--
d9b0a6f822f773a61bcc507d252ca46da660b70b by Eugen-Bleck <eugenbleck@gmail.com>:
fix: match arg case in errors
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/724 from bl3ck:fix/preserve-arg-case-in-errors 3ac43ef2090f5e4b4158ea97cbcf16399aabe2e5
PiperOrigin-RevId: 764953570
Copybara import of the project:
--
e246af5965dfd4d032e0a3ce29513f3e2e874f73 by Alankrit Verma <alankrit386@gmail.com>:
tools: allow transfer_to_agent to accept extra kwargs
transfer_to_agent now takes **kwargs to swallow unexpected keyword args
Added integration tests covering single and multiple extra kwargs.
Fixes#458.
--
55fea786a9b7eb19b830dc67d7a2e37fe7937608 by Alankrit Verma <alankrit386@gmail.com>:
fix(tests): correct indentation in test_transfer.py for better readability
--
0c04f2d777bd4f3d8951dadd5e4e105530bd6281 by Alankrit Verma <alankrit386@gmail.com>:
fix(transfer_to_agent): restore strict two-arg signature and clarify usage
Revert the earlier **kwargs change so transfer_to_agent again only accepts
(agent_name, tool_context). Improve the doc-string to make clear that no
other parameters should be passed to this tool.
Fixes#458
--
d37448dd0ef9fc6199ca0e42b211b3cd9c886eb0 by Alankrit Verma <alankrit386@gmail.com>:
fix(transfer_to_agent): update docstring for clarity and accuracy
--
ea827af78fc2c9abdf030ad50e24bba8c996df75 by Wei Sun (Jack) <Jacksunwei@gmail.com>:
Update transfer_to_agent_tool docstring for better prompt
--
a144069a67b2e5652ffd50224b1ce68ddea14783 by Wei Sun (Jack) <Jacksunwei@gmail.com>:
Update transfer_to_agent_tool.py
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/466 from AlankritVerma01:tools/transfer-accept-kwargs 686d436457e3141d128c6e81452fddc546a14a7e
PiperOrigin-RevId: 764940463
--
cd9130aca29b5d07b069cfc4a9aa022455e005e9 by Yongsul Kim <ystory84@gmail.com>:
docs: Fix broken link to A2A example
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/1021 from ystory:patch-1 5d827f7834ca33120bd2a87d63e29ac5b93eb7c9
PiperOrigin-RevId: 764937930
--
cef3ca1ed3493eebaeab3e03bdf5e56b35c0b8ef by Lucas Nobre <lucaas.sn@gmail.com>:
feat: Add index tracking to handle parallel tool call using litellm
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/759 from lucasnobre212:fix/issue_484 65e22934bf839f9ea03963b9ec6c23fdce03f59f
PiperOrigin-RevId: 764902433
Copybara import of the project:
--
c62a0a6da4317497b991f83d4d8561bdbe7292aa by Jacky W <wjx_colstu@hotmail.com>:
--
59c0606ac08ddb45ce469a4d1e1c6e515ef94df4 by Jacky W <wjx_colstu@hotmail.com>:
fix: add cache_ok option to remove sa warning.
--
1922599075af935a63544762765d6f0e6224907a by Jacky W <wjx_colstu@hotmail.com>:
chore: format code.
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/1001 from Colstuwjx:fix/issue-480-precise-mysql-timestamp 50e764fb9646e326ad0204ff7adb2a5b65bf875a
PiperOrigin-RevId: 764853016
Previously if you add `from __future__ import annotations` in your code, the parsing code would fail because the type hints will be a string instead of the class itself (e.g. input: 'str' instead of input: str).
Also added "_" to the util file name.
PiperOrigin-RevId: 764817339
Copybara import of the project:
--
f56fd74efecc2cf6fbe6db70e91dfa7780fb9c68 by Mohammad <mohammaddevgermany@gmail.com>:
build(package): add py.typed and include it in flit config
This adds a py.typed marker file to the google.adk package and updates
the Flit configuration in pyproject.toml to include it in the distribution.
This ensures the package is PEP 561 compliant and allows static type
checkers (like mypy and pyright) to recognize that the package supports type hints.
