feat(clients): google foundation for the agent platform: all-verb client, streaming, typed Gemini content, operations

GoogleClient gets every verb and stream_json (SSE and plain JSON), typed
Content/Part/Tool/GenerateRequest with the LanguageModel seam, CloudContext
resource names, long-running operation polling and pagination, OAuth bearer
tokens via GOOGLE_ACCESS_TOKEN. Example scaffold: one stub per agent module
under example/app/agent, wildcard builds, locust excludes /voice /google
/agent. plans/16-agent-platform.md splits the work into nine modules.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-24 04:12:52 +02:00
co-authored by Claude Sonnet 5.5
parent 837de58136
commit 6d744a433f
32 changed files with 1536 additions and 22 deletions
+2 -3
View File
@@ -39,7 +39,6 @@ GETS = [
"/csp/page", "/csp/report",
"/di/services", "/di/resolve/locust",
"/embedded/chart.umd.min.js", "/embedded/hello.txt", "/embedded/stats.js",
"/embedded/voice.js", "/google/status", "/voice",
"/events/fire", "/expose/record", "/expose/stats",
"/files/", "/files/welcome.txt",
"/flash", "/flash/set",
@@ -88,8 +87,8 @@ GETS = [
"/webdav/files/test.txt",
]
# NOT load tested on purpose: /voice/say, /voice/hear, /voice/turn and
# /voice/reset call paid Google APIs (check_locust_coverage.py enforces this).
# NOT load tested on purpose: everything under /voice, /google and /agent
# calls or fronts paid Google APIs (check_locust_coverage.py enforces this).
POSTS = [
("/audit/log", {"event": "locust"}),
("/audit/retention/hold", {"hold": True}),