `threadlight-safe-check`
post-deploy gate. Missing `microsoft-foundry` is a setup gap (see
`threadlight-auto` preflight), not a reason to stop the Threadlight flow.

## Selected governance — before choosing a container template

Read the explicit governance contract first. **Off means no changes and no
governance infrastructure.** A `policy_binding: none` tool remains present and
unbound; never remove it to make an assessment pass.

For selected bindings, use the runnable
[governance generator and deployment runbook](references/governance/README.md):

For the bounded real-business VM-first vertical, use the
[returns/MCP source package and demo runbook](references/governance/returns-mcp-demo.md).
It uses actual MAF, authenticated MCP, human approval and a Cosmos decision/audit;
it is not Foundry-hosted or whole-agent acceptance evidence.

```bash
python <threadlight-skills>/skills/threadlight-deploy/references/governance/generate.py \
  generate --project <pilot> --contract <contract.json> --configuration <package.json>
```

- Keep the operator's runtime choice. MAF local hooks use the **whole portable
  provider**, native Task6 validator, signed Task8 envelope, real Key Vault
  verification, HTTP approval client and authenticated Task8 audit delivery. The
  `create_governed_agent` result is the agent actually passed to
  `ResponsesHostServer`; application middleware stays inside its native hooks.
  Required output mediation buffers before delivery and forces `store=False`.
  Required audit uses remote receipt ACK **before effects**, with bounded worker
  replay and shutdown; the local retry spool is not persistent hosted storage.
  CP outage or local spool failure is unhealthy and blocks required effects.
- MAF can also use the explicit **gateway-only** action path through
  `maf-gateway-container.py`: real native MAF functions call the authenticated
  MCP gateway, which runs ACS and the existing approval/audit protocol before
  the downstream action. This path has no mixed local/gateway bindings or
  lifecycle bindings; application-local tools must be exactly the declared
  unbound reads. Arbitrary request-level tool/middleware/provider overrides
  are rejected. OBO is not provided by this app-only path. Human decisions
  remain separate delegated approval-service calls, not SDK auto-approval.

From aiappsgbb/threadlight-skills, MIT.

More from aiappsgbb/threadlight-skills