* fix: use getattr for non-OpenAI provider response compatibility
Fixes#6234Fixes#6235
Use getattr with None fallback for system_fingerprint and output
attributes to prevent AttributeError when non-OpenAI providers
return response objects without these fields.
* fix: use typed variable for response output to satisfy pyright
Fixes#6235
Use getattr with None fallback for the output attribute, and assign
to a typed list variable before the match statement to help pyright
narrow the response item types correctly.
* fix: rename response_outputs to avoid name collision with case-block variable
Fixes#6235
Rename outputs to response_outputs on line 1974 to avoid mypy error
about conflicting variable names in the match statement's case blocks.
Also use list[Any] for explicit generic type annotation.
* fix: use cast(list[Any]) for response output to satisfy pyright
Fixes#6235
The getattr() call returns Unknown type which pyright cannot narrow
in the match statement. Use an explicit cast to list[Any].
* fix: use hasattr guard instead of getattr for response.output
Fixes#6235
Using hasattr(response, 'output') and then accessing response.output
directly gives pyright enough type information to verify the match
statement exhaustiveness. This avoids the cast(list[Any]) approach
which pyright still flagged as partially unknown.
* fix: use ternary operator for response_outputs assignment
Replace if-else block with ternary expression to satisfy ruff SIM108 lint rule.
This fixes the Package Checks (3.11) CI failure.
* fix: use ternary with cast for ruff SIM108 and pyright type safety
Replace if-else block with ternary expression using cast(list[Any], ...)
to satisfy:
- ruff SIM108 (use ternary instead of if-else)
- ruff E501 (line length < 120)
- pyright type narrowing (cast preserves type info lost in ternary)
All local checks pass: ruff check, ruff format, pyright, 298 tests.
* fix: replace hasattr+cast with try/except to preserve pyright types
---------
Co-authored-by: Tao Chen <taochen@microsoft.com>
* 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
* feat(claude): bump claude-agent-sdk to 0.2.87
Upgrade claude-agent-sdk dependency from >=0.1.36,<0.1.49 to >=0.2.87,<0.3.
Changes:
- Bump version pin in pyproject.toml
- Add 'xhigh' effort level to ClaudeAgentOptions (Opus 4.7 specific)
- Expose new upstream SDK options: skills, session_id, task_budget,
include_hook_events, strict_mcp_config, continue_conversation,
fork_session
- Add TaskBudget type import
- Update uv.lock
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* chore: lower claude-agent-sdk floor to >=0.1.36
Keep the lower bound at 0.1.36 since the 0.1→0.2 transition was additive
and our code works on older versions as long as new options aren't used.
This avoids forcing unnecessary upgrades on existing users.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: replace TaskBudget import with inline type for SDK compat
TaskBudget was added in claude-agent-sdk 0.2.93 but does not exist in
0.2.87. Use dict[str, int] inline type instead so type checking passes
against 0.2.87. Lock file pinned to 0.2.87.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* 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
* fix(mem0): parallel memory retrieval logic and strict type compliance
* fix(mem0): align parallel retrieval types for pyright and mypy
* fix(mem0): handle asyncio.CancelledError in search response and update test description
* fix(mem0): improve error handling for asyncio.CancelledError and update test names for clarity
* fix(mem0): improve retrieval response handling
* fix(gemini): preserve schema response_format
* fix(gemini): satisfy pyright strict in response schema extraction
Cast Any-narrowed mappings to Mapping[str, Any] in the structured-output
schema helpers so pyright strict no longer reports partially-unknown
member, argument, and variable types. Pass response_format["format"]
straight into the recursive extractor, which already guards non-mapping
inputs. No behavior change.
* fix(gemini): use Sequence[object] cast to satisfy both mypy and pyright
The Sequence[Any] cast pyright strict needs to know the loop element type
is reported as a redundant-cast by mypy, which already narrows the
isinstance branch to Sequence[Any]. Cast to Sequence[object] instead:
pyright gets a fully known element type and mypy no longer sees an
identical-type cast. No behavior change.
---------
Co-authored-by: Evan Mattson <evan.mattson@microsoft.com>
* 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>
* Python: fix ConnectTimeout on multi-turn FoundryAgent conversations (#6241)
Expose a `timeout` parameter on `RawFoundryAgentChatClient`,
`_FoundryAgentChatClient`, `RawFoundryAgent`, `FoundryAgent`, and
`RawOpenAIChatClient` so callers can override the HTTP timeout used by
the underlying AsyncOpenAI client.
