agent/agent-framework
1
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Python: [Feature Branch] Merge from main to Azure AI branch (#2111)

Browse Source 
* Do not build DevUI assets during .NET project build (#2010)

* .NET: Add unit tests for declarative executor SetMultipleVariables (#2016)

* Add unit tests for create conversation executor

* Update indentation and comment typo.

* Added unit tests for declarative executor SetMultipleVariablesExecutor

* Updated comments and syntactic sugar

* Python: DevUI: Use metadata.entity_id instead of model field (#1984)

* DevUI: Use metadata.entity_id for agent/workflow name instead of model field

* OpenAI Responses: add explicit request validation

* Review feedback

* .NET: DevUI - Do not automatically add/map OpenAI services/endpoints (#2014)

* Don't add OpenAIResponses as part of Dev UI

You should be able to add and remove Dev UI without impacting your other production endpoints.

* Remove `AddDevUI()` and do not map OpenAI endpoints from `MapDevUI()`

* Fix comment wording

* Revise documentation

---------

Co-authored-by: Daniel Roth <daroth@microsoft.com>

* Python: DevUI: Add OpenAI Responses API proxy support  + HIL for Workflows (#1737)

* DevUI: Add OpenAI Responses API proxy support with enhanced UI features

This commit adds support for proxying requests to OpenAI's Responses API,
allowing DevUI to route conversations to OpenAI models when configured to enable testing.

Backend changes:
- Add OpenAI proxy executor with conversation routing logic
- Enhance event mapper to support OpenAI Responses API format
- Extend server endpoints to handle OpenAI proxy mode
- Update models with OpenAI-specific response types
- Remove emojis from logging and CLI output for cleaner text

Frontend changes:
- Add settings modal with OpenAI proxy configuration UI
- Enhance agent and workflow views with improved state management
- Add new UI components (separator, switch) for settings
- Update debug panel with better event filtering
- Improve message renderers for OpenAI content types
- Update types and API client for OpenAI integration

* update ui, settings modal and workflow input form, add register cleanup hooks.

* add workflow HIL support, user mode, other fixes

* feat(devui): add human-in-the-loop (HIL) support with dynamic response schemas

Implement  HIL workflow support allowing workflows to pause for user input
with dynamically generated JSON schemas based on response handler type hints.

Key Features:
- Automatic response schema extraction from @response_handler decorators
- Dynamic form generation in UI based on Pydantic/dataclass response types
- Checkpoint-based conversation storage for HIL requests/responses
- Resume workflow execution after user provides HIL response

Backend Changes:
- Add extract_response_type_from_executor() to introspect response handlers
- Enrich RequestInfoEvent with response_schema via _enrich_request_info_event_with_response_schema()
- Map RequestInfoEvent to response.input.requested OpenAI event format
- Store HIL responses in conversation history and restore checkpoints

Frontend Changes:
- Add HILInputModal component with SchemaFormRenderer for dynamic forms
- Support Pydantic BaseModel and dataclass response types
- Render enum fields as dropdowns, strings as text/textarea, numbers, booleans, arrays, objects
- Display original request context alongside response form

Testing:
- Add  tests for checkpoint storage (test_checkpoints.py)
- Add schema generation tests for all input types (test_schema_generation.py)
- Validate end-to-end HIL flow with spam workflow sample

This enables workflows to seamlessly pause execution and request structured user input
with type-safe, validated forms generated automatically from response type annotations.

