mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-02 17:40:02 +02:00
Merge origin/main (v1.91.7.0) into test-audit-reduction
Keep both intents: v1.91.7.0's functional QA, docsync and exploratory paid cases and their free owners stay; this branch's deletions stay deleted. main's new paid keys follow the derived-closure touchfile rule (free *.test.ts paths dropped, static helper/fixture closure added), its new helper-only tests join the ratchet baseline, and its free selection examples that named free test files now assert the derived selection. Periodic CI keeps seven slices without the retired Autoplan slice; the gate census keeps seven single-worker slices with --skip-judges. Wall and census literals are recomputed from the merged planner, durations are re-recorded on Ubicloud, and VERSION stays 1.91.8.0 above 1.91.7.0.
This commit is contained in:
garrytan committed
commit
b421bba2c9
325 files changed
+42569
-8257
No files matched your search
@@ -118,9 +118,11 @@ jobs:
|
||||
eval-slices:
|
||||
runs-on: ubicloud-standard-8
|
||||
needs: [build-image, plan-slices]
|
||||
env:
|
||||
EVALS_RUN_ID: ci-${{ github.run_id }}-${{ github.run_attempt }}-eval-slices-${{ matrix.slice }}
|
||||
# Seven slices retain every registered case and retry. The complete
|
||||
# census needs at most 251 minutes per slice, plus 20 minutes setup/upload.
|
||||
timeout-minutes: 358
|
||||
# census needs at most 244m40s per slice, plus 20 minutes setup/upload.
|
||||
timeout-minutes: 360
|
||||
permissions:
|
||||
contents: read
|
||||
packages: read
|
||||
@@ -132,6 +134,7 @@ jobs:
|
||||
options: --user runner
|
||||
strategy:
|
||||
fail-fast: false
|
||||
max-parallel: 8
|
||||
matrix:
|
||||
slice: [1, 2, 3, 4, 5, 6, 7]
|
||||
steps:
|
||||
@@ -190,6 +193,20 @@ jobs:
|
||||
path: /tmp/paid-slice-results
|
||||
retention-days: 90
|
||||
|
||||
- name: Upload native capture evidence
|
||||
if: always()
|
||||
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
|
||||
with:
|
||||
name: native-captures-${{ env.EVALS_RUN_ID }}
|
||||
include-hidden-files: true
|
||||
path: |
|
||||
~/.gstack/projects/*/e2e-runs
|
||||
~/.gstack/projects/*/evals/qa-callers
|
||||
~/.gstack-dev/e2e-runs
|
||||
~/.gstack-dev/evals/qa-callers
|
||||
if-no-files-found: ignore
|
||||
retention-days: 90
|
||||
|
||||
- name: Upload shard logs on failure
|
||||
if: failure()
|
||||
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
|
||||
@@ -212,7 +229,9 @@ jobs:
|
||||
gate-census:
|
||||
runs-on: ubicloud-standard-8
|
||||
needs: [build-image, plan-slices]
|
||||
# Seven slices need at most 304m each, plus 20 minutes setup/upload.
|
||||
env:
|
||||
EVALS_RUN_ID: ci-${{ github.run_id }}-${{ github.run_attempt }}-gate-census-${{ matrix.slice }}
|
||||
# Seven slices need at most 272m each, plus 20 minutes setup/upload.
|
||||
timeout-minutes: 352
|
||||
permissions:
|
||||
contents: read
|
||||
@@ -272,6 +291,20 @@ jobs:
|
||||
path: /tmp/gate-census-results
|
||||
retention-days: 90
|
||||
|
||||
- name: Upload native capture evidence
|
||||
if: always()
|
||||
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
|
||||
with:
|
||||
name: native-captures-${{ env.EVALS_RUN_ID }}
|
||||
include-hidden-files: true
|
||||
path: |
|
||||
~/.gstack/projects/*/e2e-runs
|
||||
~/.gstack/projects/*/evals/qa-callers
|
||||
~/.gstack-dev/e2e-runs
|
||||
~/.gstack-dev/evals/qa-callers
|
||||
if-no-files-found: ignore
|
||||
retention-days: 90
|
||||
|
||||
report:
|
||||
runs-on: ubicloud-standard-2
|
||||
needs: [plan-slices, eval-slices, gate-census]
|
||||
|
||||
@@ -141,7 +141,7 @@ jobs:
|
||||
if: github.event_name != 'workflow_dispatch' || inputs.validation_phase == 'all'
|
||||
env:
|
||||
EVALS_ALL: ${{ (github.event_name == 'workflow_dispatch' && inputs.evals_all) && '1' || '' }}
|
||||
run: EVALS_TIER=gate bun --no-install run scripts/test-paid-shards.ts --tier gate --emit-plan /tmp/paid-plan/manifest.json --slices 6
|
||||
run: EVALS_TIER=gate bun --no-install run scripts/test-paid-shards.ts --tier gate --emit-plan /tmp/paid-plan/manifest.json --slices 7
|
||||
|
||||
- name: Emit validation-phase manifest
|
||||
if: github.event_name == 'workflow_dispatch' && inputs.validation_phase != 'all'
|
||||
@@ -178,6 +178,8 @@ jobs:
|
||||
eval-slices:
|
||||
runs-on: ubicloud-standard-8
|
||||
needs: [build-image, plan-slices]
|
||||
env:
|
||||
EVALS_RUN_ID: ci-${{ github.run_id }}-${{ github.run_attempt }}-eval-slices-${{ matrix.slice }}
