Simplify the ADK assistant context file:
- Replace the "ADK Knowledge, Architecture, and Style" section, which
enumerated each skill with its description (duplicating metadata already
surfaced to skill-aware assistants) and pointed at several skill paths
under .agents/skills/ that do not exist there, with a single pointer to
.agents/skills/.
- Remove the "AI Coding Assistant Context" title and its meta intro, which
added no actionable context.
- Move "Project Overview" to the top so the file leads with substance.
Co-authored-by: Haran Rajkumar <haranrk@google.com>
PiperOrigin-RevId: 936991617
Merge https://github.com/google/adk-python/pull/6107
## Summary
- Fix README claiming Python 3.11+ while the package requires `>=3.10`; sync all docs (README, AGENTS.md, adk-setup skill, two sample READMEs) to 3.10+
- Swap the rate-limited shields.io PyPI downloads badge for a pepy.tech one (the old badge rendered "rate limited by upstream service")
- Add a Python Unit Tests CI status badge
## Test plan
- [ ] Confirm README badges render correctly on GitHub (downloads + unit test status)
- [ ] Verify Python version wording matches `requires-python = ">=3.10"` in pyproject.toml
Co-authored-by: Wei Sun (Jack) <weisun@google.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/6107 from google:docs/readme-badges-python-310 bdfa1c125375abe94c343389702994cbc8857e7d
PiperOrigin-RevId: 931539712
Move pull request metadata verification, Google CLA checking, and diff analysis from adk-pr-triage into a dedicated adk-pr-analyze skill. This allows the CI system to run automated read-only checks on incoming pull requests without needing write permissions or manual intervention.
Change-Id: I1b7961eaeee5e26df10396d3439127da08fd320c
Enables issue analysis workflow to trigger on comments posted to pull requests. This is done by removing the `!github.event.issue.pull_request` check from the GHA issue analysis workflow definition, since GitHub models PR comments under the `issue_comment` event. The fix implementation workflow remains restricted to issues to prevent PR-on-PR loops and permission issues.
- Update scripts/run_antigravity.py to include comments and review comments in JSON payloads fetched by helper tools.
- Update adk-issue and adk-issue-analyze skills to prevent routing conflicts when /adk-issue-analyze is explicitly requested.
- Update branch validation in issue-fix workflow to fail if the agent does not successfully create and checkout fix/issue-<number>.
- Update adk-issue-fix skill branch template to match expected GHA workflow fallback pattern.
Change-Id: I34405266bb6b11cc4ad18878ef932bb46677c89d
Introduce the adk-pr-triage skill and its supporting triage_pr.py helper
script to guide AI coding assistants through conducting rigorous and
automated triage of GitHub pull requests.
The workflow script handles compliance verification, validates that the
contributor's Google CLA signature status check run is SUCCESS, fetches
remote branches, and automates PR updates via server-side rebase before local checkout.
Provides an interactive 'Local Review' option that integrates branch checkout,
preserves original PR commit metadata, and triggers /adk-review for rigorous
quality control before squashing and pushing changes to Gerrit.
Change-Id: If311b90b185636f4f737aa04a3c50a4a460b94db
Introduce the adk-review skill to guide AI assistants through a comprehensive, multi-dimensional review of local repository changes (correctness, style, architecture, docs, samples, and tests) before they are committed.
Also includes detailed defensive programming and edge-case verification rules in the review checklist.
Change-Id: Iadc0cd5f2a4ed778d95541ac5cf412e7feb12a26
This can fix unit test github action error by removing `--extra eval`. `--extra a2a` is not needed because it's included in `test`. All tests are still passing.
Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 869014318
Merge https://github.com/google/adk-python/pull/4175
### Link to Issue or Description of Change
**1. Link to an existing issue (if applicable):**
N/A: just fixing typos discovered while reading the repo
**2. Or, if no issue exists, describe the change:**
No code change, just typo fixes: see commit diffs for all details
**Problem:**
Trying to improve overall repo quality
**Solution:**
Fixing typos as they get discovered
### Testing Plan
N/A
**Unit Tests:**
N/A
**Manual End-to-End (E2E) Tests:**
N/A
### Checklist
- [X] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [X] I have performed a self-review of my own code.