Root cause: `RawFoundryAgentChatClient.__init__` called
`project_client.get_openai_client()` without configuring any timeout,
inheriting the OpenAI SDK default of `httpx.Timeout(connect=5.0)`.
When connections are recycled between turns under load, the 5 s connect
timeout fires and surfaces as `openai.APITimeoutError`.
Fix:
- `load_openai_service_settings` (`_shared.py`): accept `timeout` and
include it in `client_args` for all three `AsyncOpenAI`/
`AsyncAzureOpenAI` construction paths.
- `RawOpenAIChatClient.__init__` (`_chat_client.py`): accept `timeout`
and forward to `load_openai_service_settings`.
- `RawFoundryAgentChatClient.__init__` (`_agent.py`): accept `timeout`
and set `openai_client.timeout = timeout` on the client returned by
`get_openai_client()` before passing it to the base class.
- `_FoundryAgentChatClient`, `RawFoundryAgent`, `FoundryAgent`: accept
and propagate `timeout` through the construction chain.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add timeout parameter to FoundryAgent and RawOpenAIChatClient
Expose a timeout parameter on RawFoundryAgentChatClient,
_FoundryAgentChatClient, RawFoundryAgent, FoundryAgent, and
RawOpenAIChatClient. When provided, the value is applied to the
underlying AsyncOpenAI client so that connect timeouts under load
or after connection recycling can be tuned by callers.
Previously, get_openai_client() was called without any timeout
override, so the SDK default of httpx.Timeout(connect=5.0) was
inherited and could fire on multi-turn conversations where the
underlying connection is recycled between turns.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Python: Add `timeout` parameter to `FoundryAgent` to fix `ConnectTimeout` on multi-turn conversations
Fixes#6241
* fix(foundry): use with_options to avoid mutating shared OpenAI client timeout (#6241)
Replace direct assignment with
in
RawFoundryAgentChatClient.__init__.
The Azure AI Projects SDK caches and returns a shared AsyncOpenAI client
per AIProjectClient. Mutating its .timeout attribute leaked the override
to all other code paths sharing that client (other agents, user code).
with_options() returns a new client instance with the override applied,
leaving the original shared client untouched.
Update tests to assert with_options is called with the correct timeout
and that the original shared client's timeout attribute is not mutated.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* test(foundry): assert with_options return value flows to instance.client (#6241)
The four timeout propagation tests verified that with_options was called
but did not confirm that the returned (timeout-configured) client was
actually stored on the instance. A silent discard of the return value
would have left the tests green while the timeout had no effect.
Each test now captures the constructed instance and asserts:
assert <instance>.client is openai_client_mock.with_options.return_value
Affected tests:
- test_raw_foundry_agent_chat_client_init_applies_timeout_to_openai_client
- test_raw_foundry_agent_chat_client_init_applies_timeout_with_preview_enabled
- test_foundry_agent_chat_client_init_propagates_timeout
- test_foundry_agent_init_propagates_timeout_to_openai_client
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix magentic manager warning
* Use typing_extensions.Sentinel for _MISSING sentinel value
Replace the bare object() sentinel with typing_extensions.Sentinel per
PEP 661 (now final). Sentinel provides a proper name and repr
('<_MISSING>') and is the idiomatic approach going forward.
Refs #4306
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: correct Sentinel type annotation for max_stall_count param (#6261)
Use int | Sentinel for max_stall_count parameter type annotation instead
of int with cast(Any, _MISSING) to properly express that the parameter
can hold either an int or the _MISSING sentinel value. This fixes the
pyright reportUnnecessaryComparison errors caused by the types int and
Sentinel having no overlap.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Rename _MISSING sentinel to UNSET in orchestrations
The sentinel is user-visible as a default in public init signatures, so
use UNSET (no leading underscore) instead of the private _MISSING name.
Drop the now-unnecessary reportPrivateUsage ignores on the UNSET imports.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* 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
* 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>
* 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
* Fix FoundryAgent stripping model from PromptAgent requests
Move run_options.pop('model', None) inside the _uses_foundry_agent_session()
conditional so that model is only stripped for hosted agent sessions (where
the server manages the model) and preserved for PromptAgent requests that
require it in the Responses API call.
