feat(ai-agents): add managed harness prompt agents by hund030 · Pull Request #9805 · Azure/azure-dev

Zhijie Huang (hund030) · 2026-09-01T05:20:23Z

Summary

Add prompt agents and optional github_copilot_preview managed harness support to the Foundry agent lifecycle, using portable project configuration and service-authoritative capability validation.

Changes

azd ai agent init: scaffold kind: prompt agents, optionally configure a managed harness, and bind an existing or provisioned Foundry project.
Agent lifecycle: support prompt-agent deployment through azd deploy, plus filtered list, show, invoke, and delete flows.
Prompt definitions: map models, instructions, tools, skills, memory, connections, and RAI policies while retaining structural validation and deferring evolving harness support rules to Foundry.
Foundry provisioning: resolve portable project endpoints consistently for greenfield and existing-project environments.

CLI Interface

# Plain prompt agent
azd ai agent init --kind prompt --agent-name my-agent --model gpt-5-mini --instructions "Be helpful."

# Managed harness prompt agent
azd ai agent init --kind prompt --harness github_copilot_preview --agent-name my-agent --model gpt-5-mini --instructions "Be helpful."

The generated azure.yaml agent service can also carry richer prompt configuration:

services:
  my-agent:
    host: azure.ai.agent
    kind: prompt
    name: my-agent
    model: gpt-5-mini
    instructions: Be helpful.
    harness:
      type: github_copilot_preview
    skills:
      - summarize
    tools:
      - type: azure_ai_search
        azure_ai_search:
          index_name: docs
    policies:
      - type: rai_policy
        raiPolicyName: ${RAI_POLICY_ID}

Use --project-id <resource-id> --model-deployment <name> to initialize against an existing Foundry project and deployment. Standard lifecycle commands are azd up, azd deploy, and azd ai agent show|list|invoke|delete.

Manual Validation

Initialized a managed prompt-agent project and successfully provisioned it against an existing Foundry project.
Deployed and invoked a basic managed agent against an enabled test subscription, receiving the expected response marker.
Confirmed through live REST calls that non-strict function, File Search, Azure AI Search, Fabric IQ, and Work IQ tools are accepted; File Search and Azure AI Search reached runtime execution.

…9754) * feat(ai-agents): agent.yaml model and Foundry service clients First of four stacked changes adding managed harness agent support. This one is the data model and the HTTP clients; it adds no commands and performs no deployment, so it can be read on its own. agent_yaml gains the prompt agent manifest: the harness block and its skills, environment and built-in tool controls, the memory block, tool declarations, and the feature gate that decides which manifest features a given harness accepts. Blocks azd interprets reject unknown keys, so a typo such as builtin_tool for builtin_tools fails the parse instead of deploying an agent with capabilities the author believed were off. Tools stay untyped and pass through, so a tool newer than this build still deploys. agent_api gains the managed agent contract and its operations. pkg/azure gains the Foundry data plane clients for files, projects, connections and RAI policies; the toolsets client is removed because the service replaced it with the connections control plane. New spelling terms stay in the extension cspell config rather than the shared core one, which this branch does not touch. * fix(ai-agents): preserve inline RAI policy fields * refactor(ai-agents): reuse unified prompt agent client * refactor(ai-agents): reference supported sibling resources --------- Co-authored-by: hund030 <zhihuan@microsoft.com>