* improve HIL support, improve workflow execution view

* ui updates

* ui updates

* improve HIL for workflows, add auth and view modes

* update workflow

* security improvements , ui fixes

* fix mypy error

* update loading spinner in ui

---------

Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com>

* .NET: Remove launchSettings.json from .gitignore in dotnet/samples (#2006)

* Remove launchSettings.json from .gitignore in dotnet/samples

* Update dotnet/samples/GettingStarted/DevUI/DevUI_Step01_BasicUsage/Properties/launchSettings.json

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update dotnet/samples/AGUIClientServer/AGUIServer/Properties/launchSettings.json

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* DevUI: Serialize workflow input as string to maintain conformance with OpenAI Responses format (#2021)

Co-authored-by: Victor Dibia <chuvidi2003@gmail.com>

* Add Microsoft Agent Framework logo to assets (#2007)

* Updated package versions (#2027)

* DevUI: Prevent line breaks within words in the agent view (#2024)

Co-authored-by: Victor Dibia <chuvidi2003@gmail.com>

* .NET [AG-UI]: Adds support for shared state. (#1996)

* Product changes

* Tests

* Dojo project

* Cleanups

* Python: Fix underlying tool choice bug and all for return to previous Handoff subagent (#2037)

* Fix tool_choice override bug and add enable_return_to_previous support

* Add unit test for handoff checkpointing

* Handle tools when we have them

* added missing chatAgent params (#2044)

* .NET: fix ChatCompletions Tools serialization (#2043)

* fix serialization in chat completions on tools

* nit

* .NET: assign AgentCard's URL to mapped-endpoint if not defined explicitly (#2047)

* fix serialization in chat completions on tools

* nit

* write e2e test for agent card resolve + adjust behavior

* nit

* Version 1.0.0-preview.251110.1 (#2048)

* .NET: Remove moved OpenAPI sample and point to SK one. (#1997)

* Remove moved OpenAPI sample and point to SK one.

* Update dotnet/samples/GettingStarted/Agents/README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.2 to 4.0.4.6 (#2031)

---
updated-dependencies:
- dependency-name: AWSSDK.Extensions.Bedrock.MEAI
  dependency-version: 4.0.4.6
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* .NET: Separate all memory and rag samples into their own folders (#2000)

* Separate all memory and rag samples into their own folders

* Fix broken link.

* Python: .Net: Dotnet devui compatibility fixes (#2026)

* DevUI: Add OpenAI Responses API proxy support with enhanced UI features

This commit adds support for proxying requests to OpenAI's Responses API,
allowing DevUI to route conversations to OpenAI models when configured to enable testing.

Backend changes:
- Add OpenAI proxy executor with conversation routing logic
- Enhance event mapper to support OpenAI Responses API format
- Extend server endpoints to handle OpenAI proxy mode
- Update models with OpenAI-specific response types
- Remove emojis from logging and CLI output for cleaner text

Frontend changes:
- Add settings modal with OpenAI proxy configuration UI
- Enhance agent and workflow views with improved state management
- Add new UI components (separator, switch) for settings
- Update debug panel with better event filtering
- Improve message renderers for OpenAI content types
- Update types and API client for OpenAI integration

* update ui, settings modal and workflow input form, add register cleanup hooks.

* add workflow HIL support, user mode, other fixes

* feat(devui): add human-in-the-loop (HIL) support with dynamic response schemas

Implement  HIL workflow support allowing workflows to pause for user input
with dynamically generated JSON schemas based on response handler type hints.

Key Features:
- Automatic response schema extraction from @response_handler decorators
- Dynamic form generation in UI based on Pydantic/dataclass response types
- Checkpoint-based conversation storage for HIL requests/responses
- Resume workflow execution after user provides HIL response

Backend Changes:
- Add extract_response_type_from_executor() to introspect response handlers
- Enrich RequestInfoEvent with response_schema via _enrich_request_info_event_with_response_schema()
- Map RequestInfoEvent to response.input.requested OpenAI event format
- Store HIL responses in conversation history and restore checkpoints

Frontend Changes:
- Add HILInputModal component with SchemaFormRenderer for dynamic forms
- Support Pydantic BaseModel and dataclass response types
- Render enum fields as dropdowns, strings as text/textarea, numbers, booleans, arrays, objects
- Display original request context alongside response form

Testing:
- Add  tests for checkpoint storage (test_checkpoints.py)
- Add schema generation tests for all input types (test_schema_generation.py)
- Validate end-to-end HIL flow with spam workflow sample

This enables workflows to seamlessly pause execution and request structured user input
with type-safe, validated forms generated automatically from response type annotations.

