CalvinBackup/gstack
1
0 Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-11-05 08:23:59 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main' into capy/tm3-rebaseline

Browse Source 
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

# Conflicts:
#	CHANGELOG.md
This commit is contained in:
garrytan committed 2026-10-19 18:29:55 +00:00
2 parents 75e5799cf2 9cf105ccff
commit 29da497e9f
39 files changed
+3591 -2261
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.github/workflows/evals-periodic.yml
+131 -40
View File
@@ -15,6 +15,10 @@ name: Periodic Evals
# diff-billed, so without it the full gate census might never execute
# anywhere); the hollow-shard guard (exit 0 + zero executed tests under
# EVALS_ALL fails) makes both lanes census-health checks, not just test runs.
# The gate census is a matrix of arms (scripts/census-arms.ts): each arm is a
# host and model with its own plan. Monday runs claude-opus (the capture
# model) and codex-sol (gpt-6.1-sol on the Codex host, adapter cases only);
# the monthly cron runs only the census, with claude-fable and codex-astra.
# eval-bg (scripts/eval-bg.ts) finds its dispatch by the nonce in the run name.
run-name: ${{ inputs.nonce && format('Periodic Evals [eval-bg {0}]', inputs.nonce) || 'Periodic Evals' }}
on:
@@ -23,6 +27,9 @@ on:
# Daily, for autoplan-schema-canary alone (latest Claude Code vs the /autoplan
# guard's payload assumptions); every census job below skips this schedule.
- cron: '30 7 * * *'
# Monthly, the census jobs alone with the claude-fable and codex-astra arms
# (the 1st; never combined with a day of week, which cron would OR).
- cron: '0 6 1 * *'
workflow_dispatch:
inputs:
redispatch_of:
@@ -30,9 +37,13 @@ on:
type: string
default: ''
include_gate_census:
description: 'Branch dispatch only: also run the weekly gate census (default: periodic lane only; gate cases validate through an evals.yml dispatch with evals_all)'
description: 'Branch dispatch only: also run the weekly gate census arms (default: periodic lane only; gate cases validate through an evals.yml dispatch with evals_all)'
type: boolean
default: false
census_arms:
description: 'Run only the gate census, with these arms (comma-separated: claude-opus, codex-sol, claude-fable, codex-astra; scripts/census-arms.ts). Empty keeps the periodic lane.'
type: string
default: ''
expected_sha:
description: 'eval-bg: the revision the dispatcher tested; the run fails fast when the ref has moved'
type: string
@@ -51,7 +62,7 @@ on:
# runs in its own group so it never cancels the run that dispatched it; both
# runs are reported.
concurrency:
group: evals-periodic-${{ github.ref }}-${{ github.event_name }}${{ inputs.redispatch_of && format('-redispatch-{0}', inputs.redispatch_of) || '' }}${{ (github.event.schedule == '30 7 * * *' || inputs.schema_canary_only) && '-schema-canary' || '' }}
group: evals-periodic-${{ github.ref }}-${{ github.event_name }}${{ inputs.redispatch_of && format('-redispatch-{0}', inputs.redispatch_of) || '' }}${{ (github.event.schedule == '30 7 * * *' || inputs.schema_canary_only) && '-schema-canary' || '' }}${{ github.event.schedule == '0 6 1 * *' && '-monthly' || '' }}
cancel-in-progress: true
env:
@@ -126,8 +137,9 @@ jobs:
periodic_slices: ${{ steps.periodic-matrix.outputs.slices }}
periodic_codex_slices: ${{ steps.periodic-matrix.outputs.codex_slices }}
periodic_slice_timeouts: ${{ steps.periodic-matrix.outputs.slice_timeouts }}
gate_slices: ${{ steps.gate-matrix.outputs.slices }}
gate_slice_timeouts: ${{ steps.gate-matrix.outputs.slice_timeouts }}
periodic_lane: ${{ steps.census.outputs.periodic_lane }}
census_arms: ${{ steps.census.outputs.arms }}
gate_matrix: ${{ steps.gate-matrix.outputs.gate_matrix }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
@@ -147,7 +159,18 @@ jobs:
with:
bun-version: 1.4.2
# Census arms (scripts/census-arms.ts): which host/model arms run the
# gate census, and whether the periodic lane runs beside them.
- name: Select the census arms
id: census
env:
SCHEDULE: ${{ github.event.schedule }}
CENSUS_ARMS: ${{ inputs.census_arms }}
INCLUDE_GATE_CENSUS: ${{ github.ref == 'refs/heads/main' || inputs.include_gate_census }}
run: bun --no-install run scripts/census-arms.ts --select >> "$GITHUB_OUTPUT"
- name: Emit run manifest (ALL periodic tests minus reasoned excludes)
if: steps.census.outputs.periodic_lane == 'true'
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 --slice-budget 420 --jobs 2 --max-parallel 38
@@ -156,6 +179,7 @@ jobs:
