release: 0.3.0

[stainless-app]

Automated Release PR

0.3.0 (2026-02-13)

Full Changelog: v0.2.0...v0.3.0

Features

• client: add custom JSON encoder for extended type support (30a7195)
• client: add support for binary request streaming (48f4cca)
• runner: dependency-aware parallel tool execution (7e6716f)
• runner: dependency-aware parallel tool execution (#44) (a72f70f)
• stream: return StreamResult from stream helpers; fix _compat SyntaxError (#46) (5590e57)
• stream: return StreamResult from stream_async / stream_sync (e3a55da)

Bug Fixes

• _compat: remove duplicate by_alias keyword arg (a7deb39)
• api: add byok provider model (bf52572)
• api: default auth server (38c637a)
• api: narrow types (3e16d98)
• docs: fix mcp installation instructions for remote servers (e4e3619)
• runner: allow local tool execution in mixed MCP+local scenarios (5d0ce6d)
• runner: inject server tool results into conversation for mixed tool calls (288b70e)
• runner: preserve thought_signature in tool call accumulation and extraction (77e5958)
• runner: server tool results, mixed-tool execution, thought_signature passthrough (#45) (637d9b8)
• runner: skip early break when local tools need execution alongside MCP (ad7379b)

Chores

• api: small type fixes (2268aff)
• ci: add missing environment (0ec49ed)
• ci: upgrade actions/github-script (cf53a9e)
• format all api.md files (ead37d4)
• internal: bump dependencies (696aacf)
• internal: fix lint error on Python 3.14 (eace981)
• internal: update actions/checkout version (c72dfca)
• runner: strip commented-out production version and banner comments from core.py (59350e3)

Styles

• tests: flatten test classes to module-level functions (57dc181)

---

This pull request is managed by Stainless's GitHub App.

The semver version number is based on included commit messages. Alternatively, you can manually set the version number in the title of this pull request.

For a better experience, it is recommended to use either rebase-merge or squash-merge when merging this pull request.

🔗 Stainless website
📚 Read the docs
🙋 Reach out for help or questions

[stainless-app]

🧪 Testing

To try out this version of the SDK, run:

pip install 'https://pkg.stainless.com/s/dedalus-sdk-python/5590e57a4fc13b4f29c8c0109bd3eb4c6da585fa/dedalus_labs-0.2.0-py3-none-any.whl'

Expires at: Sun, 15 Mar 2026 00:06:55 GMT
Updated at: Fri, 13 Feb 2026 00:06:55 GMT

[cursor]

Iterator content silently lost on request retry

Medium Severity

When content is an Iterable[bytes] (like a generator), the iterator is consumed on the first request attempt. If a retryable error occurs, the retry logic uses model_copy which performs a shallow copy, so options.content still references the same exhausted iterator. Subsequent retry attempts send an empty request body. This is exacerbated by DEFAULT_MAX_RETRIES being increased from 0 to 2 in this same PR. Users passing generator-based content could experience silent data loss on transient failures.

Additional Locations (1)

• src/dedalus_labs/_constants.py#L9-L10

 

[cursor]

PR Summary

Medium Risk
Touches core request/serialization and retry behavior (could subtly change request bodies, streaming, and error handling), and refactors runner execution/scheduling logic; changes are broad but largely additive with guarded fallbacks.

Overview
Bumps the SDK to v0.3.0 and regenerates docs/metadata, including updated changelog, endpoint stats, and dependency lock updates.

Adds new API surface: client.ocr.process() and client.responses.create() resources (sync/async + raw/streaming wrappers), expands TTS speech typing to support custom voice IDs and a new model variant, and sets a default as_base_url while also sending X-Provider-Model when configured.

Updates the HTTP layer to support raw/binary request bodies via a new content option (with deprecation warnings for body=bytes), uses a custom JSON serializer (openapi_dumps) for broader type support (e.g., datetime, pydantic models), and changes retry defaults to 2 retries with larger backoff.

Refactors the runner to pass through a wider set of chat-completions parameters, preserves thought_signature in tool calls, unifies tool-call delta accumulation, and introduces a dependency-aware scheduler (lib/runner/_scheduler.py) to execute local tools in topo order with async parallelism.

CI/release workflows are updated (checkout v6, github-script v8, PyPI workflow now targets production environment), and formatting scripts now ruffen all api.md files in the repo.

^{Written by Cursor Bugbot for commit afba00e. This will update automatically on new commits. Configure here.}

[cursor]

Missing assistant message before tool execution in streaming paths

High Severity

Both streaming paths (_execute_streaming_async and _execute_streaming_sync) call the scheduler's execute_local_tools_async/execute_local_tools_sync without first appending an assistant message with tool_calls to the messages list. The scheduler's own docstring explicitly states the caller is responsible for this. The non-streaming paths (_execute_tool_calls at line 1204, _execute_tool_calls_sync at line 1229) correctly append {"role": "assistant", "tool_calls": ...} before calling the scheduler. The old streaming code also did this but the line was removed during the refactoring. This produces a malformed conversation (tool messages without a preceding assistant message), which will cause the API to reject subsequent requests.

Additional Locations (1)

• src/dedalus_labs/lib/runner/core.py#L1067-L1075

 

[cursor]

Collected MCP tool results variable is never used

Low Severity

mcp_tool_results_from_server is assigned in both _execute_streaming_async and _execute_streaming_sync but is never read after assignment. The variable is dead code — the collected MCP tool results are silently discarded. Given the PR includes a fix for "inject server tool results into conversation for mixed tool calls," this may represent an incomplete implementation for the streaming paths.

Additional Locations (1)

• src/dedalus_labs/lib/runner/core.py#L974-L983

 

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{Bugbot Autofix is ON. A Cloud Agent has been kicked off to fix the reported issue.}

[cursor]

Default by_alias change breaks request serialization of aliased fields

Medium Severity

The model_dump helper in _compat.py changed its by_alias default from hardcoded True to None (effectively False). The _transform_recursive function in _transform.py calls model_dump(data, exclude_unset=True, mode="json") without passing by_alias, relying on the previous default. This breaks serialization of Pydantic models with field aliases — notably JSONSchema.schema_ (aliased to "schema") will now serialize as "schema_" instead of "schema", sending incorrect field names to the API.

 

[cursor]

Bugbot Autofix prepared fixes for 1 of the 1 bugs found in the latest run.

• ✅ Fixed: Default by_alias change breaks request serialization of aliased fields
  • Changed the by_alias parameter default from None to True in model_dump() to restore the original behavior where Pydantic field aliases are used during serialization.

Or push these changes by commenting:

@cursor push 018c6c55a4

Preview (018c6c55a4)

diff --git a/src/dedalus_labs/_compat.py b/src/dedalus_labs/_compat.py
--- a/src/dedalus_labs/_compat.py
+++ b/src/dedalus_labs/_compat.py
@@ -139,7 +139,7 @@
     exclude_defaults: bool = False,
     warnings: bool = True,
     mode: Literal["json", "python"] = "python",
-    by_alias: bool | None = None,
+    by_alias: bool = True,
 ) -> dict[str, Any]:
     if (not PYDANTIC_V1) or hasattr(model, "model_dump"):
         return model.model_dump(
@@ -154,7 +154,7 @@
     return cast(
         "dict[str, Any]",
         model.dict(  # pyright: ignore[reportDeprecated, reportUnnecessaryCast]
-            exclude=exclude, exclude_unset=exclude_unset, exclude_defaults=exclude_defaults, by_alias=bool(by_alias)
+            exclude=exclude, exclude_unset=exclude_unset, exclude_defaults=exclude_defaults, by_alias=by_alias
         ),
     )