* improve HIL support, improve workflow execution view

* ui updates

* ui updates

* improve HIL for workflows, add auth and view modes

* update workflow

* security improvements , ui fixes

* fix mypy error

* update loading spinner in ui

* DevUI: Serialize workflow input as string to maintain conformance with OpenAI Responses format

* Phase 1: Add /meta endpoint and fix workflow event naming for .NET DevUI compatibility

* additional fixes for .NET DevUI workflow visualization item ID tracking

**Problem:**
.NET DevUI was generating different item IDs for ExecutorInvokedEvent and
ExecutorCompletedEvent, causing only the first executor to highlight in the
workflow graph. Long executor names and error messages also broke UI layout.

**Changes:**
- Add ExecutorActionItemResource to match Python DevUI implementation
- Track item IDs per executor using dictionary in AgentRunResponseUpdateExtensions
- Reuse same item ID across invoked/completed/failed events for proper pairing
- Add truncateText() utility to workflow-utils.ts
- Truncate executor names to 35 chars in execution timeline
- Truncate error messages to 150 chars in workflow graph nodes

** Details:**
- ExecutorActionItemResource registered with JSON source generation context
- Dictionary cleaned up after executor completion/failure to prevent memory leaks
- Frontend item tracking by unique item.id supports multiple executor runs
- All changes follow existing codebase patterns and conventions

Tested with review-workflow showing correct executor highlighting and state
transitions for sequential and concurrent executors.

* format fixes, remove cors tests

* remove unecessary attributes

---------

Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com>
Co-authored-by: Reuben Bond <reuben.bond@gmail.com>

* DevUI: support having both an agent and a workflow with the same id in discovery (#2023)

* Python: Fix Model ID attribute not showing up in `invoke_agent` span (#2061)

* Best effort to surface the model id to invoke agent span

* Fix tests

* Fix tests

* Version 1.0.0-preview.251107.2 (#2065)

* Version 1.0.0-preview.251110.2 (#2067)

* Update README.md to change Grafana links to Azure portal links for dashboard access (#1983)

* .NET - Enable build & test on branch `feature-foundry-agents` (#2068)

* Tests good, mkay

* Update .github/workflows/dotnet-build-and-test.yml

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Enable feature build pipelines

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>

* Python: Add concrete AGUIChatClient (#2072)

* Add concrete AGUIChatClient

* Update logging docstrings and conventions

* PR feedback

* Updates to support client-side tool calls

* .NET: Move catalog samples to the HostedAgents folder (#2090)

* move catalog samples to the HostedAgents folder

* move the catalog samples' projects to the HostedAgents folder

* Bump OpenTelemetry.Instrumentation.Runtime from 1.12.0 to 1.13.0 (#1856)

---
updated-dependencies:
- dependency-name: OpenTelemetry.Instrumentation.Runtime
  dependency-version: 1.13.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* .NET: Bump Microsoft.SemanticKernel.Agents.Abstractions from 1.66.0 to 1.67.0 (#1962)

* Bump Microsoft.SemanticKernel.Agents.Abstractions from 1.66.0 to 1.67.0

---
updated-dependencies:
- dependency-name: Microsoft.SemanticKernel.Agents.Abstractions
  dependency-version: 1.67.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

* .NET: Bump all Microsoft.SemanticKernel packages from 1.66.* to 1.67.* (#1969)

* Initial plan

* Update all Microsoft.SemanticKernel packages to 1.67.*

Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>

* Remove unrelated changes to package-lock.json and yarn.lock

Co-authored-by: markwallace-microsoft <127216156+markwallace-microsoft@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>
Co-authored-by: markwallace-microsoft <127216156+markwallace-microsoft@users.noreply.github.com>

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>
Co-authored-by: markwallace-microsoft <127216156+markwallace-microsoft@users.noreply.github.com>

* .NET: fix: WorkflowAsAgent Sample (#1787)

* fix: WorkflowAsAgent Sample

* Also makes ChatForwardingExecutor public

* feat: Expand ChatForwardingExecutor handled types

Make ChatForwardingExecutor match the input types of ChatProtocolExecutor.

