mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Jordan Ritter
94 lines
4.4 KiB
YAML
94 lines
4.4 KiB
YAML
# Probe: d6-all-pills-e2e (D6 -- "everything works" completeness)
|
|
#
|
|
# Drives a Playwright multi-turn conversation through EVERY demo cell
|
|
# for each showcase Railway service. Where e2e-deep (D5) picks ONE
|
|
# representative per feature type, this probe runs ALL cells.
|
|
#
|
|
# Rows emitted per driver invocation:
|
|
# - Primary `d6-all-pills-e2e:<name>` Aggregate ProbeResult.
|
|
# - Side `d6:<slug>` Green only if ALL cells pass.
|
|
# - Side `d6:<slug>/<demoId>` Per-cell diagnostic (not consumed
|
|
# by dashboard rollup).
|
|
#
|
|
# -- Cadence: hourly at :40 --
|
|
#
|
|
# :40 is offset off every other Playwright probe so none co-fire for the
|
|
# shared browser pool: e2e-smoke (`*/15` = :00/:15/:30/:45), e2e-demos (:10),
|
|
# and e2e-deep/D5 (:05/:20/:35/:50). With BROWSER_POOL_BROWSERS=3
|
|
# chromium processes and FEATURE_CONCURRENCY=4, the slowest round of the
|
|
# fan-out runs ~200s per service under CPU contention.
|
|
#
|
|
# -- timeout_ms: 1_200_000 (20 min) --
|
|
# -- max_concurrency: 5 --
|
|
#
|
|
# Fleet sizing: discovery now enumerates ~18 showcase demo services (NOT the
|
|
# legacy "8 services x 4 features" assumption this header carried before).
|
|
# With max_concurrency: 5, the fan-out runs in ceil(18/5) = 4 serialized
|
|
# rounds. Later rounds start late and execute under CPU contention, so each
|
|
# service's wall-clock stretches toward ~200s. The previous 600_000 (10 min)
|
|
# outer cap was sized for a single round; under multiple rounds the late
|
|
# rounds blew the per-service budget and ALL 18 services went red with
|
|
# `driver timeout after 600000ms`. The corrected 1_200_000 (20 min) cap fits
|
|
# 4 rounds x ~200s with comfortable headroom and matches the sibling
|
|
# 18-service `e2e-demos` probe (same fleet, same 20-min budget). The
|
|
# concurrency itself (5, lowered from 8) is justified in the OVERLAP block
|
|
# below — the round count here is just the budget-sizing consequence.
|
|
#
|
|
# -- Concurrency LOWERED 8 -> 5: cgroup pids.max=1000 ceiling, OVERLAP case --
|
|
#
|
|
# The PROVEN wedge is OS thread/PID exhaustion against the container cgroup
|
|
# `pids.max=1000` ceiling: each concurrent feature-worker drives a chromium
|
|
# renderer (~15 threads), and the live wedge peaked 998/1000 specifically
|
|
# during a d6+d5 OVERLAP — the simultaneous renderers of BOTH probes summed
|
|
# past the ceiling → pthread_create EAGAIN → "Target page ... has been closed"
|
|
# → crash-loop. Fewer concurrent d6 feature-workers cut the simultaneous-
|
|
# renderer thread peak, leaving headroom for a co-firing d5 (or a recovery
|
|
# relaunch) without crossing 1000. This is the complementary lever to
|
|
# BROWSER_POOL_MAX_CONTEXTS (already lowered 40 -> 24): max_concurrency caps
|
|
# the d6 fan-out width (the overlap-peak driver), the context cap bounds the
|
|
# global context/renderer count. 5 services x 4 features = 20 concurrent
|
|
# contexts, comfortably under the 24-context global cap with overlap room.
|
|
kind: e2e_d6
|
|
id: d6-all-pills-e2e
|
|
schedule: "40 * * * *"
|
|
timeout_ms: 1200000
|
|
max_concurrency: 5
|
|
discovery:
|
|
source: railway-services
|
|
filter:
|
|
namePrefix: "showcase-"
|
|
nameExcludes:
|
|
- showcase-aimock
|
|
- showcase-harness
|
|
- showcase-pocketbase
|
|
- showcase-shell
|
|
- showcase-shell-dashboard
|
|
- showcase-shell-docs
|
|
- showcase-shell-dojo
|
|
# Harness service for .NET integration testing — not a demo service,
|
|
# deployed: true in manifest, but NOT probe-wired yet: no aimock fixtures
|
|
# and it shares the ms-agent-dotnet AsyncLocal bug. Excluded from every
|
|
# probe AND not rendered on the dashboard (see baseline-types.ts) so an
|
|
# unprobed service never shows stale red. Remove this exclusion only once
|
|
# it is fully probe-wired (aimock fixtures + the AsyncLocal fix).
|
|
- showcase-ms-agent-harness-dotnet
|
|
# Decommissioned starters
|
|
- showcase-starter-ag2
|
|
- showcase-starter-agno
|
|
- showcase-starter-claude-sdk-python
|
|
- showcase-starter-claude-sdk-typescript
|
|
- showcase-starter-crewai-crews
|
|
- showcase-starter-google-adk
|
|
- showcase-starter-langgraph-fastapi
|
|
- showcase-starter-langgraph-python
|
|
- showcase-starter-langgraph-typescript
|
|
- showcase-starter-langroid
|
|
- showcase-starter-llamaindex
|
|
- showcase-starter-mastra
|
|
- showcase-starter-ms-agent-dotnet
|
|
- showcase-starter-ms-agent-python
|
|
- showcase-starter-pydantic-ai
|
|
- showcase-starter-spring-ai
|
|
- showcase-starter-strands
|
|
key_template: "d6-all-pills-e2e:${name}"
|