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/913 from mohamadghaffari:add-py-typed f56fd74efecc2cf6fbe6db70e91dfa7780fb9c68
PiperOrigin-RevId: 764603119
Copybara import of the project:
--
79962881ca1c17eb6d7bd9dcf31a44df93c9badd by Almas Akchabayev <almas.akchabayev@gmail.com>:
fix: separate thinking from text parts in streaming mode
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/777 from almeynman:separate-thinking-and-text-parts-in-stream-mode b63dcc7fd0fc3973888dcbb9d4cc7e7e0a66e7f7
PiperOrigin-RevId: 764561932
--
bdb2ddff1336db7fbeae71d3d76b4d294d7c4bea by Arpit Roopchandani <17565234+whoisarpit@users.noreply.github.com>:
Fix: Set output_schema correctly for LiteLllm
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/580 from whoisarpit:fix/lite_llm_response_schema 08bdb5a993fc44adf03e985c820c2083de30ba58
PiperOrigin-RevId: 764524765
When the user id contains special characters (i.e. an email), we have added in extra url parsing to address those characters. We have also added an if statement to use the correct url when there is no user_id supplied.
Copybara import of the project:
--
ef8499001afaea40bd037c4e9946b883e23a5854 by Danny Park <dpark@calicolabs.com>:
--
773cd2b50d15b9b056b47b6155df492b0ca8034c by Danny Park <dpark@calicolabs.com>:
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/996 from dpark27:fix/list_vertex_ai_sessions d351d7f6017c03165129adc7d0212f21d1340d88
PiperOrigin-RevId: 764522026
Copybara import of the project:
--
824b4379d59a375191f8ce10997efd4021d5d0b3 by Andres Videla <andres.videla@trademe.co.nz>:
Adding regex for claude-4 models to anthropic_llm and updating tests
--
8fa2a2df1931026dc803eee0e9b60e82e90c9efa by Wei Sun (Jack) <Jacksunwei@gmail.com>:
Adds trailing comma.
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/934 from avidelatm:feature/add-support-for-claude-4-models-to-anthropic_llm 8d10bacdbec952ec9832180ac6c1d220916641da
PiperOrigin-RevId: 764396694
--
50b09bbe9735c889a9c815eddcee6715ebe848da by Yuan Chai <350365422@qq.com>:
fix: improve json serialization by allowing non-ascii characters
--
c66977ae6ec4edc71a2d633eb09918eb2a226461 by Yuan Chai <350365422@qq.com>:
fix: serialize function call arguments to JSON string
Previously accepted JSON objects directly, which was less robust. Now serialize arguments to JSON strings using `_safe_json_serialize`, ensuring stability and handling non-ASCII characters correctly.
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/605 from nauyiahc:fix_non_ascii_char a52513c5747296b717acee989684324e1b072d34
PiperOrigin-RevId: 764396496
Copybara import of the project:
--
bbd21e72e46227d5bbcaef6601f4a81724e7829f by Sanchit Rk <sanchitrrk@gmail.com>:
Fix: add missing kwargs to db session service
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/946 from sanchitrk:fix/missing-kwargs-db-session-service ebb699b04d8420ad14244cf3d43a2982b01d6b7f
PiperOrigin-RevId: 764392251
Copybara import of the project:
--
a6e3a220a507a27523e427e88a803f4fec40db9c by Alankrit Verma <alankrit386@gmail.com>:
test(base_llm_flow): add test for infinite loop on truncated responses
--
b5f2245788b8ed51189d1ad057372989452f070d by Alankrit Verma <alankrit386@gmail.com>:
feat(base_llm_flow): break run_async loop on partial/truncated events
--
cbbae4c468a4de3b5a737aef07cb4615f8418c38 by Wei Sun (Jack) <Jacksunwei@gmail.com>:
Raise ValueError if the last event is partial.
This is invalid state for llm flow.
--
6eebae0bc27c664eee4743ff7278ae5803415c9f by Wei Sun (Jack) <Jacksunwei@gmail.com>:
Delete tests/unittests/flows/llm_flows/test_base_llm_flow_truncation.py
--
e08b0ab19ca6eb88eb84f044bf72e815b2cf317c by Wei Sun (Jack) <Jacksunwei@gmail.com>:
format base_llm_flow.py
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/659 from AlankritVerma01:fix/522-base-llm-flow-truncation e08b0ab19ca6eb88eb84f044bf72e815b2cf317c
PiperOrigin-RevId: 764380150
