Merge https://github.com/google/adk-python/pull/2109Fixes#2105
## Problem
When integrating Google ADK with Langfuse using the @observe
decorator, the usage details displayed in Langfuse web UI were
incorrect.
The root cause was in the telemetry implementation where
total_token_count was being mapped to gen_ai.usage.output_tokens
instead of candidates_token_count.
- Expected mapping:
- candidates_token_count → completion_tokens (output tokens)
- prompt_token_count → prompt_tokens (input tokens)
- Previous incorrect mapping:
- total_token_count → completion_tokens (wrong!)
- prompt_token_count → prompt_tokens (correct)
## Solution
Updated trace_call_llm function in telemetry.py to use
candidates_token_count for output token tracking instead of
total_token_count, ensuring proper token count reporting to
observability tools like Langfuse.
## Testing plan
- Updated test expectations in test_telemetry.py
- Verified telemetry tests pass
- Manual verification with Langfuse integration
## Screenshots
**Before**
<img width="1187" height="329" alt="Screenshot from 2025-07-22 20-20-33" src="https://github.com/user-attachments/assets/ad5fc957-64a2-4524-bd31-0cebb15a5270" />
**After**
<img width="1187" height="329" alt="Screenshot from 2025-07-22 20-21-40" src="https://github.com/user-attachments/assets/3920df2a-be75-47e0-9bd0-f961bb72c838" />
_Notes_: From the screenshot, there's another problem: thoughts_token_count field is not mapped, but this should be another issue imo
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/2109 from tl-nguyen:fix-telemetry-token-count-mapping 3d043f558b5f8bcb2c6e0370e2cc4c0ff25d1f4a
PiperOrigin-RevId: 786827802
This commit adds support for the session resumption configuration in the run_config.
The SessionResumptionConfig is added to RunConfig to allow the user to set up a configuration for session resumption(only transparent mode for now).
There are two modes of session resumption: manual and transparent. In manual mode, you have to manually bookkeeping the session information and restarts the session which is tricky to do right now. In transparent mode, the server does the bookkeeping for you and no hassle on ADK side. For now, the transparent mode should be enough.
Also, added the relevant unit tests to check that every possible configuration is set properly and the run_config is correctly populated.
This is needed for supporting the new session resumption feature.
PiperOrigin-RevId: 786549455
This CL add new callbacks in plugin system:
- `on_tool_error_callback`
- `on_model_error_callback`
This allow the user to create plugins that can handle errors.
PiperOrigin-RevId: 786469646
Mainly it's due to GenAI sdk changed their header of genai SDK versions, we have UT to verify that ADK or ADK users won't override their headers. Updated the header accordingly in the UT.
PiperOrigin-RevId: 786334741
Merge https://github.com/google/adk-python/pull/1959
### What
Fix misleading comment.
```diff
- # Make sure a malicious user can obtain a session and events not belonging to them
+ # Make sure a malicious user **cannot** obtain a session or events not belonging to them
```
### Why
The previous wording contradicted the assertion `assert len(session_mismatch.events) == 0`, which verifies that a malicious user **cannot** access another user’s session or events.
### Testing plan
Docs-only change.
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/1959 from mthorme:fix-comment-session-mismatch b1f139af340bd240d40ed58f5dea3274c3a3bd83
PiperOrigin-RevId: 785908548
This change takes cares of SQL results containing values that are not json serializable (e.g. datetime, bignumeric) by converting them to their string representation.
PiperOrigin-RevId: 785719997
We update both adk web run eval endpoint and adk eval cli to use the LocalService. The old method is marked as deprecated and will be removed in later PRs.
PiperOrigin-RevId: 785612708
Fixes#423
Related to #1670
- This avoids the `GeneratorExit` error thrown, which would crash OTel metric collection and cause `Failed to detach context` error.
- This also allows all function calls are processed when exit_loop is called together with other tools in the same LLmResponse.
A sample agent for testing:
```
from google.adk import Agent
from google.adk.agents.loop_agent import LoopAgent
from google.adk.tools.exit_loop_tool import exit_loop
worker_1 = Agent(
name='worker_1',
description='Worker 1',
instruction="""\
Just say job #1 is done.
If job #1 is said to be done. Call exit_loop tool.""",
tools=[exit_loop],
)
worker_2 = Agent(
name='worker_2',
description='Worker 2',
instruction="""\
Just say job #2 is done.
If job #2 is said to be done. Call exit_loop tool.""",
tools=[exit_loop],
)
work_agent = LoopAgent(
name='work_agent',
description='Do all work.',
sub_agents=[worker_1, worker_2],
max_iterations=5,
)
root_agent = Agent(
model='gemini-2.0-flash',
name='hello_world_agent',
description='hello world agent that can roll a check prime',
instruction="""Hand off works to sub agents.""",
sub_agents=[work_agent],
)
```
PiperOrigin-RevId: 785538101
Merge https://github.com/google/adk-python/pull/1130
This enables the use of the `model-optimizer-*` family of models in vertex, as per the [documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/vertex-ai-model-optimizer#using-vertex-ai-model-optimizer).
To use this, ensure your location is set to `global` and pass a model optimizer model to an agent:
```python
root_agent = Agent(
model="model-optimizer-exp-04-09",
name="fast_and_slow_agent",
instruction="Answer any question the user gives you - easy or hard.",
generate_content_config=types.GenerateContentConfig(
temperature=0.01,
model_selection_config=ModelSelectionConfig(
feature_selection_preference=FeatureSelectionPreference.BALANCED
# Options: PRIORITIZE_QUALITY, BALANCED, PRIORITIZE_COST
)
),
)
```
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/1130 from calvingiles:feat-model-optimizer 1a76bfa22420edb07d83415dcea6dd0114084e8e
PiperOrigin-RevId: 784921913
Now the LangchainTool can wrap:
* Langchain StructuredTool (sync and async).
* Langchain @Tool (sync and async).
This enhance the flexibility for user and enables async functionalities.
PiperOrigin-RevId: 784728061
