George WealeandCopybara-Service b30c2f4e13 fix: avoid local .adk storage in Cloud Run/GKE ...

Default session and artifact services to in-memory when running in Cloud Run/Kubernetes (or when agents_dir isn’t writable) to prevent startup failures from attempting to create .adk under read-only/unwritable container paths (e.g. /app/agents/.adk). Local development defaults are unchanged.

  - ADK_FORCE_LOCAL_STORAGE=1 to always use .adk defaults
  - ADK_DISABLE_LOCAL_STORAGE=1 to always avoid local storage

If local artifact initialization raises PermissionError, fall back to in-memory and log a warning

Close #3907

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 853315459

2026-01-07 10:18:11 -08:00

..

a2a

feat: Update event_converter used in A2ARemote agent to use a2a_task.status.message only if parts are non-empty

2025-12-18 14:23:27 -08:00

agents

chore: Add docstring for StreamingMode

2026-01-07 00:15:12 -08:00

apps

docs: too many E(inv=2, role=user) plus reformatting

2025-11-21 13:49:01 -08:00

artifacts

fix: Add a FastAPI endpoint for saving artifacts

2025-12-01 16:29:18 -08:00

auth

fix: Remove fallback to cached exchanged credential in _load_existing_credential

2026-01-06 14:50:05 -08:00

cli

fix: avoid local .adk storage in Cloud Run/GKE

2026-01-07 10:18:11 -08:00

code_executors

feat: Capture thinking output, forward raw payloads, and fix exec locals

2025-11-20 16:30:19 -08:00

dependencies

chore: Update vertex ai in example store and rag retrieval to use proxy

2025-10-28 15:46:38 -07:00

errors

fix: Add a FastAPI endpoint for saving artifacts

2025-12-01 16:29:18 -08:00

evaluation

fix: Fix double JSON encoding when saving eval set results

2026-01-05 14:26:05 -08:00

events

chore: Clarify the usage of agent_state

2025-11-05 19:30:58 -08:00

examples

chore: Lazy load Vertex AI dependencies in ADK modules

2025-11-06 10:40:54 -08:00

features

feat: Enable PROGRESSIVE_SSE_STREAMING feature by default

2025-12-19 10:50:49 -08:00

flows

feat: make LlmAgent.model optional with a default fallback

2026-01-06 17:56:14 -08:00

memory

chore: Add warning for full resource path in VertexAiMemoryBankService agent_engine_id

2025-12-01 10:51:47 -08:00

models

fix: Filter out thought parts in lite_llm._get_content

2026-01-06 15:44:33 -08:00

planners

No public description

2025-04-19 16:34:44 -07:00

platform

refactor: Extract out platform specific code like threading

2025-06-10 09:05:56 -07:00

plugins

fix: make the BigQuery analytics plugin work with agents that don't have instructions such as the LoopAgent

2026-01-05 11:21:25 -08:00

sessions

feat: Add database schema migration command and script

2026-01-06 16:36:45 -08:00

telemetry

fix: use mode='json' in model_dump to serialize bytes correctly when using telemetry

2026-01-07 07:38:18 -08:00

tools

fix: Add schema type sanitization to OpenAPI spec parser

2026-01-06 16:47:06 -08:00

utils

feat: Mark Vertex calls made from non-gemini models

2025-12-23 06:50:46 -08:00

__init__.py

Agent Development Kit(ADK)

2025-04-08 17:25:47 +00:00

py.typed

ADK changes

2025-05-29 12:10:41 -07:00

runners.py

chore: Clean up the invocation context initialization logic for LIVE

2026-01-07 08:31:01 -08:00

version.py

chore: Bumps version to v1.21.0 and updates CHANGELOG.md

2025-12-11 16:54:08 -08:00