agent-framework

Python: Fix Python OTel usage detail attributes (#6493 )

* fix python otel usage detail attributes

Map cached/read/reasoning usage detail fields to standard OTel GenAI attributes while preserving provider-specific legacy keys.

Add focused coverage for direct response spans, aggregated agent spans, and provider usage parsing.

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

* address usage detail review feedback

Omit missing OpenAI Responses usage detail counts while preserving zero-valued counts.

Record zero-valued token usage in OTel histograms and add regression coverage.

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

---------

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

Eduard van Valkenburg · 2026-06-15 07:10:14 +00:00

d7e8d2206d

Python: [BREAKING] Align FileAccess tools with .NET — directory discovery and recursive search (#6476 )

* Align FileAccess tools with .Net; add directory discovery and recursive search

* Fix choices field description: spacing, line length, grammar

Addresses PR review: separate concatenated string literals with proper
spacing/newlines, wrap lines under the 120-char Ruff limit, and fix
"doesn't" -> "don't".

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

* Address PR comments

---------

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

westey · 2026-06-15 06:55:21 +00:00

d7027fc1f9

Python: Add AgentLoopMiddleware for re-running agents in a loop (#6174 )

* Python: Add AgentLoopMiddleware for re-running agents in a loop

Add `AgentLoopMiddleware`, an `AgentMiddleware` that re-runs the wrapped
agent in a loop. A single configurable class covers three common patterns,
each with a convenience classmethod factory:

- Ralph loop (`.ralph(...)`): no exit criteria, with feedback tracking
  (`record_feedback`/`progress`), progress injection (`inject_progress`),
  optional fresh context per iteration (`fresh_context`), and an early-stop
  completion signal (`is_complete`).
- Predicate (`.with_predicate(...)`): loop while a `should_continue` callable
  returns True (e.g. paired with `todos_remaining`/`background_tasks_running`).
- Judge (`.with_judge(...)`): a second chat client decides whether the original
  request was answered, using a `JudgeVerdict` structured-output response.

The loop also auto-resolves pending function-approval / user-input requests via
an `on_approval_request` callable (bounded by `max_approval_rounds`), and the
next iteration's input is controlled by `next_message`. Supports both streaming
and non-streaming runs.

Exports `AgentLoopMiddleware`, `JudgeVerdict`, `todos_remaining`, and
`background_tasks_running`. Adds tests, a sample, and docs.

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

* Python: Refine AgentLoopMiddleware API and sample

- with_judge: add criteria list with {{criteria}} templating into judge
  instructions plus an agent-side instruction; add fresh_context, additional
  judge feedback relay; default judge max_iterations.
- should_continue is now required and positional; supports (bool, str|None)
  feedback tuples surfaced to next_message/record_feedback via feedback kwarg.
- Judge forwards full multi-modal request and response messages.
- Default max_iterations=10 (explicit None = unbounded); removed is_complete and
  Ralph terminology; ShouldContinueResult is a real TypeAlias.
- Sample: stream all loops, print iteration counts via injected user-block
  boundaries (robust to function calling), <role>: content formatting, per-method
  expected output, and a looping todo sample.

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

* Python: Fix CI checks for AgentLoopMiddleware

- Resolve pyright errors in _loop.py: drop the always-true final_result None
  check (the while loop always assigns it) and cast finish_reason to the
  AgentResponse constructor's expected type.
- Apply pyupgrade --py310-plus: import TypeAlias from typing.

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

* Python: Resolve mypy/pyright disagreement on finish_reason

pyright infers AgentResponse.finish_reason as including str and rejects the
direct assignment, while mypy considers a cast redundant. Drop the cast and
suppress only pyright with a targeted reportArgumentType ignore, satisfying
both type checkers.

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

* Python: Add todo+judge AgentLoopMiddleware sample

Add a second AgentLoopMiddleware sample that composes two criteria in one
should_continue predicate: a TodoProvider check (evaluated first) and a
report-style judge chat client (evaluated once todos are complete) that grades
the assembled report against shared requirements. Register it in the middleware
samples README.

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

* Python: Compose todo+judge loops as two middleware

Rework the todo+judge sample to compose two AgentLoopMiddleware on the agent
itself (middleware=[judge_loop, todo_loop]) instead of a single hand-written
predicate. The inner todos_remaining loop drafts the report todo-by-todo and the
outer with_judge loop re-runs it until an editor chat client judges the report
publication-ready, reusing the built-in helpers.

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

* Reset session for fresh_context loops via snapshot/restore

AgentLoopMiddleware.fresh_context previously only reset context.messages,
so with an attached session each iteration still reloaded the local
transcript or re-threaded the service-side conversation id and the model
saw the accumulated history. Snapshot the session once before the loop
(via to_dict) and restore it (from_dict + field copy) between iterations,
so every pass starts from the pre-loop baseline. The final iteration's
pass is persisted (no restore after the terminating iteration), so a
subsequent agent.run continues from there.

Removed the obsolete warning, updated docstrings and core AGENTS.md, and
added tests: a snapshot/restore round-trip, a session-reset
streaming x fresh_context x inject_progress x store matrix across multiple
runs and loop iterations, and response_format parsing across the loop.

