CalvinBackup/gstack
1
0 Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-10-03 01:46:55 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/test-audit-reduction' into capy/audit-fix-wave

Browse Source
This commit is contained in:
garrytan committed 2026-09-29 15:09:14 +00:00
2 parents a11b651827 94e4b0fbf0
commit 44177fffc6
666 files changed
+11963 -102378
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.github/workflows/evals-periodic.yml
+10 -10
View File
@@ -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, 7 ordinary slices plus overlay and Autoplan slices, and a FAIL-CLOSED report — a slice
# one planner manifest, 6 ordinary slices plus an overlay slice, 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
@@ -96,7 +96,7 @@ jobs:
- name: Emit run manifest (ALL periodic tests minus reasoned excludes)
env:
EVALS_ALL: "1"
run: EVALS_TIER=periodic bun --no-install run scripts/test-paid-shards.ts --tier periodic --emit-plan /tmp/paid-plan/manifest.json --slices 9 --autoplan-slice
run: EVALS_TIER=periodic bun --no-install run scripts/test-paid-shards.ts --tier periodic --emit-plan /tmp/paid-plan/manifest.json --slices 7
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
with:
@@ -107,7 +107,7 @@ jobs:
- name: Emit gate census manifest (ALL gate tests)
env:
EVALS_ALL: "1"
run: EVALS_TIER=gate bun run scripts/test-paid-shards.ts --tier gate --emit-plan /tmp/gate-census-plan/manifest.json --slices 8
run: EVALS_TIER=gate bun run scripts/test-paid-shards.ts --tier gate --emit-plan /tmp/gate-census-plan/manifest.json --slices 7 --skip-judges
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
with:
@@ -120,8 +120,8 @@ jobs:
needs: [build-image, plan-slices]
env:
EVALS_RUN_ID: ci-${{ github.run_id }}-${{ github.run_attempt }}-eval-slices-${{ matrix.slice }}
# Nine slices retain every registered case and retry. The complete
# census needs at most 292m20 per slice, plus 20 minutes setup/upload.
# Seven slices retain every registered case and retry. The complete
# census needs at most 244m40s per slice, plus 20 minutes setup/upload.
timeout-minutes: 360
permissions:
contents: read
@@ -136,7 +136,7 @@ jobs:
fail-fast: false
max-parallel: 8
matrix:
slice: [1, 2, 3, 4, 5, 6, 7, 8, 9]
slice: [1, 2, 3, 4, 5, 6, 7]
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
@@ -174,7 +174,7 @@ jobs:
name: paid-plan
path: /tmp/paid-plan
- name: Run slice ${{ matrix.slice }}/9
- name: Run slice ${{ matrix.slice }}/7
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -231,7 +231,7 @@ jobs:
needs: [build-image, plan-slices]
env:
EVALS_RUN_ID: ci-${{ github.run_id }}-${{ github.run_attempt }}-gate-census-${{ matrix.slice }}
# Eight slices need at most 302m each, plus 20 minutes setup/upload.
# Seven slices need at most 272m each, plus 20 minutes setup/upload.
timeout-minutes: 352
permissions:
contents: read
@@ -247,7 +247,7 @@ jobs:
fail-fast: false
max-parallel: 4
matrix:
slice: [1, 2, 3, 4, 5, 6, 7, 8]
slice: [1, 2, 3, 4, 5, 6, 7]
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
@@ -272,7 +272,7 @@ jobs:
name: gate-census-plan
path: /tmp/gate-census-plan
- name: Run gate census slice ${{ matrix.slice }}/8
- name: Run gate census slice ${{ matrix.slice }}/7
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}