* fix: Update for the new AgentRunResponseUpdate merge logic

AIAgent always sends out List<ChatMessage> now.

* Updated (#2076)

* Bump vite in /python/samples/demos/chatkit-integration/frontend (#1918)

Bumps [vite](https://github.com/vitejs/vite/tree/HEAD/packages/vite) from 7.1.9 to 7.1.12.
- [Release notes](https://github.com/vitejs/vite/releases)
- [Changelog](https://github.com/vitejs/vite/blob/v7.1.12/packages/vite/CHANGELOG.md)
- [Commits](https://github.com/vitejs/vite/commits/v7.1.12/packages/vite)

---
updated-dependencies:
- dependency-name: vite
  dependency-version: 7.1.12
  dependency-type: direct:development
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Bump Roslynator.Analyzers from 4.14.0 to 4.14.1 (#1857)

---
updated-dependencies:
- dependency-name: Roslynator.Analyzers
  dependency-version: 4.14.1
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Bump MishaKav/pytest-coverage-comment from 1.1.57 to 1.1.59 (#2034)

Bumps [MishaKav/pytest-coverage-comment](https://github.com/mishakav/pytest-coverage-comment) from 1.1.57 to 1.1.59.
- [Release notes](https://github.com/mishakav/pytest-coverage-comment/releases)
- [Changelog](https://github.com/MishaKav/pytest-coverage-comment/blob/main/CHANGELOG.md)
- [Commits](https://github.com/mishakav/pytest-coverage-comment/compare/v1.1.57...v1.1.59)

---
updated-dependencies:
- dependency-name: MishaKav/pytest-coverage-comment
  dependency-version: 1.1.59
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>

* Python: Handle agent user input request in AgentExecutor (#2022)

* Handle agent user input request in AgentExecutor

* fix test

* Address comments

* Fix tests

* Fix tests

* Address comments

* Address comments

* Python: OpenAI Responses Image Generation Stream Support, Sample and Unit Tests (#1853)

* support for image gen streaming

* small fixes

* fixes

* added comment

* Python: Fix MCP Tool Parameter Descriptions Not Propagated to LLMs (#1978)

* mcp tool description fix

* small fix

* .NET: Allow extending agent run options via additional properties (#1872)

* Allow extending agent run options via additional properties

This mirrors the M.E.AI model in ChatOptions.AdditionalProperties which is very useful when building functionality pipelines.

Fixes https://github.com/microsoft/agent-framework/issues/1815

* Expand XML documentation

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Add AdditionalProperties tests to AgentRunOptions

Co-authored-by: kzu <169707+kzu@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: kzu <169707+kzu@users.noreply.github.com>

* Python: Use the last entry in the task history to avoid empty responses (#2101)