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

* Updated samples and docstrings

---------

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

Eduard van Valkenburg · 2026-06-12 14:35:54 +00:00

1acd242550

Python: Integrate shell tool into harness agent (#6451 )

* Integrate shell tool into AgentHarness

* Validate shell_executor exposes as_function() with a clear TypeError

Addresses PR review feedback: a public factory should fail fast with an
actionable error rather than a cryptic AttributeError when an incompatible
shell_executor is supplied. Validation happens upfront, regardless of whether
the client supports shell tools.

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

* Type shell harness params via TYPE_CHECKING import

Addresses PR review feedback: type shell_executor and
shell_environment_provider_options instead of Any, using a TYPE_CHECKING
import from agent_framework_tools.shell. The import never executes at
runtime, so there is no circular dependency, and the lazy runtime import of
ShellEnvironmentProvider is retained. Since ShellExecutor is a protocol
without as_function(), the validated getattr result is invoked directly.

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

---------

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

westey · 2026-06-11 20:51:59 +00:00

3d5421edc1

Python: Add tool approval middleware (#6414 )

* Add Python tool approval middleware

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

* Fix tool approval restored state handling

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

* Gate hidden approvals on explicit approval responses

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

* Handle string inputs in approval replay scan

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

* Cover argument-scoped approval rules

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

* Refine tool approval state and budgets

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

* Fix tool approval PR CI failures

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

* Revert DevUI Aspire README link change

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

---------

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

Eduard van Valkenburg · 2026-06-11 17:35:44 +00:00

df29af611c

Python: [Generated by SRE Agent] Fix MCP allowed_tools empty list handling (#6296 )

* Fix MCP allowed_tools empty list handling

When allowed_tools is set to an empty list [], the falsy check
'if not self.allowed_tools' incorrectly treats it as unconfigured
(same as None), causing all tools to be exposed. Change to an
explicit 'is None' check so that an empty list correctly results
in no tools being allowed.

Co-authored-by: Azure SRE Agent <noreply@microsoft.com>

* Clarify allowed_tools docstring: None vs [] semantics

Per Eduard's review on PR #6296: explicitly document that None exposes all tools and [] exposes none, across all four MCPTool / MCPStdioTool / MCPStreamableHTTPTool / MCPWebsocketTool docstrings.

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

* allowed_tools docstring: recommend load_tools=False for full disable

Per Eduard's follow-up on PR #6296: `load_tools=False` is the cleaner idiom when you don't want to expose any tools. Reframe `allowed_tools=[]` in the docstring as a runtime guard / inspection-only path and cross-reference `load_tools`.

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

---------

Co-authored-by: Azure SRE Agent <noreply@microsoft.com>
Co-authored-by: Giles Odigwe <79032838+giles17@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

chetantoshniwal · 2026-06-11 06:46:46 +00:00

4149f24791

Python: HarnessAgent: Disable compaction when max tokens not provided (#6410 )

* HarnessAgent: Disable compaction when max tokens not provided

* Fix regression.

* Address PR comments

* Require max_output_tokens to be positive

Reject max_output_tokens=0 (must be positive), mirroring
max_context_window_tokens. Addresses PR review feedback.

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

---------

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

westey · 2026-06-10 13:57:23 +00:00

8dde9ef627

Python: Parse MCP CallToolResult.structuredContent field to prevent tool results returning None (#6421 )

* Parse structuredContent from MCP CallToolResult (#3313)

The _parse_tool_result_from_mcp method only iterated over the content
field from CallToolResult, ignoring the structuredContent field entirely.
MCP servers that return JSON data via structuredContent (e.g., Power BI
MCP) appeared to return None.

Add handling for structuredContent: when present, serialize it as JSON
text and append it to the result list. This preserves the data for the
LLM while maintaining backward compatibility with existing behavior.

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

* Python: Parse MCP CallToolResult.structuredContent field to prevent tool results returning None

Fixes #3313

* Address review feedback: add default=str to json.dumps and remove .checkpoints/

- Add default=str to json.dumps for structuredContent serialization so
  non-JSON-serializable values (e.g. bytes) degrade gracefully instead
  of raising TypeError
- Remove all .checkpoints/ runtime artifacts from the repository
- Add **/.checkpoints/ to .gitignore to prevent future accidental commits
- Add test for non-serializable structuredContent values

Fixes #3313

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

* Address review feedback for #3313: Python: MCP CallToolResult.structuredContent field is not parsed, causing tool results to return None

---------

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

Giles Odigwe · 2026-06-10 12:51:09 +00:00

93cbf6b3f0

Python: [BREAKING] Add sampling guardrails to MCP tools (#6413 )

* Add sampling guardrails to MCP tools

Add approval, token, and request-count controls to the MCP sampling
callback used when an MCPTool is configured with a chat client.

