mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00

Files

T

Eduard van Valkenburg 57c901a245 Python: Fix hyperlight WasmSandbox cross-thread Drop and harden hosted-agent sample (#5603 )

* update hyperlight to beta and move samples, add hosted agent sample

* Python: Fix hyperlight WasmSandbox cross-thread Drop and harden sample

Root cause: when a worker-side closure raised, the exception's __traceback__
retained frame locals that included the partially constructed PyO3 sandbox.
Future.result() re-raised that exception on the caller thread, and when the
caller's exception was eventually GC'd the frame locals were released
off-thread, dec_ref'ing the unsendable sandbox from the wrong thread and
tripping the PyO3 panic
'_native_wasm::WasmSandbox is unsendable, but is being dropped on another thread'.

Fix:
* Add _SandboxWorker._run_on_worker which catches every exception on the
  worker, drops __traceback__ there, deletes the original exception, and
  re-raises a fresh instance on the caller thread. initialize and execute
  route through it; dispose keeps its bare-submit semantics.
* Add an opt-in diagnostic module _drop_diagnostic (no-op unless
  HYPERLIGHT_TRACE_DROPS=1) that installs a sys.unraisablehook and dumps
  owner-thread + per-thread stacks on any future cross-thread unsendable
  Drop. Useful for triaging similar PyO3 regressions.
* Tests: cross-thread invocation, traceback-leak isolation, _SandboxEntry
  attribute-shape check, and a stale-reference stress test driven through
  asyncio.to_thread.

Sample (samples/04-hosting/foundry-hosted-agents/responses/06_hyperlight_codeact):
* Dockerfile installs agent-framework-* from in-tree source with python/ as
  build context so unreleased fixes can be validated end-to-end.
* call_server.py pins the Responses API version.
* main.py enables include_detailed_errors=True so future tool failures
  surface the actual exception text instead of a bare 'Error: Function
  failed.' string.
* README.md documents the in-tree-package build and the Hyperlight
  hypervisor requirement (/dev/kvm on Linux, MSHV on Windows). Hosted
  environments without hypervisor passthrough surface 'No Hypervisor was
  found for Sandbox'; this is a hosting constraint, not a hyperlight bug.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: remove _drop_diagnostic from hyperlight package

The diagnostic module was useful while bisecting the cross-thread Drop bug,
but it is no longer needed now that _SandboxWorker._run_on_worker prevents
the panic at the source.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: address PR review feedback on hyperlight

- Use lazy agent_framework.hyperlight import in sample main.py.
- Env-driven endpoint (FOUNDRY_AGENT_ENDPOINT) in call_server.py; remove personal URLs.
- Align agent.yaml model deployment with manifest (gpt-4.1-mini).
- Tighten Dockerfile requirements guard; drop dangling deploy.ps1 reference.
- Preserve exception args when sanitizing tracebacks in _run_on_worker.
- Add public _SandboxWorker.is_alive(); update test to avoid private attr.
- Add namespace coverage tests for agent_framework.hyperlight lazy loader.
- Add prominent note: Foundry hosted-agent runtime does not yet support
  Hyperlight (no hypervisor exposed); container works locally with /dev/kvm.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: bump hyperlight-sandbox dependencies to 0.4.x

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Python: renumber hyperlight codeact sample to 08

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Coerce worker exception args to strings for cross-thread safety

Stringify exc.args on the worker thread before propagating, so any
PyO3 unsendable object captured in args (e.g. via a caller-supplied
callback or underlying SDK) cannot be Dropped on the calling thread.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* moved sample

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

57c901a245 · 2026-05-05 10:06:16 +00:00

History

azure_ai_search

Python: Add Hyperlight CodeAct package and docs (#5185 )

2026-04-17 00:49:44 +00:00

code_act

Python: Fix hyperlight WasmSandbox cross-thread Drop and harden hosted-agent sample (#5603 )

2026-05-05 10:06:16 +00:00

mem0

Python: Fix broken samples and add missing READMEs (#5038 )

2026-04-01 21:35:16 +00:00

neo4j

Python: Adds sample documentation for two separate Neo4j context providers for retrieval and memory (#4010 )

2026-04-07 09:57:35 +00:00

neo4j_memory

Python: Adds sample documentation for two separate Neo4j context providers for retrieval and memory (#4010 )

2026-04-07 09:57:35 +00:00

redis

Python: Fix broken samples and add missing READMEs (#5038 )

2026-04-01 21:35:16 +00:00

azure_ai_foundry_memory.py

Python: [BREAKING] Standardize model selection on model (#4999 )

2026-04-01 19:00:18 +00:00

foundry_toolbox_context_provider.py

Python: Add support for Foundry Toolboxes (#5346 )

2026-04-20 23:56:01 +00:00

README.md

Python: Add support for Foundry Toolboxes (#5346 )

2026-04-20 23:56:01 +00:00

simple_context_provider.py

Python: Fix broken samples and add missing READMEs (#5038 )

2026-04-01 21:35:16 +00:00

README.md

Context Provider Samples

These samples demonstrate how to use context providers to enrich agent conversations with external knowledge — from custom logic to Azure AI Search (RAG) and memory services.

Samples

File / Folder	Description
`simple_context_provider.py`	Implement a custom context provider by extending `ContextProvider` to extract and inject structured user information across turns.
`foundry_toolbox_context_provider.py`	Compose a Microsoft Foundry toolbox with a `ContextProvider` that caches the toolbox once and picks a subset of its tools per-turn via `select_toolbox_tools`, driven by keywords in the latest user message.
`azure_ai_foundry_memory.py`	Use `FoundryMemoryProvider` to add semantic memory — automatically retrieves, searches, and stores memories via Azure AI Foundry.
`azure_ai_search/`	Retrieval Augmented Generation (RAG) with Azure AI Search in semantic and agentic modes. See its own README.
`mem0/`	Memory-powered context using the Mem0 integration (open-source and managed). See its own README.
`redis/`	Redis-backed context providers for conversation memory and sessions. See its own README.

Prerequisites

For simple_context_provider.py:

FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
FOUNDRY_MODEL: Model deployment name
Azure CLI authentication (az login)

For foundry_toolbox_context_provider.py:

FOUNDRY_PROJECT_ENDPOINT: Your Microsoft Foundry project endpoint
FOUNDRY_MODEL: Model deployment name
A toolbox already configured in that project; set TOOLBOX_NAME / TOOLBOX_VERSION at the top of the sample
Azure CLI authentication (az login)

For azure_ai_foundry_memory.py:

FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
FOUNDRY_MODEL: Chat/responses model deployment name
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: Embedding model deployment name (e.g., text-embedding-ada-002)
Azure CLI authentication (az login)

See each subfolder's README for provider-specific prerequisites.