* Use the last entry in the task history to avoid empty responses

* History only contains Messages

* Updated package versions (#2104)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Reuben Bond <203839+ReubenBond@users.noreply.github.com>
Co-authored-by: Peter Ibekwe <109177538+peibekwe@users.noreply.github.com>
Co-authored-by: Jeff Handley <jeffhandley@users.noreply.github.com>
Co-authored-by: Daniel Roth <daroth@microsoft.com>
Co-authored-by: Victor Dibia <chuvidi2003@gmail.com>
Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Shawn Henry <sphenry@gmail.com>
Co-authored-by: Javier Calvarro Nelson <jacalvar@microsoft.com>
Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com>
Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com>
Co-authored-by: Korolev Dmitry <deagle.gross@gmail.com>
Co-authored-by: westey <164392973+westey-m@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Reuben Bond <reuben.bond@gmail.com>
Co-authored-by: Tao Chen <taochen@microsoft.com>
Co-authored-by: wuweng <wuweng@microsoft.com>
Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com>
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Jacob Alber <jaalber@microsoft.com>
Co-authored-by: Giles Odigwe <79032838+giles17@users.noreply.github.com>
Co-authored-by: Daniel Cazzulino <daniel@cazzulino.com>
Co-authored-by: kzu <169707+kzu@users.noreply.github.com>
This commit is contained in:
Dmytro Struk
2025-11-11 23:12:09 -08:00
committed by GitHub
Unverified
parent 85fcd230bf
commit 361c47f30f
231 changed files with 19659 additions and 4143 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/packages/devui/agent_framework_devui/models/__init__.py
+12 -1
View File
@@ -27,14 +27,18 @@ from openai.types.responses import (
from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails
from openai.types.shared import Metadata, ResponsesModel
from ._discovery_models import DiscoveryResponse, EntityInfo
from ._discovery_models import Deployment, DeploymentConfig, DeploymentEvent, DiscoveryResponse, EntityInfo
from ._openai_custom import (
AgentFrameworkRequest,
CustomResponseOutputItemAddedEvent,
CustomResponseOutputItemDoneEvent,
ExecutorActionItem,
MetaResponse,
OpenAIError,
ResponseFunctionResultComplete,
ResponseOutputData,
ResponseOutputFile,
ResponseOutputImage,
ResponseTraceEvent,
ResponseTraceEventComplete,
ResponseWorkflowEventComplete,
@@ -51,10 +55,14 @@ __all__ = [
"ConversationItem",
"CustomResponseOutputItemAddedEvent",
"CustomResponseOutputItemDoneEvent",
"Deployment",
"DeploymentConfig",
"DeploymentEvent",
"DiscoveryResponse",
"EntityInfo",
"ExecutorActionItem",
"InputTokensDetails",
"MetaResponse",
"Metadata",
"OpenAIError",
"OpenAIResponse",
@@ -67,6 +75,9 @@ __all__ = [
"ResponseFunctionToolCall",
"ResponseFunctionToolCallOutputItem",
"ResponseInputParam",
"ResponseOutputData",
"ResponseOutputFile",
"ResponseOutputImage",
"ResponseOutputItemAddedEvent",
"ResponseOutputItemDoneEvent",
"ResponseOutputMessage",
python/packages/devui/agent_framework_devui/models/_discovery_models.py
+147 -1
View File
@@ -4,9 +4,10 @@
from __future__ import annotations
import re
from typing import Any
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, field_validator
class EnvVarRequirement(BaseModel):
@@ -36,6 +37,10 @@ class EntityInfo(BaseModel):
# Environment variable requirements
required_env_vars: list[EnvVarRequirement] | None = None
# Deployment support
deployment_supported: bool = False # Whether entity can be deployed
deployment_reason: str | None = None # Explanation of why/why not entity can be deployed
# Agent-specific fields (optional, populated when available)
instructions: str | None = None
model_id: str | None = None
@@ -55,3 +60,144 @@ class DiscoveryResponse(BaseModel):
"""Response model for entity discovery."""
entities: list[EntityInfo] = Field(default_factory=list)
# ============================================================================
# Deployment Models
# ============================================================================
class DeploymentConfig(BaseModel):
"""Configuration for deploying an entity."""
entity_id: str = Field(description="Entity ID to deploy")
resource_group: str = Field(description="Azure resource group name")