* feat(ai-agents): agent.yaml model and Foundry service clients First of four stacked changes adding managed harness agent support. This one is the data model and the HTTP clients; it adds no commands and performs no deployment, so it can be read on its own. agent_yaml gains the prompt agent manifest: the harness block and its skills, environment and built-in tool controls, the memory block, tool declarations, and the feature gate that decides which manifest features a given harness accepts. Blocks azd interprets reject unknown keys, so a typo such as builtin_tool for builtin_tools fails the parse instead of deploying an agent with capabilities the author believed were off. Tools stay untyped and pass through, so a tool newer than this build still deploys. agent_api gains the managed agent contract and its operations. pkg/azure gains the Foundry data plane clients for files, projects, connections and RAI policies; the toolsets client is removed because the service replaced it with the connections control plane. New spelling terms stay in the extension cspell config rather than the shared core one, which this branch does not touch. * feat(ai-agents): provision and deploy prompt agents Second of four stacked changes. Builds on the model and clients from the previous change and adds the service target that turns a prompt agent manifest into deployed Foundry resources. Deployment is graph driven. The manifest is resolved into nodes for the agent and for every resource it depends on -- memory store, connections, skills, RAI policy -- and the graph decides creation order and reports per node progress. Sibling resources are reconciled rather than recreated, so a redeploy that changes nothing makes no writes. This package is submitted whole rather than split further. The graph types are shared by every node implementation and the nodes are mutually referential, so any smaller cut does not compile without a refactor that would itself need review. * fix(ai-agents): preserve inline RAI policy fields * refactor(ai-agents): reuse unified prompt agent client * refactor(ai-agents): reference supported sibling resources * refactor(ai-agents): align prompt deployment dependencies * fix(ai-agents): constrain prompt deployment to Foundry * fix(ai-agents): scope prompt deployment state * fix(ai-agents): bypass tagged lookup for prompt agents * fix(ai-agents): align prompt schema and policy contract * fix(ai-agents): remove unshipped prompt config fallback --------- Co-authored-by: hund030 <zhihuan@microsoft.com>

* feat(ai-agents): agent.yaml model and Foundry service clients First of four stacked changes adding managed harness agent support. This one is the data model and the HTTP clients; it adds no commands and performs no deployment, so it can be read on its own. agent_yaml gains the prompt agent manifest: the harness block and its skills, environment and built-in tool controls, the memory block, tool declarations, and the feature gate that decides which manifest features a given harness accepts. Blocks azd interprets reject unknown keys, so a typo such as builtin_tool for builtin_tools fails the parse instead of deploying an agent with capabilities the author believed were off. Tools stay untyped and pass through, so a tool newer than this build still deploys. agent_api gains the managed agent contract and its operations. pkg/azure gains the Foundry data plane clients for files, projects, connections and RAI policies; the toolsets client is removed because the service replaced it with the connections control plane. New spelling terms stay in the extension cspell config rather than the shared core one, which this branch does not touch. * feat(ai-agents): provision and deploy prompt agents Second of four stacked changes. Builds on the model and clients from the previous change and adds the service target that turns a prompt agent manifest into deployed Foundry resources. Deployment is graph driven. The manifest is resolved into nodes for the agent and for every resource it depends on -- memory store, connections, skills, RAI policy -- and the graph decides creation order and reports per node progress. Sibling resources are reconciled rather than recreated, so a redeploy that changes nothing makes no writes. This package is submitted whole rather than split further. The graph types are shared by every node implementation and the nodes are mutually referential, so any smaller cut does not compile without a refactor that would itself need review. * feat(ai-agents): CLI surface for managed harness agents Third of four stacked changes. Adds the commands that sit on top of the model and the deployment engine from the previous two. azd ai agent init gains a kind and harness selection and writes the matching manifest, including discovery of an existing Responsible AI policy with a warn and fall back path when none can be read. list, show, delete and invoke gain managed agent handling, with invoke supporting streamed responses. Infrastructure synthesis learns the project endpoint so a generated module resolves it from the environment. Also carries the extension CHANGELOG for all four changes in this stack, since the entries describe features that only exist once the stack is complete. * fix(ai-agents): preserve inline RAI policy fields * refactor(ai-agents): reuse unified prompt agent client * refactor(ai-agents): reference supported sibling resources * refactor(ai-agents): align prompt deployment dependencies * fix(ai-agents): constrain prompt deployment to Foundry * fix(ai-agents): scope prompt deployment state * fix(ai-agents): align prompt CLI with Foundry * fix(ai-agents): enforce managed prompt CLI contract * fix(ai-agents): unify prompt project context * fix(ai-agents): bypass tagged lookup for prompt agents * fix(ai-agents): complete managed prompt invocation * fix(ai-agents): finalize prompt init contract * fix(ai-agents): finalize prompt agent lifecycle --------- Co-authored-by: hund030 <zhihuan@microsoft.com>

