Skip to content

fix: add default None to optional HttpToolConfig fields - #8190

Open
MOHAMMED WASIM KHAN (wasim-builds) wants to merge 7 commits into
microsoft:mainfrom
wasim-builds:fix/7172-http-tool-config-defaults
Open

fix: add default None to optional HttpToolConfig fields#8190
MOHAMMED WASIM KHAN (wasim-builds) wants to merge 7 commits into
microsoft:mainfrom
wasim-builds:fix/7172-http-tool-config-defaults

Conversation

@wasim-builds

Copy link
Copy Markdown

What happened

HttpTool._from_config() failed with ValidationError: Field required [type=missing, input_type=dict] for the headers field when reconstructing an HttpTool from its serialized config.

Root cause

HttpToolConfig declared headers: Optional[dict[str, Any]] without a default value. When dump_component() serialized the config via model_dump(exclude_none=True), the None value for headers was omitted. On deserialization, _from_config() passed the incomplete dict back to HttpToolConfig, which rejected the missing field.

Fix

Added = None defaults to both description and headers in HttpToolConfig. These are already optional in HttpTool.__init__, so this just makes the Pydantic model consistent with the constructor.

Testing

No new tests. I manually verified the reproduction from the issue: creating an HttpTool without headers, wrapping it in StaticStreamWorkbench, calling dump_component(), and then load_component() now succeeds.

Fixes #7172

Wasim added 7 commits September 4, 2026 12:15
Added a new cancellation.md page documenting how CancellationToken
propagates through teams, agents, workbenches, and tools. Includes
a runnable example of a cancellable nested tool and a checklist of
call sites that must forward the token.

Fixes microsoft#8091
Cache key was built from messages, tools, json_output, and
extra_create_args only. Calls that differed only in tool_choice
(e.g. auto vs none) collided and returned stale cached responses.

Added tool_choice to the cache key data. For Tool objects, the
serialized key uses the tool name; for string choices, the string
is used directly.

Fixes microsoft#7968
…string

Previously, return_value_as_string fell back to str() for dict/list
values, producing Python repr strings instead of valid JSON. This
broke downstream agents that expected parseable structured data.

Now dict and list return values are serialized with json.dumps(),
matching the existing BaseModel path. Other types still use str()
as a safe fallback.

Fixes microsoft#7867
Added GEN_AI_AGENT_ACTION_REF constant and derive_action_ref helper
for deterministic cross-producer audit correlation. Added optional
action_ref parameter to trace_tool_span().

Fixes microsoft#7850
…nClient

Streaming tool_call chunks can have None fields for id, function.name,
or function.arguments. Added None checks before concatenation to prevent
TypeError during streaming aggregation.

Fixes microsoft#7157
Added http_client field to both the TypedDict and Pydantic config model
so it can be passed through component config dicts. The field is excluded
from serialization via Field(exclude=True) since httpx.AsyncClient
instances are not JSON-serializable.

Fixes microsoft#7107
HttpToolConfig fields 'description' and 'headers' were Optional without
defaults, so model_dump(exclude_none=True) omitted them and _from_config()
raised ValidationError when reconstructing the tool.

Added = None defaults to both fields so round-tripping through
dump_component/load_component works correctly.

Fixes microsoft#7172
Copilot AI lite review requested due to automatic review settings September 4, 2026 07:34

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This changes some previously printable tool returns into exceptions. A dict/list containing a non-JSON-native value such as Path, datetime, bytes, or a custom object used to fall through to str(value); now json.dumps() raises TypeError. Could JSON serialization fall back to the previous string behaviour when the value is not JSON-serializable?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Failed to call _from_config() when HttpTool in StaticStreamWorkbench

3 participants