app_name: str = Field(description="Azure Container App name")
region: str = Field(default="eastus", description="Azure region")
ui_mode: str = Field(default="user", description="UI mode (user or developer)")
ui_enabled: bool = Field(default=True, description="Whether to enable web interface")
stream: bool = Field(default=True, description="Stream deployment events")
@field_validator("app_name")
@classmethod
def validate_app_name(cls, v: str) -> str:
"""Validate Azure Container App name format.
Azure Container App names must:
- Be 3-32 characters long
- Contain only lowercase letters, numbers, and hyphens
- Start with a lowercase letter
- End with a lowercase letter or number
- Not contain consecutive hyphens
"""
if not v:
raise ValueError("app_name cannot be empty")
if len(v) < 3 or len(v) > 32:
raise ValueError("app_name must be between 3 and 32 characters")
if not re.match(r"^[a-z][a-z0-9-]*[a-z0-9]$", v):
raise ValueError(
"app_name must start with a lowercase letter, "
"end with a letter or number, and contain only lowercase letters, numbers, and hyphens"
)
if "--" in v:
raise ValueError("app_name cannot contain consecutive hyphens")
return v
@field_validator("resource_group")
@classmethod
def validate_resource_group(cls, v: str) -> str:
"""Validate Azure resource group name format.
Azure resource group names must:
- Be 1-90 characters long
- Contain only alphanumeric, underscore, parentheses, hyphen, period (except at end)
- Not end with a period
"""
if not v:
raise ValueError("resource_group cannot be empty")
if len(v) > 90:
raise ValueError("resource_group must be 90 characters or less")
if not re.match(r"^[a-zA-Z0-9._()-]+$", v):
raise ValueError(
"resource_group can only contain alphanumeric characters, "
"underscores, hyphens, periods, and parentheses"
)
if v.endswith("."):
raise ValueError("resource_group cannot end with a period")
return v
@field_validator("region")
@classmethod
def validate_region(cls, v: str) -> str:
"""Validate Azure region format.
Validates that the region string is a reasonable format.
Does not validate against the full list of Azure regions (which changes).
"""
if not v:
raise ValueError("region cannot be empty")
if len(v) > 50:
raise ValueError("region name too long")
# Azure regions are typically lowercase with no spaces (e.g., eastus, westeurope)
if not re.match(r"^[a-z0-9]+$", v):
raise ValueError("region must contain only lowercase letters and numbers (e.g., eastus, westeurope)")
return v
@field_validator("entity_id")
@classmethod
def validate_entity_id(cls, v: str) -> str:
"""Validate entity_id format to prevent injection attacks."""
if not v:
raise ValueError("entity_id cannot be empty")
if len(v) > 256:
raise ValueError("entity_id too long")
# Allow alphanumeric, hyphens, underscores, and periods
if not re.match(r"^[a-zA-Z0-9._-]+$", v):
raise ValueError("entity_id contains invalid characters")
return v
@field_validator("ui_mode")
@classmethod
def validate_ui_mode(cls, v: str) -> str:
"""Validate ui_mode is one of the allowed values."""
if v not in ("user", "developer"):
raise ValueError("ui_mode must be 'user' or 'developer'")
return v
class DeploymentEvent(BaseModel):
"""Real-time deployment event (SSE)."""
type: str = Field(description="Event type (e.g., deploy.validating, deploy.building)")
message: str = Field(description="Human-readable message")
url: str | None = Field(default=None, description="Deployment URL (on completion)")
auth_token: str | None = Field(default=None, description="Auth token (on completion, shown once)")
class Deployment(BaseModel):
"""Deployment record."""
id: str = Field(description="Deployment ID (UUID)")
entity_id: str = Field(description="Entity ID that was deployed")
resource_group: str = Field(description="Azure resource group")
app_name: str = Field(description="Azure Container App name")
region: str = Field(description="Azure region")
url: str = Field(description="Deployment URL")
status: str = Field(description="Deployment status (deploying, deployed, failed)")
created_at: str = Field(description="ISO 8601 timestamp")
error: str | None = Field(default=None, description="Error message if failed")
python/packages/devui/agent_framework_devui/models/_openai_custom.py