- [ ] I have commented my code, particularly in hard-to-understand areas.
- [ ] I have added tests that prove my fix is effective or that my feature works.
- [X] New and existing unit tests pass locally with my changes.
- [ ] I have manually tested my changes end-to-end.
- [ ] Any dependent changes have been merged and published in downstream modules.
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/4175 from didier-durand:fix-typos-c 16e93ed2d9bc153fa0332ab1ae39633fcc5056e9
PiperOrigin-RevId: 858751240
Fixes https://github.com/google/adk-python/issues/3174
The event compaction process, configured via `EventsCompactionConfig`, was
previously scheduled as a background task using `asyncio.create_task`.
Because Python's `asyncio.create_task` only holds a weak reference to
the created task and no strong reference was maintained by ADK, the
compaction task could be garbage-collected before it finished executing.
This resulted in event compaction failing silently or only partially
running, preventing session history from being summarized.
### Approaches Considered
Two approaches were considered to fix this:
1. **`asyncio.create_task` + Reference:** Create the task with `create_task` and store a strong reference to it (e.g., in a `set` on the [Runner](http://_vscodecontentref_/0) instance), removing it only when complete via `task.add_done_callback()`.
* **Pros:** The [run_async](http://_vscodecontentref_/1) async generator finishes immediately after yielding the last agent event.
* **Cons:** Adds complexity to the Runner state; background task failures are silent to the [run_async](http://_vscodecontentref_/2) caller; requires enhancement to `runner.close()` to correctly manage pending tasks on shutdown.
2. **`await`:** Directly `await` the compaction coroutine at the end of [run_async](http://_vscodecontentref_/3) after all agent events have been yielded.
* **Pros:** Simple to implement; ensures compaction runs to completion; failures during compaction propagate immediately to the [run_async](http://_vscodecontentref_/4) caller, making them visible and easier to debug.
* **Cons:** The `async for` loop iterating over [run_async](http://_vscodecontentref_/5) will not terminate until compaction finishes.
### Decision
This change implements the `await` approach. Although it means the `async for` loop takes longer to terminate when compaction occurs, it was chosen for its **simplicity and robustness**. Ensuring that compaction either succeeds or fails visibly is preferable to silent background failures.
All agent response events are yielded *before* compaction starts, so there is **no user-perceived delay in receiving the agent's answer** for the current turn.
### Integration Note for Users
Because compaction is now awaited, code consuming events via `async for event in runner.run_async(...)` will only finish iterating *after* compaction is complete (if compaction is triggered for that invocation).
If your application only needs the agent's response to proceed (e.g., displaying a message in a UI and allowing the user to reply), you can process events as they arrive and initiate the next turn without waiting for the `async for` loop to fully terminate. A new call to [run_async](http://_vscodecontentref_/6) for the next user query can be made immediately and will execute concurrently.
**Example:**
```python
async def handle_agent_turn(runner, message):
print("Agent is thinking...")
async for event in runner.run_async(user_id='...', session_id='...', new_message=message):
# Stream events to UI, log, etc.
if event.author == 'model' and event.content and event.content.parts[0].text:
print(f"Agent response: {event.content.parts[0].text}")
# The agent has provided a text response.
# The application can now enable user input for the next turn,
# even though this async for loop might not finish immediately
# if compaction is running.
print("Invocation complete (including compaction if any).")
# In your application:
# A new call to handle_agent_turn(runner, next_message) can be made
# as soon as the user provides the next input, without waiting for
# the previous call's generator to be exhausted.
Co-authored-by: Hangfei Lin <hangfei@google.com>
PiperOrigin-RevId: 833885375
Usage: you can create symlink to AGENTS.md with the file name required by the specific AI coding tool.
Co-authored-by: Wei Sun (Jack) <weisun@google.com>
PiperOrigin-RevId: 825627185
This explains the high-level architecture and philosophy of the ADK project.
It can also be feed into LLMs for vibe-coding.
PiperOrigin-RevId: 780178125
Adds a description for docstring and comments in the AGENTS.md and adds a section for Versioning that describes how ADK follows Semantic Versioning 2.0.0
PiperOrigin-RevId: 778667398
Haran Rajkumar