…ss-agents # Conflicts: # cli/azd/extensions/azure.ai.agents/internal/cmd/init_infra.go # cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/yaml.go # cli/azd/extensions/azure.ai.agents/internal/pkg/azure/foundry_toolsets_client.go # cli/azd/extensions/azure.ai.agents/internal/pkg/azure/foundry_toolsets_client_test.go # cli/azd/extensions/azure.ai.agents/schemas/azure.ai.agent.json

azure-pipelines · 2026-09-01T05:21:14Z

Azure Pipelines: Successfully started running 4 pipeline(s). 23 pipeline(s) were filtered out due to trigger conditions. There may be pipelines that require an authorized user to comment /azp run to run.

Copilot

Pull request overview

Adds first-class prompt agents and optional managed harness support to the Foundry agent lifecycle.

Changes:

Adds prompt-agent configuration, initialization, and schema support.
Implements deployment dependencies and lifecycle commands.
Adds portable Foundry endpoint resolution for new and existing projects.

Reviewed changes

Copilot reviewed 100 out of 100 changed files in this pull request and generated 10 comments.

Show a summary per file

File	Description
`cli/azd/extensions/azure.ai.agents/README.md`	Updates RAI policy guidance.
`cli/azd/extensions/azure.ai.agents/cspell.yaml`	Adds extension terminology.
`cli/azd/extensions/azure.ai.agents/internal/exterrors/codes.go`	Updates extension error codes.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_api/models.go`	Models prompt-agent API data.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_api/operations.go`	Extends agent API operations.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_api/responses_operations.go`	Implements Responses API calls.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_api/responses_operations_test.go`	Tests Responses API behavior.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/managed_test.go`	Tests managed-agent mapping.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/map.go`	Maps prompt definitions to API requests.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/parse.go`	Validates prompt manifests.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/prompt_features.go`	Validates prompt features and policies.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/prompt_features_test.go`	Tests prompt feature validation.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/prompt_harness_gate.go`	Validates harness configuration.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/prompt_harness_gate_test.go`	Tests harness validation.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/prompt_schema_test.go`	Tests prompt schema behavior.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/prompt_strict_inline.go`	Strictly validates inline blocks.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/prompt_strict_yaml_test.go`	Tests strict YAML decoding.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/prompt_tools.go`	Validates prompt tool definitions.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/prompt_tools_test.go`	Tests prompt tool handling.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/yaml.go`	Defines prompt-agent YAML models.
`cli/azd/extensions/azure.ai.agents/internal/pkg/agents/agent_yaml/yaml_test.go`	Tests YAML model behavior.
`cli/azd/extensions/azure.ai.agents/internal/pkg/azure/foundry_rai_policies.go`	Adds Foundry RAI policy access.
`cli/azd/extensions/azure.ai.agents/internal/pkg/azure/foundry_rai_policies_test.go`	Tests RAI policy utilities.
`cli/azd/extensions/azure.ai.agents/schemas/azure.ai.agent.json`	Extends the public agent schema.
`cli/azd/extensions/azure.ai.agents/internal/project/agent_definition.go`	Resolves prompt definitions.
`cli/azd/extensions/azure.ai.agents/internal/project/agent_definition_ref_test.go`	Tests definition references.
`cli/azd/extensions/azure.ai.agents/internal/project/agent_definition_test.go`	Tests definition loading.
`cli/azd/extensions/azure.ai.agents/internal/project/agent_policies_test.go`	Tests inline policy preservation.
`cli/azd/extensions/azure.ai.agents/internal/project/config.go`	Adds prompt service configuration.
`cli/azd/extensions/azure.ai.agents/internal/project/doc_examples_test.go`	Validates documented examples.
`cli/azd/extensions/azure.ai.agents/internal/project/foundry_dependencies.go`	Extends Foundry dependency checks.
`cli/azd/extensions/azure.ai.agents/internal/project/memory_store.go`	Shares memory-store reconciliation.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_client.go`	Configures prompt API clients.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_client_test.go`	Tests prompt client settings.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_connections.go`	Resolves connection dependencies.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_connections_test.go`	Tests connection resolution.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_convention_test.go`	Tests prompt file conventions.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_deployment.go`	Resolves model deployment nodes.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_deployment_test.go`	Tests deployment nodes.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_environment_test.go`	Tests deployment environment outputs.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_graph.go`	Builds the deployment graph.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_graph_warnings_test.go`	Tests deployment warnings.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_headers_test.go`	Tests request headers.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_inline.go`	Decodes inline prompt definitions.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_inline_test.go`	Tests inline definitions.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_json_schema_test.go`	Tests schema integration.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_memory.go`	Provisions prompt memory stores.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_memory_test.go`	Tests memory provisioning.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_policy_node.go`	Verifies RAI policy dependencies.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_policy_node_test.go`	Tests policy dependency handling.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_skills.go`	Resolves skills and toolboxes.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_skills_test.go`	Tests skills and toolboxes.