+192 -10
View File
@@ -80,9 +80,16 @@ class CustomResponseOutputItemDoneEvent(BaseModel):
class ResponseWorkflowEventComplete(BaseModel):
"""Complete workflow event data."""
"""Complete workflow event data.
type: Literal["response.workflow_event.complete"] = "response.workflow_event.complete"
DevUI extension for workflow execution events (debugging/observability).
Uses past-tense 'completed' to follow OpenAI's event naming pattern.
Workflow events are shown in the debug panel for monitoring execution flow,
not in main chat. Use response.output_item.added for user-facing content.
"""
type: Literal["response.workflow_event.completed"] = "response.workflow_event.completed"
data: dict[str, Any] # Complete event data, not delta
executor_id: str | None = None
item_id: str
@@ -91,9 +98,17 @@ class ResponseWorkflowEventComplete(BaseModel):
class ResponseTraceEventComplete(BaseModel):
"""Complete trace event data."""
"""Complete trace event data.
type: Literal["response.trace.complete"] = "response.trace.complete"
DevUI extension for non-displayable debugging/metadata events.
Uses past-tense 'completed' to follow OpenAI's event naming pattern
(e.g., response.completed, response.output_item.added).
Trace events are shown in the Traces debug panel, not in main chat.
Use response.output_item.added for user-facing content.
"""
type: Literal["response.trace.completed"] = "response.trace.completed"
data: dict[str, Any] # Complete trace data, not delta
span_id: str | None = None
item_id: str
@@ -124,6 +139,139 @@ class ResponseFunctionResultComplete(BaseModel):
timestamp: str | None = None # Optional timestamp for UI display
class ResponseRequestInfoEvent(BaseModel):
"""DevUI extension: Workflow requests human input.
This is a DevUI extension because:
- OpenAI Responses API doesn't have a concept of workflow human-in-the-loop pausing
- Agent Framework workflows can pause via RequestInfoExecutor to collect external information
- Clients need to render forms and submit responses to continue workflow execution
When a workflow emits this event, it enters IDLE_WITH_PENDING_REQUESTS state.
Client should render a form based on request_schema and submit responses via
a new request with workflow_hil_response content type.
"""
type: Literal["response.request_info.requested"] = "response.request_info.requested"
request_id: str
"""Unique identifier for correlating this request with the response."""
source_executor_id: str
"""ID of the executor that is waiting for this response."""
request_type: str
"""Fully qualified type name of the request (e.g., 'module.path:ClassName')."""
request_data: dict[str, Any]
"""Current data from the RequestInfoMessage (may contain defaults/context)."""
request_schema: dict[str, Any]
"""JSON schema describing the request data structure (what the workflow is asking about)."""
response_schema: dict[str, Any] | None = None
"""JSON schema describing the expected response structure for form rendering (what user should provide)."""
item_id: str
"""OpenAI item ID for correlation."""
output_index: int = 0
"""Output index for OpenAI compatibility."""
sequence_number: int
"""Sequence number for ordering events."""
timestamp: str
"""ISO timestamp when the request was made."""
# DevUI Output Content Types - for agent-generated media/data
# These extend ResponseOutputItem to support rich content outputs that OpenAI's API doesn't natively support
class ResponseOutputImage(BaseModel):
"""DevUI extension: Agent-generated image output.
This is a DevUI extension because:
- OpenAI Responses API only supports text output in ResponseOutputMessage.content
- ImageGenerationCall exists but is for tool calls (generating images), not returning existing images
- Agent Framework agents can return images via DataContent/UriContent that need proper display
This type allows images to be displayed inline in chat rather than hidden in trace logs.
"""
id: str
"""The unique ID of the image output."""
image_url: str
"""The URL or data URI of the image (e.g., data:image/png;base64,...)"""
type: Literal["output_image"] = "output_image"
"""The type of the output. Always `output_image`."""
alt_text: str | None = None
"""Optional alt text for accessibility."""
mime_type: str = "image/png"