- Add `sampling_approval_callback`, `sampling_max_tokens`, and
  `sampling_max_requests` parameters to `MCPTool` and its
  `MCPStdioTool`, `MCPStreamableHTTPTool`, and `MCPWebsocketTool`
  subclasses, positioned directly after `client`.
- Gate each server-initiated `sampling/createMessage` request behind the
  approval callback, which denies by default when no callback is provided.
- Clamp the requested `maxTokens` to `sampling_max_tokens` and enforce a
  per-session request count via `sampling_max_requests`.
- Log incoming sampling requests at WARNING level (counts only).
- Export `SamplingApprovalCallback` from the public API.
- Add tests, a sample, and documentation updates.

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

* Make sampling denial message context-aware

Distinguish the deny-by-default case (no approval callback configured)
from an explicit denial by a configured `sampling_approval_callback`, so
the returned ErrorData message is accurate for callback-driven denials
and exceptions.

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

---------

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

Eduard van Valkenburg · 2026-06-10 10:17:36 +00:00

9a56bc9f16

Python: Filter MCP tool kwargs to declared params via allowlist (#6399 )

* Filter MCP tool kwargs to declared params via allowlist

Previously MCPTool combined framework runtime kwargs (from
FunctionInvocationContext.kwargs) with the LLM-supplied arguments and
stripped only a hardcoded denylist of known framework keys before
forwarding to the MCP server. Any new framework-injected kwarg leaked to
the server unless the denylist was updated.

Switch to an allowlist built from each tool's declared parameters
(inputSchema.properties). Only declared params are forwarded; everything
else is stripped. Add an `additional_tool_argument_names` constructor
argument so users can opt extra names back in, globally (Sequence[str])
and/or per remote tool name (Mapping with reserved "*" global key). The
existing denylist is kept as a safety net for framework-named params a
server declares in its schema; explicitly opted-in extras always win. The
reserved _meta handling is unchanged.

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

* Address MCP allowlist review comments and fix reload arg loss

- Fix pyright reportUnknownArgumentType in _load_tools (cast schema properties).
- Register declared param names before the existing-tool skip guard so that
  tool-list reloads preserve the allowlist for already-loaded tools (previously
  unchanged tools silently dropped all declared args after a background reload).
- Handle bare-string values in an additional_tool_argument_names mapping instead
  of iterating their characters.
- Clarify the framework denylist comment: explicit extras override the denylist.
- Make the extras-override-denylist test unambiguous (opt in a denylisted name).

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

---------

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

Eduard van Valkenburg · 2026-06-09 07:37:11 +00:00

cfb033e5d4

Python: Fix per-service-call history persistence with server-storing clients (#6310 )

* Fix per-service-call history persistence with server-storing clients

When an Agent set require_per_service_call_history_persistence=True together
with a HistoryProvider, and the chat client stored history server-side by
default (e.g. OpenAIChatClient, STORES_BY_DEFAULT=True), the external history
provider was silently never persisted.

Unify persistence on the per-service-call middleware: when the flag is set and
a HistoryProvider exists, the middleware is always installed and owns
persistence. service_stores_history now only selects middleware behavior:
- service does not store: load providers and drive the function loop with a
  local sentinel conversation id, or
- service stores: skip loading (the service owns history) and persist each
  service call while the real conversation id flows through.

Also rationalize chat-options handling in _prepare_run_context:
- _merge_options now skips None overrides and strips remaining None values, so
  an unset `store` is never forwarded and the service decides its own default.
- Resolve `store` and `conversation_id` once from a single combined view
  (effective_options) instead of probing both default and runtime dicts; the
  auto-injection and per-service-call resolution now agree on conversation_id.

Fixes #5798

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

* Correct as_agent() docstring: persistence is per service call, not once per run

Address PR review: when the client stores history server-side, the
per-service-call middleware still persists after each model call; only
provider loading is skipped. The previous "persist once per run()" wording
contradicted the implementation.

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

* Address PR review: docs, missing-conversation-id warning, and tests

- Clarify that require_per_service_call_history_persistence is a no-op when no
  HistoryProvider is present (docstrings in _agents.py and _clients.py).
- Warn on every service call when the client stores history server-side but
  returns no conversation_id, so the (uncommon) loss of cross-turn resumability
  cannot fail silently.
- Add tests: storing client + existing conversation_id does not raise and the id
  propagates; two runs on the same session keep persisting with a stable
  service_session_id and no provider loading; storing-without-conversation-id
  warns per call.

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

---------

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

Eduard van Valkenburg · 2026-06-09 05:47:57 +00:00

7e0767a0a0

Python: feat(python): Add MCP client OTel spans per GenAI semantic conventions (#6349 )

* feat(python): Add MCP client OTel spans per GenAI semantic conventions

Implement MCP client spans per the OTel GenAI Semantic Conventions for MCP
(https://opentelemetry.io/docs/specs/semconv/gen-ai/mcp/#client).