# container executor runs every other slice.
- name: Derive the periodic executor matrix from the plan
id: periodic-matrix
if: steps.census.outputs.periodic_lane == 'true'
run: |
{
echo "slices=$(jq -c '[range(1; .sliceCount + 1)] - .plan.codexSlices' /tmp/paid-plan/manifest.json)"
@@ -164,26 +188,38 @@ jobs:
} >> "$GITHUB_OUTPUT"
- uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7
if: steps.census.outputs.periodic_lane == 'true'
with:
name: paid-plan
path: /tmp/paid-plan/manifest.json
retention-days: 30
- name: Emit gate census manifest (ALL gate tests)
# One plan per arm: the Codex host plans only its adapter cases and
# records every Claude-only case as excluded with its reason.
- name: Emit gate census manifests (ALL gate tests, one plan per arm)
if: steps.census.outputs.arms != '[]'
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 --slice-budget 420 --jobs 2 --skip-judges --max-parallel 20
- name: Derive the gate census executor matrix from the plan
id: gate-matrix
ARMS: ${{ steps.census.outputs.arms }}
run: |
echo "slices=$(jq -c '[range(1; .sliceCount + 1)]' /tmp/gate-census-plan/manifest.json)" >> "$GITHUB_OUTPUT"
echo "slice_timeouts=$(jq -ec '[0] + .plan.sliceCiTimeoutMinutes' /tmp/gate-census-plan/manifest.json)" >> "$GITHUB_OUTPUT"
set -euo pipefail
for arm in $(jq -r '.[]' <<<"$ARMS"); do
mapfile -t arm_env < <(bun --no-install run scripts/census-arms.ts --env "$arm")
env "${arm_env[@]}" EVALS_TIER=gate bun run scripts/test-paid-shards.ts --tier gate --emit-plan "/tmp/gate-census-plan/$arm/manifest.json" --slice-budget 420 --jobs 2 --skip-judges --max-parallel 20
done
# One executor per arm and planned slice, each with its slice's ceiling.
- name: Derive the gate census executor matrix from the plans
id: gate-matrix
env:
ARMS: ${{ steps.census.outputs.arms }}
run: bun --no-install run scripts/census-arms.ts --matrix /tmp/gate-census-plan "$ARMS" >> "$GITHUB_OUTPUT"
- uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7
if: steps.census.outputs.arms != '[]'
with:
name: gate-census-plan
path: /tmp/gate-census-plan/manifest.json
path: /tmp/gate-census-plan
retention-days: 30
# autoplan-schema-canary: installs the latest published Claude Code with
@@ -237,6 +273,7 @@ jobs:
eval-slices:
runs-on: ubicloud-standard-8
needs: [build-image, plan-slices]
if: ${{ needs.plan-slices.outputs.periodic_lane == 'true' }}
env:
EVALS_RUN_ID: ci-${{ github.run_id }}-${{ github.run_attempt }}-eval-slices-${{ matrix.slice }}
# The planner packs ~7 minutes of recorded work per slice; each slice's job
@@ -388,7 +425,7 @@ jobs:
eval-codex-slices:
runs-on: ubicloud-standard-8
needs: [build-image, plan-slices]
if: ${{ needs.plan-slices.outputs.periodic_codex_slices != '[]' }}
if: ${{ needs.plan-slices.outputs.periodic_lane == 'true' && needs.plan-slices.outputs.periodic_codex_slices != '[]' }}
env:
EVALS_RUN_ID: ci-${{ github.run_id }}-${{ github.run_attempt }}-eval-slices-${{ matrix.slice }}
timeout-minutes: ${{ fromJSON(needs.plan-slices.outputs.periodic_slice_timeouts)[matrix.slice] }}
@@ -512,16 +549,18 @@ jobs:
# blind spots rot invisibly. Census health, not selector correctness —
# selector logic has free synthetic-diff contract tests.
gate-census:
name: gate-census-${{ matrix.arm }} (${{ matrix.slice }})
runs-on: ubicloud-standard-8
needs: [build-image, plan-slices]
# A branch dispatch validates the periodic lane only; gate cases on a
# branch go through an evals.yml dispatch with evals_all. Main (schedule
# or dispatch) always runs the census; a branch opts in explicitly.
if: ${{ github.ref == 'refs/heads/main' || inputs.include_gate_census }}
# The planner picks the arms (scripts/census-arms.ts). A branch dispatch
# validates the periodic lane only unless it sets include_gate_census or
# census_arms; gate cases on a branch also go through an evals.yml
# dispatch with evals_all. Main (schedule or dispatch) always runs it.
if: ${{ needs.plan-slices.outputs.gate_matrix != '[]' }}
env:
EVALS_RUN_ID: ci-${{ github.run_id }}-${{ github.run_attempt }}-gate-census-${{ matrix.slice }}
# Per-slice job ceiling from the packed plan (W2c/ENG-2), as for eval-slices.
timeout-minutes: ${{ fromJSON(needs.plan-slices.outputs.gate_slice_timeouts)[matrix.slice] }}
EVALS_RUN_ID: ci-${{ github.run_id }}-${{ github.run_attempt }}-gate-census-${{ matrix.arm }}-${{ matrix.slice }}