`cli/azd/extensions/azure.ai.agents/internal/project/prompt_tools_test.go`	Tests prompt tool deployment.
`cli/azd/extensions/azure.ai.agents/internal/project/service_target_agent.go`	Dispatches prompt service targets.
`cli/azd/extensions/azure.ai.agents/internal/project/service_target_agent_test.go`	Tests service-target initialization.
`cli/azd/extensions/azure.ai.agents/internal/project/service_target_prompt.go`	Implements prompt deployment.
`cli/azd/extensions/azure.ai.agents/internal/cmd/agent_endpoint.go`	Resolves prompt endpoints.
`cli/azd/extensions/azure.ai.agents/internal/cmd/delete.go`	Adds prompt-agent deletion.
`cli/azd/extensions/azure.ai.agents/internal/cmd/doctor/checks_agent_status.go`	Extends status diagnostics.
`cli/azd/extensions/azure.ai.agents/internal/cmd/helpers.go`	Supports prompt service resolution.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init.go`	Routes prompt initialization.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_adopt.go`	Integrates prompt adoption.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_adopt_test.go`	Tests adoption behavior.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_from_code.go`	Aligns code initialization.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_from_templates_helpers.go`	Adds template helpers.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_from_templates_helpers_test.go`	Tests template helpers.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_infra.go`	Integrates Foundry infrastructure.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_managed.go`	Scaffolds prompt agents.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_managed_flags_test.go`	Tests managed flags.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_managed_foundry.go`	Resolves Foundry targets and models.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_managed_manifest_test.go`	Tests manifest-based initialization.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_managed_test.go`	Tests prompt initialization.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_rai_policy.go`	Adds RAI policy selection.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_rai_policy_test.go`	Tests policy selection.
`cli/azd/extensions/azure.ai.agents/internal/cmd/init_test.go`	Extends init coverage.
`cli/azd/extensions/azure.ai.agents/internal/cmd/invoke.go`	Routes prompt invocation.
`cli/azd/extensions/azure.ai.agents/internal/cmd/invoke_managed.go`	Streams prompt responses.
`cli/azd/extensions/azure.ai.agents/internal/cmd/invoke_managed_stream_test.go`	Tests SSE streaming.
`cli/azd/extensions/azure.ai.agents/internal/cmd/invoke_managed_test.go`	Tests prompt invocation.
`cli/azd/extensions/azure.ai.agents/internal/cmd/list.go`	Lists prompt agents.
`cli/azd/extensions/azure.ai.agents/internal/cmd/list_prompt_test.go`	Tests prompt listing.
`cli/azd/extensions/azure.ai.agents/internal/cmd/listen.go`	Adds prompt cleanup hooks.
`cli/azd/extensions/azure.ai.agents/internal/cmd/nextstep/error_codes.go`	Updates next-step errors.
`cli/azd/extensions/azure.ai.agents/internal/cmd/project_endpoint.go`	Validates Foundry endpoints.
`cli/azd/extensions/azure.ai.agents/internal/cmd/project_endpoint_test.go`	Tests endpoint validation.
`cli/azd/extensions/azure.ai.agents/internal/cmd/prompt_service.go`	Resolves prompt service context.
`cli/azd/extensions/azure.ai.agents/internal/cmd/prompt_service_test.go`	Tests prompt service resolution.
`cli/azd/extensions/azure.ai.agents/internal/cmd/resource_services.go`	Emits Foundry sibling services.
`cli/azd/extensions/azure.ai.agents/internal/cmd/resource_services_test.go`	Tests sibling service emission.
`cli/azd/extensions/azure.ai.agents/internal/cmd/root.go`	Registers the list command.
`cli/azd/extensions/azure.ai.agents/internal/cmd/show.go`	Adds prompt-agent status output.
`cli/azd/extensions/azure.ai.agents/internal/cmd/show_test.go`	Tests prompt status output.
`cli/azd/extensions/azure.ai.agents/internal/synthesis/synthesizer.go`	Expands portable project endpoints.
`cli/azd/extensions/azure.ai.agents/internal/synthesis/synthesizer_test.go`	Tests endpoint expansion.
`cli/azd/extensions/azure.ai.projects/internal/provisioning/foundry_provisioning_provider.go`	Resolves portable provisioning targets.
`cli/azd/extensions/azure.ai.projects/internal/provisioning/foundry_provisioning_provider_test.go`	Tests resolved project endpoints.
`cli/azd/extensions/azure.ai.projects/internal/provisioning/resource_group_location_check.go`	Handles portable brownfield endpoints.
`cli/azd/extensions/azure.ai.projects/internal/provisioning/resource_group_location_check_validate_test.go`	Tests location-check routing.
`cli/azd/extensions/azure.ai.projects/internal/synthesis/synthesizer.go`	Mirrors endpoint expansion logic.
`cli/azd/extensions/azure.ai.projects/internal/synthesis/synthesizer_test.go`	Updates synthesis endpoint tests.