Operations instrumented:
- initialize: CLIENT span capturing MCP session setup
- tools/list: CLIENT span for tool listing (per-page)
- prompts/list: CLIENT span for prompt listing (per-page)
- tools/call: CLIENT span (nested under execute_tool when called via FunctionTool)
- prompts/get: CLIENT span

Span attributes follow the MCP semantic conventions:
- Required: mcp.method.name
- Conditional: error.type, gen_ai.tool.name, gen_ai.prompt.name
- Recommended: gen_ai.operation.name, mcp.protocol.version, mcp.session.id,
  network.transport, server.address, server.port

Transport-specific attributes per subclass:
- MCPStdioTool: network.transport=pipe
- MCPStreamableHTTPTool: network.transport=tcp, network.protocol.name=http
- MCPWebsocketTool: network.transport=tcp, network.protocol.name=websocket

All span creation gated behind OBSERVABILITY_SETTINGS.ENABLED.

Closes #3624
Closes #4697

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

* refactor: simplify MCP spans — remove enrichment logic and protocol version caching

- Always create nested CLIENT spans for tools/call instead of enriching
  the parent execute_tool span
- Remove _ACTIVE_TOOL_EXECUTION_SPAN contextvar (no longer needed)
- Remove enrich_span_with_mcp_attributes() helper
- Remove _otel_error_type preservation in FunctionTool.invoke()
- Remove _mcp_protocol_version instance variable; protocol version is
  only set on the initialize span where it is available

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

* Refine copilot solution

* fix: enable automatic exception recording on MCP spans

Remove record_exception=False and set_status_on_exception=False from
create_mcp_client_span. Let OTel handle exception recording and status
setting automatically. The manual set_mcp_span_error calls for tools/call
still correctly set error.type (which OTel's automatic handling doesn't
touch), so tool_error is preserved.

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

* Reduce number of lines

* Add comment to sample

* test: address PR review comments on MCP observability tests

- Fix initialize test to call mocked session.initialize() and read
  protocolVersion from the result instead of hardcoding it
- Add tools/call McpError error-path test
- Add prompts/get McpError error-path test

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

* Fix export error

---------

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

Tao Chen · 2026-06-05 19:23:01 +00:00

dcc218dbac

Python: Refactor workflow as agent pending request handling (#6259 )

* WIP: Refactor Workflow as agent pending request handling

* WIP: debugging empty message bug

* Working: Workflow as agent with function approval

* Address Copilot comments

* Fix mypy

* Address comments and fix pipeline

* Request info non function approval now becomes function call

* Revert uv.lock

* Fix mypy

* Bump min version of azure-ai-project

* Remove RequestInfoFunctionArgs

* fix tests

* Fix failing tests

* Fix sample

Tao Chen · 2026-06-05 17:23:19 +00:00

9cafd7e58b

Python: MCP long-running task support in Python (#6319 )

* MCP long-running task support in Python

* Fix pyupgrade and AGENTS.md reconnect description

- pyupgrade: drop forward-reference string annotations in _mcp.py (Python 3.10+ resolves them natively now that MCPTaskOptions is defined before use).

- AGENTS.md: align reconnect description with current behavior. Phase 1 (initial tools/call) does NOT retry on connection loss; raises 'connection lost; task state unknown' instead, so a server that accepted the request but lost the response cannot start the operation twice. Phase 2 (tasks/get / tasks/result) still reconnects once against the same task_id.

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

* Fix bandit nosec marker for CI pipeline

* Address PR feedbacks

* Clarifiied comments and addressed more PR feedbacks.

---------

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

Peter Ibekwe · 2026-06-05 00:04:55 +00:00

bf4ad48cf2

Python: Fix compaction message-id collisions and tool-loop summary persistence (#6299 )

* Fix compaction message-id collisions and tool-loop summary persistence

Fixes two bugs in the compaction strategies:

- #5237: incremental group annotation assigned message ids by position
  within the re-annotated slice, so moving the re-annotation start back to
  a previous group start restarted ids at 0 and produced collisions
  (e.g. a user message reusing an assistant message's id), merging groups
  and causing tool-result compaction to wrongly exclude messages.
  group_messages/_ensure_message_ids now take an id_offset and guard
  against existing-id collisions; annotate_message_groups threads the
  slice start index through as the offset.

- #4991: the function-invocation loop copied the message list each
  iteration, so summaries inserted by compaction landed in a throwaway
  copy and were lost across tool-loop iterations (only the persistent
  excluded flags survived). _prepare_messages_for_model_call now compacts
  the list in place when messages is a list, so inserted summaries persist.

Adds regression tests (incremental id uniqueness, existing-id collision
avoidance, idempotency, and tool-loop summary persistence including
streaming and conversation-id modes).

Also adds a summarization.py sample demonstrating SummarizationStrategy
directly with a real client, and reworks advanced.py with tool-call
groups and a real summarizer.

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

* Guard incremental message-id assignment against prefix-id collisions

Addresses PR review on #5237: _ensure_message_ids only guarded against
collisions within the re-annotated slice. A preexisting (e.g. user-supplied)
id in the preserved prefix could still be reassigned in the suffix when the
id was numerically out of position, merging groups across the re-annotation
boundary again.

group_messages/_ensure_message_ids now accept reserved_ids, and
annotate_message_groups passes the preserved prefix's ids so auto-assigned
suffix ids never collide across the full list. Adds a regression test
reproducing the out-of-position prefix-id collision.