"""The MIME type of the image (e.g., image/png, image/jpeg)."""
class ResponseOutputFile(BaseModel):
"""DevUI extension: Agent-generated file output.
This is a DevUI extension because:
- OpenAI Responses API only supports text output in ResponseOutputMessage.content
- Agent Framework agents can return files via DataContent/UriContent that need proper display
- Supports PDFs, audio files, and other media types
This type allows files to be displayed inline in chat with appropriate renderers.
"""
id: str
"""The unique ID of the file output."""
filename: str
"""The filename (used to determine rendering and download)."""
type: Literal["output_file"] = "output_file"
"""The type of the output. Always `output_file`."""
file_url: str | None = None
"""Optional URL to the file."""
file_data: str | None = None
"""Optional base64-encoded file data."""
mime_type: str = "application/octet-stream"
"""The MIME type of the file (e.g., application/pdf, audio/mp3)."""
class ResponseOutputData(BaseModel):
"""DevUI extension: Agent-generated generic data output.
This is a DevUI extension because:
- OpenAI Responses API only supports text output in ResponseOutputMessage.content
- Agent Framework agents can return arbitrary structured data that needs display
- Useful for debugging and displaying non-text content
This type allows generic data to be displayed inline in chat.
"""
id: str
"""The unique ID of the data output."""
data: str
"""The data payload (string representation)."""
type: Literal["output_data"] = "output_data"
"""The type of the output. Always `output_data`."""
mime_type: str
"""The MIME type of the data."""
description: str | None = None
"""Optional description of the data."""
# Agent Framework extension fields
class AgentFrameworkExtraBody(BaseModel):
"""Agent Framework specific routing fields for OpenAI requests."""
@@ -144,7 +292,7 @@ class AgentFrameworkRequest(BaseModel):
"""
# All OpenAI fields from ResponseCreateParams
model: str # Used as entity_id in DevUI!
model: str | None = None
input: str | list[Any] | dict[str, Any] # ResponseInputParam + dict for workflow structured input
stream: bool | None = False
@@ -156,20 +304,25 @@ class AgentFrameworkRequest(BaseModel):
metadata: dict[str, Any] | None = None
temperature: float | None = None
max_output_tokens: int | None = None
top_p: float | None = None
tools: list[dict[str, Any]] | None = None
# Reasoning parameters (for o-series models)
reasoning: dict[str, Any] | None = None # {"effort": "low" | "medium" | "high" | "minimal"}
# Optional extra_body for advanced use cases
extra_body: dict[str, Any] | None = None
model_config = ConfigDict(extra="allow")
def get_entity_id(self) -> str:
"""Get entity_id from model field.
def get_entity_id(self) -> str | None:
"""Get entity_id from metadata.entity_id.
In DevUI, model IS the entity_id (agent/workflow name).
Simple and clean!
In DevUI, entity_id is specified in metadata for routing.
"""
return self.model
if self.metadata:
return self.metadata.get("entity_id")
return None
def get_conversation_id(self) -> str | None:
"""Extract conversation_id from conversation parameter.
@@ -218,11 +371,40 @@ class OpenAIError(BaseModel):
return self.model_dump_json()
class MetaResponse(BaseModel):
"""Server metadata response for /meta endpoint.
Provides information about the DevUI server configuration and capabilities.
"""
ui_mode: Literal["developer", "user"] = "developer"
"""UI interface mode - 'developer' shows debug tools, 'user' shows simplified interface."""
version: str
"""DevUI version string."""
framework: str = "agent_framework"
"""Backend framework identifier."""
runtime: Literal["python", "dotnet"] = "python"
"""Backend runtime/language - 'python' or 'dotnet' for deployment guides and feature availability."""
capabilities: dict[str, bool] = {}
"""Server capabilities (e.g., tracing, openai_proxy)."""
auth_required: bool = False
"""Whether the server requires Bearer token authentication."""
# Export all custom types
__all__ = [
"AgentFrameworkRequest",
"MetaResponse",
"OpenAIError",
"ResponseFunctionResultComplete",
"ResponseOutputData",
"ResponseOutputFile",
"ResponseOutputImage",
"ResponseTraceEvent",
"ResponseTraceEventComplete",
"ResponseWorkflowEventComplete",