mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-09 10:18:32 +01:00
fix: preserve review continuity and native eval completion
This commit is contained in:
1 parent
02e6d4db57
commit
084f75297d
57 files changed
+3840
-254
No files matched your search
@@ -4,7 +4,7 @@ name: Periodic Evals
|
||||
# tests can't rot invisibly — the class where the autoplan-dual-voice E2E was
|
||||
# silently broken for months until a lucky local diff selected it. Engine:
|
||||
# scripts/test-paid-shards.ts (the same runner local eval:bg:periodic uses):
|
||||
# one planner manifest, 6 executor slices, and a FAIL-CLOSED report — a slice
|
||||
# one planner manifest, 6 ordinary slices plus dedicated Autoplan slice 7, and a FAIL-CLOSED report — a slice
|
||||
# whose artifact never landed is a failure, not an absence. The gate-census
|
||||
# job is the weekly EVALS_ALL backstop for the gate tier (PR lanes are
|
||||
# diff-billed, so without it the full gate census might never execute
|
||||
@@ -100,7 +100,7 @@ jobs:
|
||||
- name: Emit run manifest (ALL periodic tests minus reasoned excludes)
|
||||
env:
|
||||
EVALS_ALL: "1"
|
||||
run: EVALS_TIER=periodic bun run scripts/test-paid-shards.ts --tier periodic --emit-plan /tmp/paid-plan/manifest.json --slices 6
|
||||
run: EVALS_TIER=periodic bun run scripts/test-paid-shards.ts --tier periodic --emit-plan /tmp/paid-plan/manifest.json --slices 7 --autoplan-slice
|
||||
|
||||
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
|
||||
with:
|
||||
@@ -111,8 +111,9 @@ jobs:
|
||||
eval-slices:
|
||||
runs-on: ubicloud-standard-8
|
||||
needs: [build-image, plan-slices]
|
||||
# ~70 shards / 6 slices / EVALS_JOBS=2, 1800s shard wall — worst case is
|
||||
# bounded by ceil(12/2) x 30min; typical is far under.
|
||||
# Six ordinary slices retain their existing walls and concurrency. Slice 7
|
||||
# runs only Autoplan: its specified 172min two-attempt wall leaves 28min
|
||||
# for setup/upload. This is not a measured latency bound for ordinary work.
|
||||
timeout-minutes: 200
|
||||
permissions:
|
||||
contents: read
|
||||
@@ -126,7 +127,7 @@ jobs:
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
slice: [1, 2, 3, 4, 5, 6]
|
||||
slice: [1, 2, 3, 4, 5, 6, 7]
|
||||
steps:
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
|
||||
with:
|
||||
@@ -164,7 +165,7 @@ jobs:
|
||||
name: paid-plan
|
||||
path: /tmp/paid-plan
|
||||
|
||||
- name: Run slice ${{ matrix.slice }}/6
|
||||
- name: Run slice ${{ matrix.slice }}/7
|
||||
env:
|
||||
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
|
||||
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
|
||||
|
||||
Reference in new issue
Block a user