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

---------

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

Eduard van Valkenburg · 2026-06-04 08:37:59 +00:00

f970a699d8

Python: run sync tools off the event loop (#5773 )

* fix: run sync tools off event loop

* chore: silence harness tool marker type check

Yufeng He · 2026-06-04 04:42:08 +00:00

f29bae8fbc

Python: Add MCP-based skills discovery (McpSkillsSource) (#6169 )

* Add MCP-based skills discovery (McpSkill, McpSkillsSource, McpSkillResource)

Implement Agent Skills discovery over MCP following the SEP-2640 convention:
- McpSkillsSource: reads skill://index.json to discover skills served by an MCP server
- McpSkill: lazily fetches SKILL.md content via resources/read on demand
- McpSkillResource: wraps MCP resource results (text and binary)
- Path traversal protection in get_resource for defense in depth
- Samples for Foundry Toolbox and standalone MCP skills server
- Comprehensive unit tests (514 lines)

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

* Address PR review comments: rename to MCP* convention, fix error handling and samples

- Rename McpSkill/McpSkillResource/McpSkillsSource to MCPSkill/MCPSkillResource/MCPSkillsSource
- Add data-URI prefix stripping for blob resource decoding
- Let non-McpError exceptions propagate from get_resource()
- Fix contradictory test comment
- Use interactive input() in mcp_based_skill sample
- Remove misleading sample output block

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

* Restore debug logging for McpError in get_resource()

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

* Use AzureCliCredential in Foundry toolbox skills sample for consistency

Replace DefaultAzureCredential with AzureCliCredential to match the
credential convention used in all other samples.

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

* Use MCPStreamableHTTPTool in MCP skills sample

Replace raw mcp library imports (ClientSession, streamable_http_client)
with the framework's MCPStreamableHTTPTool to keep MCP server connections
consistent regardless of whether skills are enabled.

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

* Branch on McpError.error.code so only not-found errors return empty

Previously _try_read_index() and get_resource() swallowed every McpError
as 'no skills available', making auth failures, server crashes, and
connection drops indistinguishable from a server that simply has no
skills.

Now only two codes are treated as not-found:
- -32002 (MCP-spec Resource not found)
- -32601 (METHOD_NOT_FOUND — server lacks resources/read)

All other McpError codes and non-McpError exceptions propagate with a
warning log, surfacing real failures visibly.

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

* Add tests for non-McpError and non-not-found error propagation in MCP skills

Cover the re-raise branch in MCPSkill.get_resource for plain
ConnectionError/TimeoutError, the generic McpError (code 0) propagation
on get_resource, and TimeoutError propagation in _try_read_index.

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

* Revert "Use MCPStreamableHTTPTool in MCP skills sample"

This reverts commit f31ed0ded9.

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

* Introduce MCP_SKILLS experimental feature for MCP skill classes

Add a separate MCP_SKILLS feature ID to ExperimentalFeature enum and
use it for MCPSkillResource, MCPSkill, and MCPSkillsSource, since their
promotion timeline is partly outside of our control.

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

---------

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

semenshi-m · 2026-06-03 18:09:50 +00:00

c6951c21f6

Python: progressive tool exposure via FunctionInvocationContext (#6233 )

* Python: progressive tool exposure via FunctionInvocationContext

Add first-class progressive tool exposure to the Python core function-calling
loop. Tools can now add or remove real FunctionTool schemas at runtime via the
injected FunctionInvocationContext, taking effect on the next iteration of the
loop.

- FunctionInvocationContext gains a live `tools` list plus experimental
  `add_tools()` / `remove_tools()` helpers (feature: PROGRESSIVE_TOOLS).
- The function-calling loop establishes a run-local, normalized tools list and
  threads it into the context at both invocation paths so mutations propagate.
- Add a sample (dynamic_tool_exposure.py) and a tools samples README, including
  a note that CodeAct providers (Monty/Hyperlight) use their own provider-level
  tool management instead.

Supersedes #3877.

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

* Validate non-negative input in dynamic_tool_exposure sample tools

Address review feedback: factorial and fibonacci now return an error
message for negative n instead of producing incorrect results.

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

* Make add_tools atomic and surface swallowed function errors

Address review feedback on progressive tool exposure:

- add_tools now validates the full batch against a throwaway copy before
  committing, so a duplicate-name clash partway through a sequence leaves
  the live tool list unchanged (all-or-nothing).
- _auto_invoke_function now logs a warning (with traceback) when a tool
  raises, so contract errors such as a duplicate-name ValueError from
  add_tools are debuggable without enabling include_detailed_errors.

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

* Avoid retaining tracebacks when logging swallowed function errors

Logging with exc_info=exc fed the exception traceback to the logging
machinery, whose frame references created reference cycles collected
lazily by the cyclic GC. On Windows that could drop a hyperlight
WasmSandbox on a non-owning thread ("unsendable, dropped on another
thread"), crashing the xdist worker. Log a pre-formatted message with
the exception repr instead, so no traceback object is retained.