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

+
+			switch {
+			case requestedKind == AgentKindChoicePrompt:
+				harness, harnessErr := resolveInitHarness(flags.harness, "")


+		promptAgent.Skills = manifest.definition.Skills
+		promptAgent.Tools = manifest.definition.Tools
+		promptAgent.ToolChoice = manifest.definition.ToolChoice
+		promptAgent.StructuredInputs = manifest.definition.StructuredInputs
+		promptAgent.Policies = manifest.definition.Policies


 	projectCfg, err := project.MarshalStruct(&project.ServiceTargetAgentConfig{
 		Endpoint:    projectEndpoint,
-		Deployments: deployments,
+		Deployments: resources.Deployments,
 	})


+	if !runtime.HasStatusCode(resp, http.StatusOK, http.StatusCreated, http.StatusAccepted) {
+		return nil, nil, runtime.NewResponseError(resp)
+	}


+	for entry := range strings.SplitSeq(env["AZURE_AI_PROJECT_CONNECTION_NAMES"], ",") {
+		if strings.EqualFold(strings.TrimSpace(entry), strings.TrimSpace(name)) {
+			return true


+	if strings.HasPrefix(trimmed, raiPolicyIDPrefix) && strings.Contains(trimmed, raiPolicyIDSegment) {
+		return nil


+		return err
+	}
+
+	list, err := client.ListAgents(ctx, promptListQuery(), pctx.Settings.EffectiveAPIVersion())


  "properties": {
+    "promptAgent": {
+      "type": "object",
+      "description": "Marks the service as a Prompt-family (prompt, prompt-voice, managed) agent and tells azd how to reach the harness that runs it. `azd ai agent init` writes every field as a ${VAR} reference so azure.yaml carries no tenant-specific values.",


+    },
+    "$ref": {
+      "type": "string",
+      "description": "Path to the file carrying this agent's definition, relative to the service's project directory. Defaults to agent.yaml when omitted."