|
||||
# !cancelled(), not always(): still runs when build-image was skipped
|
||||
# (image already published), but a newer push's cancel-in-progress stops
|
||||
# it instead of letting a superseded run finish its paid slices first.
|
||||
@@ -187,9 +189,9 @@ jobs:
|
||||
# 40-way per row queued claude session STARTUP behind 39 siblings and ate
|
||||
# per-test budgets — the documented timeout-flake family). Tune with
|
||||
# parity data before raising.
|
||||
# The complete gate census needs at most 236 minutes per slice; keep
|
||||
# The complete gate census needs at most 242 minutes per slice; keep
|
||||
# 20 minutes for setup/upload without preempting configured retries.
|
||||
timeout-minutes: 256
|
||||
timeout-minutes: 265
|
||||
permissions:
|
||||
contents: read
|
||||
packages: read
|
||||
@@ -201,8 +203,9 @@ jobs:
|
||||
options: --user runner
|
||||
strategy:
|
||||
fail-fast: false
|
||||
max-parallel: 6
|
||||
matrix:
|
||||
slice: [1, 2, 3, 4, 5, 6]
|
||||
slice: [1, 2, 3, 4, 5, 6, 7]
|
||||
steps:
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
|
||||
with:
|
||||
@@ -251,7 +254,7 @@ jobs:
|
||||
key: eval-input-v1-${{ github.repository_id }}-pr-${{ github.event.pull_request.number }}-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.slice }}
|
||||
restore-keys: eval-input-v1-${{ github.repository_id }}-pr-${{ github.event.pull_request.number }}-
|
||||
|
||||
- name: Run slice ${{ matrix.slice }}/6
|
||||
- name: Run slice ${{ matrix.slice }}/7
|
||||
env:
|
||||
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
|
||||
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
|
||||
@@ -297,6 +300,20 @@ jobs:
|
||||
path: /tmp/paid-slice-results
|
||||
retention-days: 90
|
||||
|
||||
- name: Upload native capture evidence
|
||||
if: always()
|
||||
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
|
||||
with:
|
||||
name: native-captures-${{ env.EVALS_RUN_ID }}
|
||||
include-hidden-files: true
|
||||
path: |
|
||||
~/.gstack/projects/*/e2e-runs
|
||||
~/.gstack/projects/*/evals/qa-callers
|
||||
~/.gstack-dev/e2e-runs
|
||||
~/.gstack-dev/evals/qa-callers
|
||||
if-no-files-found: ignore
|
||||
retention-days: 90
|
||||
|
||||
# The spooled per-shard full logs — a red weekly/PR lane three weeks
|
||||
# later needs more than a summary line.
|
||||
- name: Upload shard logs on failure
|
||||
|
||||
@@ -295,7 +295,8 @@ jobs:
|
||||
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
|
||||
with:
|
||||
name: free-test-shard-logs-${{ matrix.shard }}
|
||||
path: /tmp/gstack-free-test-*.log
|
||||
path: .context/free-test-logs/gstack-free-test-*.log
|
||||
include-hidden-files: true
|
||||
if-no-files-found: ignore
|
||||
|
||||
# Branch protection already requires the `free-tests` context. Keep that
|
||||
|
||||
@@ -153,8 +153,6 @@ jobs:
|
||||
# the ledger uploaded below, so repeats stay visible and ranked.
|
||||
GSTACK_FREE_RETRY_FLAKY: '1'
|
||||
GSTACK_FLAKE_LEDGER: ${{ runner.temp }}/flake-ledger.jsonl
|
||||
# Point os.tmpdir() at the runner temp so the shard logs land
|
||||
# somewhere the artifact step below can glob.
|
||||
TEMP: ${{ runner.temp }}
|
||||
TMP: ${{ runner.temp }}
|
||||
run: bun run test:windows
|
||||
@@ -180,7 +178,10 @@ jobs:
|
||||
uses: actions/upload-artifact@v7
|
||||
with:
|
||||
name: windows-free-test-shard-logs
|
||||
path: ${{ runner.temp }}/gstack-free-test-*.log
|
||||
path: |
|
||||
.context/free-test-logs/gstack-free-test-*.log
|
||||
${{ runner.temp }}/gstack-free-test-*.log
|
||||
include-hidden-files: true
|
||||
if-no-files-found: ignore
|
||||
|
||||
- name: Upload flake ledger
|
||||
|
||||
Reference in new issue
Block a user