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

* added missing decorator

---------

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

Eduard van Valkenburg · 2026-06-03 09:01:07 +00:00

49a6e433a3

Python: Fix OTLP HTTP base-endpoint losing /v1/{signal} auto-append (#5913 )

* Python: Fix OTLP HTTP base-endpoint losing /v1/{signal} auto-append

Per the OTel spec, OTEL_EXPORTER_OTLP_ENDPOINT is a *base* URL for HTTP —
the SDK auto-appends /v1/traces, /v1/metrics, /v1/logs when it reads the
env var directly. Signal-specific endpoint env vars are *full* URLs used
verbatim.

_get_exporters_from_env read the base endpoint and forwarded it as the
constructor ``endpoint=`` argument, which the SDK always treats as a full
signal URL. As a result, with OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318
and HTTP protocol, the exporter sent to http://localhost:4318 instead of
http://localhost:4318/v1/traces (and likewise for metrics/logs).

Replicate the spec's auto-append here when falling back to the base
endpoint under HTTP. gRPC behavior is unchanged.

* Python: Fix mypy type errors in OTLP endpoint assignment

Pre-declare traces_endpoint, metrics_endpoint, logs_endpoint as
str | None before the if/else block. Mypy inferred str from the
if-branch f-string assignments and then rejected the str | None
expressions in the else-branch as incompatible.

Dineshsuriya D · 2026-06-02 09:59:50 +00:00

a5f355e04a

Python: feat(evals): Foundry Adaptive Evals integration (rubric-generation) (#6101 )

* Python: feat(evals): RubricScore type + EvalScoreResult.dimensions

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

* Python: feat(foundry-evals): RubricDimension + GeneratedEvaluatorRef + accept in evaluators=

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

* Python: feat(evals): parse rubric_scores from output items + assertion helpers

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

* Python: feat(evals): BaseAgent.as_eval_source / Workflow.as_eval_source

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

* Python: feat(foundry-evals): EvalGenerationSource + generate_rubric helper

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

* Python: feat(foundry-evals): YAML config loader + sample

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

* Python: fix(evals): address PR review feedback

Addresses 4 Copilot review comments on PR #6101:

1. assert_dimension_score_at_least: drop the (not evaluator or found_any) guard so require_applicable=True correctly raises when the named evaluator produces no entries for the dimension. Adds TestRubricAssertions covering the regression.

2. GeneratedEvaluatorRef docstring: reword to describe actual behaviour (pinning recommended, not required) so it matches the dataclass default and FoundryEvals warning path.

3. _poll_generation_job: switch from asyncio.get_event_loop() to get_running_loop() and bound the per-iteration sleep by remaining time, matching _poll_eval_run.

4. generate_rubric: type category as Literal['quality','safety'] and validate at the entry point with a ValueError; drop the silent 'invalid -> quality' rewrite in _generation_job_to_ref. Adds a regression test.

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

* Python: feat(foundry-evals): hosted-agent-aware rubric generation

* Auto-detect hosted Foundry agents in agent_as_eval_source: when the
  agent's chat_client exposes a string agent_name (the convention used
  by RawFoundryAgentChatClient for PromptAgents/HostedAgents), emit a
  type='agent' EvalGenerationSource so the service fetches instructions
  and tools from the agent registry instead of relying on the local
  wrapper (which holds neither for hosted agents).
* Add hosted_agent_version kwarg and a new agent_version field on
  EvalGenerationSource so PromptAgent runs can pin to a specific hosted
  version for reproducible rubric generation.
* Add force_prompt_source escape hatch to bypass auto-detection and
  always emit a rendered prompt dossier - useful when the local wrapper
  carries overrides the service-side agent doesnt see.
* Fix _to_sdk_source for dataset sources: SDK ctor takes name=/version=,
  not dataset_name=/dataset_version=. The mismatch would raise TypeError
  against the real azure-ai-projects 2.3.0a* SDK; only unmocked
  integration paths were affected.

Tests cover: auto-detection happy path, versionless hosted agent,
explicit hosted_agent_version forwarding, force_prompt_source override,
non-string chat_client attrs (MagicMock test doubles) not mis-detected,
agent_version forwarded through _to_sdk_source, and the corrected
dataset SDK kwarg names.

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

* fix(foundry-evals): accept canonical dimension_scores key per docs

The published Foundry rubric-evaluator output (Microsoft Learn 'Rubric evaluators' reference) places per-dimension breakdowns under properties.dimension_scores, not properties.rubric_scores. The parser now tries dimension_scores first and falls back to rubric_scores for preview-build compatibility, and tolerates non-list payloads (e.g. MagicMock auto-attrs) by trying the next candidate when parsing yields zero entries.

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

* feat(foundry-evals): add manual create_rubric_evaluator

Adds FoundryEvals.create_rubric_evaluator as the agent-framework surface over project_client.beta.evaluators.create_version. This is the manual counterpart to generate_rubric: callers supply RubricDimension instances (authored locally, ported from another framework, or hand-tuned) and we POST a RubricBasedEvaluatorDefinition. The service auto-attaches the non-editable residual dimension (general_quality for quality, general_policy_compliance for safety).