Fixes#5525
* test: add coverage for resp_* continuation preserving model
Adds test_raw_foundry_agent_chat_client_prepare_options_preserves_model_for_resp_continuation
to explicitly verify that HostedAgent v1 / v2-no-session paths (where conversation_id
starts with resp_) preserve model and previous_response_id without triggering the
hosted-session gate.
---------
Co-authored-by: Benke Qu <bequ@microsoft.com>
Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com>
* 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.
* feat(bedrock): add structured output support via Converse API (Fixes#5966)
* fix(bedrock): improve unsupported model exception handling and schema parsing
* refactor(bedrock): use generic traversal for strict schema enforcement
* address Copilot review comments on structured output
* refine bedrock structured output: guard additionalProperties, TypeError check, docs + test
* fix(bedrock): widen response_format to Mapping and add missing test coverage
* 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>
* 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>
* Initial plan
* Fix integration test worker crashes on Python 3.13
Three changes to prevent pytest-xdist workers from crashing during
Azure Functions integration tests:
1. Add `start_new_session=True` to subprocess on Linux so signals
(e.g. from test-timeout) cannot propagate between the func host
and the xdist worker process.
2. Add an overall 100-second budget to the fixture setup loop so
the retry logic never exceeds the 120-second test timeout. When
pytest-timeout's thread method fires during fixture setup and the
thread doesn't respond, it calls os._exit() which kills the
xdist worker – this is the root cause of the "Not properly
terminated" crashes.
3. Remove the `UV_PYTHON: "3.10"` workaround from both workflow
files so integration tests actually run on Python 3.13.
Co-authored-by: larohra <41490930+larohra@users.noreply.github.com>
* Validate integration tests on Python 3.13
Co-authored-by: larohra <41490930+larohra@users.noreply.github.com>
* Revert unintentional uv.lock dependency bumps
Co-authored-by: larohra <41490930+larohra@users.noreply.github.com>
* Use time.monotonic() instead of time.time() for fixture budget timing
Addresses review feedback: monotonic clock is immune to NTP/clock
adjustments that could skew the budget enforcement.
Co-authored-by: larohra <41490930+larohra@users.noreply.github.com>
* Fix func worker segfault on Python 3.13 by redirecting worker to Python 3.12
The Azure Functions Python worker crashes with SIGSEGV (exit code 139)
on Python 3.13 due to protobuf C extension (google._upb) compatibility
issues. When the test runner uses Python >=3.13, the conftest now
automatically finds a compatible Python 3.10-3.12 and sets
languageWorkers__python__defaultExecutablePath so the func host uses
it for the worker process.
The CI setup action also ensures Python 3.12 is available on the
runner, falling back to uv python install if the system doesn't have
it.
Co-authored-by: larohra <41490930+larohra@users.noreply.github.com>
* Address code review: add path validation, clarify version range and config key format
Co-authored-by: larohra <41490930+larohra@users.noreply.github.com>
* Run func worker natively on Python 3.13 by disabling dependency isolation
Replace the Python 3.12 redirect workaround with the proper fix:
set PYTHON_ISOLATE_WORKER_DEPENDENCIES=0 on Python >=3.13.
The segfault (exit code 139) is caused by the Azure Functions worker's
module isolation mechanism conflicting with protobuf's C extensions
(google._upb) on Python 3.13. Disabling isolation lets the worker
load dependencies from the app's own environment, which avoids the
crash while keeping everything running on Python 3.13.
See: https://github.com/Azure/azure-functions-python-worker/issues/1797
Co-authored-by: larohra <41490930+larohra@users.noreply.github.com>
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: larohra <41490930+larohra@users.noreply.github.com>
Co-authored-by: Laveesh Rohra <larohra@microsoft.com>
* Reorganize A2A samples: client demos in 02-agents, use package A2AExecutor
- Move client samples (agent_with_a2a, a2a_agent_as_function_tools) to samples/02-agents/a2a/
- Add new concept samples: polling, stream reconnection, protocol selection
- Replace sample agent_executor.py with package-level A2AExecutor (stream=True)
- Update 04-hosting/a2a to focus on server-side, point to 02-agents for clients
- Add README.md for the new 02-agents/a2a/ sample collection
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix streaming artifact coalescing and address PR review feedback
A2AExecutor fix:
- Generate a stable artifact_id per stream in _run_stream so all streaming
chunks share the same ID, enabling proper append=True coalescing per the
A2A spec (TaskArtifactUpdateEvent with same artifactId).
