deepagents-code 0.1.42__tar.gz → 0.1.44__tar.gz

{deepagents_code-0.1.42 → deepagents_code-0.1.44}/CHANGELOG.md

@@ -2,6 +2,36 @@
 
 # Deep Agents Code Changelog
 
+## [0.1.44](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.43...deepagents-code==0.1.44) (2026-07-20)
+
+### Bug Fixes
+
+- Improved approval handling by hiding the `Auto` option when it isn't eligible and moving Auto mode path checks off the event loop. ([#4839](https://github.com/langchain-ai/deepagents/issues/4839), [#4856](https://github.com/langchain-ai/deepagents/issues/4856))
+- Warmed MCP auth imports off the event loop to avoid blocking runtime work. ([#4855](https://github.com/langchain-ai/deepagents/issues/4855))
+
+## [0.1.43](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.42...deepagents-code==0.1.43) (2026-07-17)
+
+### Features
+
+- Added classifier-backed Auto approval mode behind `DEEPAGENTS_CODE_EXPERIMENTAL=1` ([#4804](https://github.com/langchain-ai/deepagents/issues/4804)).
+- Added a shutdown toast for deferred exits ([#4830](https://github.com/langchain-ai/deepagents/issues/4830)).
+- Task descriptions that were truncated can now be expanded by clicking or pressing `Ctrl+O` ([#4811](https://github.com/langchain-ai/deepagents/issues/4811)).
+- Debug Console clears with `Ctrl+L` now persist after reopening ([#4812](https://github.com/langchain-ai/deepagents/issues/4812)).
+- Added debug logging for skill-name override collisions ([#4772](https://github.com/langchain-ai/deepagents/issues/4772)).
+
+### Bug Fixes
+
+- Keep chat input responsive during `/restart` ([#4808](https://github.com/langchain-ai/deepagents/issues/4808)).
+- Fixed paste placeholders disappearing when backspacing a newline below them ([#4757](https://github.com/langchain-ai/deepagents/issues/4757)).
+- Made markdown `AppMessage` output selectable ([#4814](https://github.com/langchain-ai/deepagents/issues/4814)).
+- Fixed live tool-group counts to include only running tools ([#4809](https://github.com/langchain-ai/deepagents/issues/4809)).
+- Kept `task` timers monotonic across nested subagent human-in-the-loop flows ([#4771](https://github.com/langchain-ai/deepagents/issues/4771)).
+- Preserved goal criteria proposals when marker clearing fails ([#4785](https://github.com/langchain-ai/deepagents/issues/4785)).
+- Reduced repeated probing of an unreachable Ollama daemon to once per reload ([#4806](https://github.com/langchain-ai/deepagents/issues/4806)).
+- Quieted MCP auth-skip debug logging for known patterns ([#4805](https://github.com/langchain-ai/deepagents/issues/4805)).
+- Improved `/version` diagnostics for editable installs and core dependency reporting, including surfacing `langchain-quickjs` ([#4816](https://github.com/langchain-ai/deepagents/issues/4816), [#4813](https://github.com/langchain-ai/deepagents/issues/4813)).
+- Removed the `uv install` tip from the `/version` update hint ([#4822](https://github.com/langchain-ai/deepagents/issues/4822)).
+
 ## [0.1.42](https://github.com/langchain-ai/deepagents/compare/deepagents-code==0.1.41...deepagents-code==0.1.42) (2026-07-17)
 
 ### Features

{deepagents_code-0.1.42 → deepagents_code-0.1.44}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepagents-code
-Version: 0.1.42
+Version: 0.1.44
 Summary: Terminal coding agent built on the Deep Agents SDK - works with any model, with persistent memory, customizable skills, subagents, and approval controls.
 Project-URL: Homepage, https://docs.langchain.com/oss/python/deepagents/overview
 Project-URL: Documentation, https://reference.langchain.com/python/deepagents/

{deepagents_code-0.1.42 → deepagents_code-0.1.44}/deepagents_code/_build_info.py

@@ -1,3 +1,3 @@
 """Generated at build time. Do not edit or commit."""
 
-BUILD_COMMIT = "18679a1"
+BUILD_COMMIT = "2b9cd08"

{deepagents_code-0.1.42 → deepagents_code-0.1.44}/deepagents_code/_cli_context.py

@@ -39,6 +39,8 @@ class CLIContextSchema:
 
     model_context_limit: int | None = None
 
+    approval_mode: str = "manual"
+
     auto_approve: bool = False
 
     approval_mode_key: str | None = None
@@ -73,14 +75,11 @@ class CLIContext(TypedDict, total=False):
     model_context_limit: int | None
     """Effective context-window limit for profile-aware middleware."""
 
-    auto_approve: bool
-    """Whether gated tool calls should skip the human-approval interrupt.
+    approval_mode: str
+    """`manual`, classifier-backed `auto`, or unrestricted `yolo`."""
 
-    Sourced from the client session (not graph state) so the model cannot
-    self-approve by writing state. The `interrupt_on` `when` predicate reads
-    this to suppress interrupts at the source when "approve always" is on,
-    avoiding the interrupt-then-auto-resolve round-trip.
-    """
+    auto_approve: bool
+    """Compatibility snapshot for clients predating the typed mode field."""
 
     approval_mode_key: str | None
     """Store key for the live approval-mode control record.

{deepagents_code-0.1.42 → deepagents_code-0.1.44}/deepagents_code/_version.py

@@ -2,7 +2,7 @@
 
 # Keep the `x-release-please-version` annotation — release-please uses it to
 # bump `__version__` in sync with `pyproject.toml` on every release PR.
-__version__ = "0.1.42"  # x-release-please-version
+__version__ = "0.1.44"  # x-release-please-version
 
 DOCS_URL = "https://docs.langchain.com/oss/python/deepagents/code"
 """URL for `deepagents-code` documentation."""