Per the Microsoft Learn 'Rubric evaluators' reference, the auto-generation path (create_generation_job) is primarily a portal/UI feature; external SDK clients with rich local agent context are better served by manual create_version. This keeps generate_rubric for users who want to round-trip through a Foundry-registered agent.

Validation up front: weight must be in [1,10], ids unique, descriptions non-empty, pass_threshold in [0,1]. The returned GeneratedEvaluatorRef is identical in shape to one obtained from generate_rubric, so downstream evaluators= lists work unchanged.

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

* samples(foundry-evals): manual rubric sample + namespace re-exports

Adds evaluate_with_manual_rubric_sample.py demonstrating the end-to-end dev scenario for FoundryEvals.create_rubric_evaluator: hand-author a list of RubricDimension, register via create_rubric_evaluator, then use the pinned GeneratedEvaluatorRef alongside built-in evaluators in an agent regression run.

Also re-exports RubricDimension, GeneratedEvaluatorRef, build_sources, and load_evals_config from agent_framework.foundry (both the lazy runtime shim and the type stub) so the rubric samples can import everything from a single namespace; the auto-generate sample was previously broken because the shim was missing build_sources / load_evals_config.

Updates the foundry-evals README with a chooser entry for the two rubric paths.

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

* feat(foundry-evals): remove rubric creation flows; keep consumption only

Reframes agent-framework as a pure consumer of Foundry rubric evaluators: scoring against rubrics that already exist (authored in the Foundry portal or via the dedicated SDK / REST surface) instead of creating them from the SDK.

Removed creation surface area:

- FoundryEvals.generate_rubric (auto-generate path) and create_rubric_evaluator (manual path), plus all _GenerationSdkTypes / _ManualRubricSdkTypes / _to_sdk_dimensions / _coalesce_generation_sources / _to_sdk_source / _poll_generation_job / _generation_job_to_ref / _evaluator_version_to_ref / _get_beta_evaluators / _import_*_sdk_types helpers.

- EvalGenerationSource (the input source discriminator), RubricDimension (the input dimension type), agent_as_eval_source / workflow_as_eval_source / _detect_hosted_foundry_agent helpers, and the YAML-config loader (_evals_config.py with RubricGenerationSpec / RubricSourceSpec / parse_evals_config / load_evals_config / build_sources).

- BaseAgent.as_eval_source / Workflow.as_eval_source plus the _render_agent_dossier / _render_workflow_dossier helpers in core. These existed only to feed the now-removed generation pipeline.

- Samples evaluate_with_generated_rubric_sample.py, evaluate_with_manual_rubric_sample.py, and evaluators.yaml. Replaced with a short README section showing how to reference an existing rubric evaluator via GeneratedEvaluatorRef.

Kept (consumption surface):

- GeneratedEvaluatorRef, slimmed to (name, version, display_name). Still accepted alongside built-in evaluator strings in FoundryEvals(evaluators=[...]). Versionless refs still warn.

- RubricScore on EvalScoreResult.dimensions plus EvalResults.assert_dimension_score_at_least for per-dimension CI gates.

- _parse_dimension_entries / _extract_rubric_scores output parsing (both canonical dimension_scores and the legacy rubric_scores key).

Tests: 160/160 foundry unit tests and 71/71 core local-eval tests pass; pyright is clean across changed files. The pre-existing tests/core/test_telemetry.py::test_detect_hosted_fallback_import_error failure is unrelated and reproduces on the prior commit.

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

* samples(foundry-evals): add evaluate_with_rubric_sample

Adds a runnable end-to-end sample showing how to consume a pre-existing rubric evaluator created in Foundry: reference it with GeneratedEvaluatorRef(name, version), mix it with built-in evaluators in FoundryEvals, and gate CI with assert_dimension_score_at_least on a specific dimension.

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

* fix(foundry-evals): satisfy mypy on _fetch_output_items

mypy infers OutputItemListResponse.sample as dict[str, object] | None while pyright correctly infers the typed Sample model. Cast to Any so both type checkers accept the attribute access pattern, rename the local to avoid shadowing the inner-loop sample binding, and drop the now-stale pyright suppressions.

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

* docs(foundry-evals): drop unpublished rubric-evaluators learn.microsoft.com link

The Adaptive Evals authoring docs are not yet published on Microsoft Learn, so the link 404s. Keep the descriptive text without the broken hyperlink; we can re-add it once the docs ship.

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

* test(foundry-evals): hoist repeated local imports to module top

Per code review feedback (eavanvalkenburg): the test file repeated 'from agent_framework_foundry._foundry_evals import ...' inside 22 test bodies and 'from agent_framework_foundry import GeneratedEvaluatorRef' inside 8 more. Move all of them to the existing top-level imports; the symbols are the same across tests and the local imports were redundant.

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

---------

Co-authored-by: Ben Thomas <25218250+alliscode@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Ben Thomas · 2026-06-01 23:01:56 +00:00

e0d0ad16a0

Python: Fix core observability unsafe serialization of function-call arguments containing dataclass/framework objects (#6026 )

* fix: safely serialize function-call arguments in core observability

Apply make_json_safe() to content.arguments in _to_otel_part() before
building the otel message dict, so that dataclass/framework payloads
(e.g. workflow request_info events) do not cause a TypeError when
_capture_messages() calls json.dumps().