- Previously, item.message_id was None for OpenAI/Foundry streaming updates,
causing the SDK to generate a new random UUID per token (100+ separate
artifacts instead of 1 appended artifact).
Sample improvements:
- Replace join workaround with response.text now that coalescing works
- Add background=True to stream reconnection resume call (required for
continuation token emission on in-progress tasks)
- Fix type ignore specificity in polling sample
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Map A2A protocol message_id to AgentResponseUpdate.message_id in two paths
where it was previously omitted, aligning with .NET behavior:
1. Standalone A2AMessage: set message_id=msg.message_id (matches .NET
ConvertToAgentResponseUpdate(Message) which sets both ResponseId and
MessageId to message.MessageId)
2. TaskStatusUpdateEvent (terminal/input_required): set
message_id=message.message_id (matches .NET which sets
MessageId=statusUpdateEvent.Status.Message?.MessageId)
Fixes#5949
Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* 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.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix mypy redundant-cast in FileSearchResult.from_dict
Use cast(list[object], ...) instead of cast(list[Any], ...) so the
cast represents a real type change (lists are invariant) and is no
longer flagged by mypy as redundant, while still satisfying pyright's
reportUnknownVariableType. Matches the existing pattern in _memory.py.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Tighten path normalization and directory resolution in FileAccess
- _normalize_relative_path now strips surrounding whitespace up front
so leading/trailing spaces never leak into file segments, and
rejects trailing path separators for file paths so 'foo/' is no
longer silently coerced to 'foo'.
- FileSystemAgentFileStore._resolve_safe_directory_path normalizes
with is_directory=True and maps an empty normalized result to the
root. This matches InMemoryAgentFileStore so whitespace-only
directory inputs resolve to the root instead of raising.
- Added tests for whitespace stripping, trailing-separator rejection,
and whitespace-only directory listing on the filesystem store.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Harden FileAccess search and atomic save in store API
- Add wall-clock timeout (10s) around regex scans so a pathological pattern (e.g. `(a+)+`) below the length cap cannot stall the event loop.
- Offload the InMemoryAgentFileStore regex scan to a worker thread, matching the filesystem store.
- Fail closed when `Path.is_symlink` raises during the safe-path probe so a permission error cannot silently bypass the symlink/reparse-point rejection.
- Add `overwrite: bool = True` to `AgentFileStore.write_file`; the in-memory store performs the check under the existing lock and the filesystem store uses `open(mode='x')` so concurrent callers cannot race past `overwrite=False`.
- `file_access_save_file` now relies on the atomic store call instead of a separate `file_exists` round-trip.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix Python 3.10 timeout handling and add directory arg to list/search tools
- Catch asyncio.TimeoutError in _run_search_with_timeout. In Python 3.10
asyncio.wait_for raises asyncio.exceptions.TimeoutError, which is
distinct from the builtin TimeoutError (the two were unified in 3.11).
Catching the asyncio alias works on every supported version.
- Add an optional directory parameter to file_access_list_files and
file_access_search_files so agents can enumerate / scope searches to
nested folders, not just the store root.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address FileAccess review feedback: case, errors, signal, TOCTOU
- InMemoryAgentFileStore now stores (display_name, content) so list_files
and search_files return the original-case names callers wrote, matching
the behaviour of FileSystemAgentFileStore on case-preserving filesystems
and removing the silent in-memory vs. on-disk contract divergence.
- FileSystemAgentFileStore.read_file raises ValueError instead of letting
UnicodeDecodeError bubble for binary / non-UTF-8 input, restoring
symmetry with search_files (which still skips) and giving the tool
layer a recoverable type to translate.
- Tool wrappers now catch ValueError and OSError around every operation
and surface them as readable strings, so 'you used ..' and 'the file
already exists' are both reported to the model the same way instead of
the former crashing out as an unhandled exception.
- _search_files_sync logs per skipped non-UTF-8 file at WARNING and an
aggregate INFO summary so operators can distinguish 'no matches' from
'half the corpus was unreadable'.