+  policy, it only associates the agent with an existing one. For prompt and
+  managed agents, `azd ai agent init` lists the policies on the selected account
+  and can bind one for you; see `--rai-policy`.


azure-sdk-automation · 2026-09-02T11:41:05Z

azure.ai.agents PR build

Note

This is an unsigned development build. Install it only if you trust this PR.

Install the extension:

azd ext install "https://azuresdkartifacts.z5.web.core.windows.net/azd/extensions/pr/9805/azure-ai-agents.zip"

Version: 1.0.0-beta.13.pr.9805.6777781
Merge commit: e14f548

azure-sdk-automation · 2026-09-02T11:43:09Z

azure.ai.projects PR build

Note

This is an unsigned development build. Install it only if you trust this PR.

Install the extension:

azd ext install "https://azuresdkartifacts.z5.web.core.windows.net/azd/extensions/pr/9805/azure-ai-projects.zip"

Version: 1.0.0-beta.8.pr.9805.6777782
Merge commit: e14f548

…ss-agents

Kshitij Chawla (kshitij-microsoft) and others added 6 commits August 31, 2026 11:00

fix(ai-agents): harden prompt agent lifecycle

d231cab

fix(ai-agents): defer harness capability validation

74c9b34

microsoft-github-policy-service Bot assigned Zhijie Huang (hund030) Sep 1, 2026

github-actions Bot added area/extensions Extensions (general) ext-agents azure.ai.agents extension labels Sep 1, 2026

Zhijie Huang (hund030) requested review from Hui Miao (huimiu) and Travis Angevine (trangevi) and a balanced review from Copilot September 1, 2026 06:12

Copilot started reviewing on behalf of Zhijie Huang (hund030) September 1, 2026 06:13 View session

Zhijie Huang (hund030) linked an issue Sep 1, 2026 that may be closed by this pull request

Support prompt and managed harness agents in azd #9807

Open

Copilot AI reviewed Sep 1, 2026

View reviewed changes

fix(ai-agents): use published connections dependency

830bcc7

github-actions Bot added the ext-projects azure.ai.projects extension label Sep 2, 2026

Zhijie Huang (hund030) added 3 commits September 2, 2026 15:35

fix(ai-agents): publish versioned prompt skill references

e755b72

Merge origin/main into feature/managed-harness-agents

1057f07

fix(ai-agents): route prompt manifest adoption correctly

1b4714b

Zhijie Huang (hund030) added 2 commits September 3, 2026 14:29

fix(ai-agents): reuse existing models for prompt adoption

b02e17b

Merge remote-tracking branch 'origin/main' into feature/managed-harne…

e358467

…ss-agents

Navigation Menu

Uh oh!

feat(ai-agents): add managed harness prompt agents - #9805

feat(ai-agents): add managed harness prompt agents#9805
Zhijie Huang (hund030) wants to merge 12 commits into
mainfrom
feature/managed-harness-agents

Zhijie Huang (hund030) commented Sep 1, 2026 •

edited

Loading

Uh oh!

azure-pipelines Bot commented Sep 1, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

azure-sdk-automation Bot commented Sep 2, 2026

Uh oh!

azure-sdk-automation Bot commented Sep 2, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

		if strings.HasPrefix(trimmed, raiPolicyIDPrefix) && strings.Contains(trimmed, raiPolicyIDSegment) {
		return nil

Uh oh!

Conversation

Zhijie Huang (hund030) commented Sep 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Changes

CLI Interface

Manual Validation

Uh oh!

azure-pipelines Bot commented Sep 1, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

azure-sdk-automation Bot commented Sep 2, 2026

azure.ai.agents PR build

Uh oh!

azure-sdk-automation Bot commented Sep 2, 2026

azure.ai.projects PR build

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Zhijie Huang (hund030) commented Sep 1, 2026 •

edited

Loading