Lift make_json_safe() into agent_framework._serialization (no new
external deps — dataclasses/datetime only) so the core observability
path can use it without a dependency on the ag-ui adapter.

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

* fix(core): safely serialize workflow request_info payloads in observability (#5733)

- Add make_json_safe() helper to recursively convert non-serializable objects
- Use make_json_safe() in _to_otel_part() for function_call arguments
- Fix CustomPayload test class to use @dataclass (resolves B903 lint error)

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

* fix(serialization): guard callability and normalize dict keys in make_json_safe (#5733)

- Use callable(getattr(obj, method, None)) instead of hasattr() so that
  non-callable attributes named model_dump/to_dict/dict do not raise
  TypeError at runtime.
- Wrap each call in try/except TypeError to handle callables with
  mandatory arguments gracefully.
- Convert dict keys to str() so that non-string keys (e.g. datetime,
  int) cannot cause json.dumps to raise TypeError.
- Add regression tests for both scenarios.

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

* Address observability serialization review feedback

---------

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

Evan Mattson · 2026-06-01 21:41:52 +00:00

f36096ce1a

Python: refresh dev dependencies and validate runtime bounds (#6238 )

Updates third-party dev dependencies across the Python workspace and
validates that all runtime dependency bounds still hold at both ends.

Dev dependency bumps (root, lab, declarative, durabletask):
- uv 0.11.6 -> 0.11.17, ruff 0.15.8 -> 0.15.15,
  pytest-asyncio 1.3.0 -> 1.4.0, mcp 1.27.0 -> 1.27.2,
  azure-monitor-opentelemetry 1.8.7 -> 1.8.8,
  poethepoet 0.42.1 -> 0.46.0, prek 0.3.9 -> 0.4.3,
  types-python-dateutil and types-PyYaml stub bumps.
- Transitive Dependabot items swept via lock: idna 3.11 -> 3.17,
  pip 26.0.1 -> 26.1.2.

Deliberately excluded:
- opentelemetry-sdk stays 1.40.0: azure-monitor-opentelemetry (incl.
  1.8.8) hard-pins opentelemetry-sdk==1.40.
- mypy stays 1.20.0 and pyright stays 1.1.408: the 2.1.0 / 1.1.409
  bumps introduce new diagnostics that fail type checking and need
  dedicated PRs.
- rich kept as a range: agentlightning (lab[lightning]) forces
  rich==13.9.4.

Code/formatting changes driven by the ruff upgrade:
- devui lifespan now uses try/finally so shutdown cleanup always runs
  (ruff RUF075).
- Removed unused TYPE_CHECKING imports in core and foundry flagged by
  ruff 0.15.15.
- Reapplied ruff 0.15.15 formatting to the files it changed.

Validation: validate-dependency-bounds-test "*" passes (31/31 lower +
31/31 upper); typing 62/62; lint 31/31; devui tests pass.

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

Eduard van Valkenburg · 2026-06-01 17:53:56 +00:00

8091d052d8

Python: Add background agent support to harness agent (#6155 )

* Add background agent support to harness agent

* Address PR comments

westey · 2026-06-01 17:20:39 +00:00

52a8045bb6

Python: coalesce code interpreter history chunks (#5801 )

* fix: coalesce code interpreter history chunks

* fix: narrow content item list types

* fix: remove redundant content list casts

Yufeng He · 2026-06-01 13:26:20 +00:00

78d175a1e2

Python: consolidate MCP reliability fixes (#6145 )

* Python: consolidate MCP reliability fixes

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

* Fix MCP cleanup and metadata typing

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

* Satisfy MCP metadata mypy typing

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

* Fix Pyright metadata mapping type

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

---------

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

Eduard van Valkenburg · 2026-05-29 07:21:14 +00:00

e8ff541ebf

Python: Adding AgentFileStore and FileAccessProvider to support file access operations. (#6099 )

* Adding AgentFileStore and FileAccessProvider to support file ased operations for agents.

* Address PR review feedback on FileAccessProvider

- Probe symlinks on the unresolved candidate path so in-root symlinks
cannot silently pass and out-of-root symlinks surface the correct
error message.
- Validate matching_lines elements in FileSearchResult.from_dict and
raise a clean ValueError for non-mapping entries.
- Cap search regex pattern length (256 chars) via a new
_compile_search_regex helper to mitigate ReDoS, and surface the cap
in the file_access_search_files tool description.
- Skip non-UTF-8 files during filesystem search instead of aborting
the entire directory walk.
- Replace the module-scope trailing string in the data-processing
sample with comments to avoid Ruff B018.
- Remove the checked-in working/region_totals.md sample artifact so
the save flow works from a clean checkout.
- Expand the Windows stdout reconfiguration comment in task_runner.py
for clarity.
- Add tests for invalid/oversize regex, non-UTF-8 file search, and
in-root symlink rejection.