- FileSystemAgentFileStore softens its docstrings to acknowledge the
inherent probe-then-open TOCTOU window. On POSIX both read and write
now pass O_NOFOLLOW so the kernel refuses if the leaf segment becomes
a symlink between the probe and the open. Windows has no equivalent
flag; the limitation is documented.
- Tests cover: case preservation on list/search, ValueError on non-UTF-8
read at the store and tool layer, tool-layer string responses for
path-traversal and oversized-regex inputs, search-skip log output,
symlink rejection on delete/search/list, and symlinked intermediate
directory rejection.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address FileAccess nit comments: docstrings, enumerate, opt-in delete approval
- Expand FileSearchMatch/FileSearchResult.to_dict docstrings to explain why
the override is needed (__slots__ defeats the mixin's __dict__ iteration)
and why exclude/exclude_none are accepted-but-ignored (mixin signature
compatibility for callers like to_json).
- Use enumerate(lines, start=1) in _search_file_content so the +1 below is
no longer needed; rename loop variable to line_number for clarity.
- Add opt-in require_delete_approval: bool = False on FileAccessProvider.
When True, file_access_delete_file is registered with approval_mode
'always_require' so the host must approve every delete. Default False
preserves current behaviour and matches the .NET reference, but
deployments that want a safer-by-default posture can enable it.
- Add tests covering both delete approval modes.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* FileAccess: require delete approval by default
Flip the default for FileAccessProvider(require_delete_approval=...) from
False to True so destructive deletes are gated by host approval out of the
box. Callers that want the previous autonomous behaviour (which matches the
.NET reference) can pass require_delete_approval=False.
Tests updated accordingly.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fixing linkinspector by installing Chrome for puppeteer first.
---------
Co-authored-by: Ben Thomas <25218250+alliscode@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Expose supported_protocol_bindings as configurable parameter on A2AAgent
Add supported_protocol_bindings parameter to A2AAgent.__init__() allowing
users to configure which A2A protocol bindings (JSONRPC, GRPC, HTTP+JSON)
the client prefers when connecting to remote agents.
- Defaults to ["JSONRPC"] matching current behavior
- Passes through to ClientConfig for transport negotiation
- Replaces 4 hardcoded references with the configurable value
Closes#6057
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Fix empty list falsy trap and add fallback path test coverage
- Use 'is not None' check instead of 'or' to preserve explicit empty list
- Add test verifying empty list is not silently replaced with defaults
- Add test verifying fallback path uses custom bindings
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Document known protocol binding values in docstring
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Use Literal union for protocol binding type hint
Provides IDE autocomplete for known values while keeping the type
open for custom bindings (Literal is str at runtime).
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Bumps the released 1.6.0 packages agent-framework, agent-framework-core, agent-framework-foundry, and agent-framework-openai to 1.7.0, with root continuing to exactly pin agent-framework-core[all]. Bumps the changed prerelease packages agent-framework-a2a, agent-framework-chatkit, agent-framework-declarative, agent-framework-devui, and agent-framework-foundry-hosting to the 260528 date stamp, raises core floors on the packages included in this release, raises Foundry's OpenAI floor alongside OpenAI, and raises ChatKit's openai-chatkit floor to the minimum version required by the current typed API usage. No beta cohort bump was applied; the absent mistal/mistral package was intentionally not bumped because no such package exists in this branch.
* Python: Allow hosted checkpoints to restore MessageRole
Allow Responses hosting checkpoint storage to deserialize the Azure Responses MessageRole enum that hosted workflows can persist inside Agent Framework Message objects.
Add regression coverage for both direct load() and the hosted get_latest() restore path, including the plain-storage failure mode where list_checkpoints logs the blocked type and get_latest() returns None.
Ruff also normalizes a duplicate contextlib import in the touched hosting module.
* Address MessageRole checkpoint review comments
* Cover hosted MessageRole checkpoint restore path
Tao Chen ·
Willow Lopez ·
Eduard van Valkenburg ·
Giles Odigwe ·
Evan Mattson ·
Vedant Sonani ·
cooleryu ·
Peter Ibekwe ·
Yufeng He ·
semenshi-m ·
Benke Qu ·
Dineshsuriya D ·
Hameed Kunkanoor ·
Thota Sai Karthik ·
Ben Thomas ·
westey ·
Copilot ·
Daria Korenieva ·
Baidar ·