# Per-slice job ceiling from the arm's packed plan (W2c/ENG-2), as for eval-slices.
timeout-minutes: ${{ matrix.timeout }}
permissions:
contents: read
packages: read
@@ -536,7 +575,7 @@ jobs:
fail-fast: false
max-parallel: 20
matrix:
slice: ${{ fromJSON(needs.plan-slices.outputs.gate_slices) }}
include: ${{ fromJSON(needs.plan-slices.outputs.gate_matrix) }}
steps:
- name: Record the job start for the slice deadline
run: echo "GSTACK_SLICE_JOB_STARTED_AT=$(date +%s)" >> "$GITHUB_ENV"
@@ -588,7 +627,15 @@ jobs:
printenv OPENAI_API_KEY | "$codex" login --with-api-key
"$codex" login status >/dev/null 2>&1
- name: Run gate census slice ${{ matrix.slice }}
# The arm's host and model (EVALS_HOST, plus EVALS_MODEL or
# GSTACK_CODEX_MODEL). The Codex host runs codex exec with
# danger-full-access, so it needs no bubblewrap and runs in this container.
- name: Select the census arm's host and model
env:
ARM: ${{ matrix.arm }}
run: bun --no-install run scripts/census-arms.ts --env "$ARM" >> "$GITHUB_ENV"
- name: Run gate census slice ${{ matrix.slice }} (${{ matrix.arm }})
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -597,13 +644,13 @@ jobs:
EVALS_JOBS: "2"
EVALS_CONCURRENCY: "2"
GSTACK_EVAL_DIR: /tmp/gate-census-results
run: EVALS_TIER=gate bun run scripts/test-paid-shards.ts --tier gate --plan /tmp/gate-census-plan/manifest.json --slice ${{ matrix.slice }}
run: EVALS_TIER=gate bun run scripts/test-paid-shards.ts --tier gate --plan /tmp/gate-census-plan/${{ matrix.arm }}/manifest.json --slice ${{ matrix.slice }}
- name: Upload census results
if: always()
uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7
with:
name: gate-census-${{ matrix.slice }}-a${{ github.run_attempt }}
name: gate-census-${{ matrix.slice }}-a${{ github.run_attempt }}-${{ matrix.arm }}
path: /tmp/gate-census-results
retention-days: 90
@@ -638,6 +685,9 @@ jobs:
actions: read
outputs:
redispatch: ${{ steps.verdict.outputs.redispatch }}
# A census-only run (monthly cron or census_arms dispatch) re-dispatches
# with the same arms; empty keeps the weekly selection.
redispatch_census_arms: ${{ needs.plan-slices.outputs.periodic_lane != 'true' && join(fromJSON(needs.plan-slices.outputs.census_arms), ',') || '' }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
@@ -648,6 +698,7 @@ jobs:
bun-version: 1.4.2
- uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8
if: needs.plan-slices.outputs.periodic_lane == 'true'
with:
name: paid-plan
path: /tmp/paid-report
@@ -655,25 +706,35 @@ jobs:
# One directory per attempt-scoped slice artifact (no merge): shard
# records never overwrite each other and the first attempt decides.
- uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8
if: needs.plan-slices.outputs.periodic_lane == 'true'
with:
pattern: paid-slice-*
path: /tmp/paid-report
- uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8
if: needs.plan-slices.outputs.gate_matrix != '[]'
with:
name: gate-census-plan
path: /tmp/gate-census-report
path: /tmp/gate-census-plan
- uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8
if: needs.plan-slices.outputs.gate_matrix != '[]'
with:
pattern: gate-census-[0-9]*
path: /tmp/gate-census-report
path: /tmp/gate-census-slices
- name: Reconcile slices against the manifest (fail-closed)
id: reconcile
if: always()
env:
PERIODIC_LANE: ${{ needs.plan-slices.outputs.periodic_lane }}
run: |
set +e
if [ "$PERIODIC_LANE" != "true" ]; then
echo "periodic lane skipped: census-only run (monthly cron or census_arms dispatch)" | tee /tmp/report.txt
echo "exit=0" >> "$GITHUB_OUTPUT"
exit 0
fi
EVALS_TIER=periodic bun --no-install run scripts/test-paid-shards.ts --tier periodic --report /tmp/paid-report | tee /tmp/report.txt
# PIPESTATUS[0], NOT $?: GitHub's default run-step shell is
# `bash -e {0}` with NO pipefail, so $? after the pipe is tee's
@@ -686,20 +747,34 @@ jobs:
if: always()
env:
GATE_CENSUS: ${{ needs.gate-census.result }}
ARMS: ${{ needs.plan-slices.outputs.census_arms }}
# One report per arm: its plan plus its own slice artifacts
# (gate-census-<slice>-a<attempt>-<arm>) in /tmp/gate-census-report/<arm>.
run: |
set +e
if [ "$GATE_CENSUS" = "skipped" ]; then
echo "gate census skipped: branch dispatch without include_gate_census (periodic lane only)" | tee /tmp/gate-report.txt
echo "gate census skipped: no census arm selected (branch dispatch without include_gate_census or census_arms)" | tee /tmp/gate-report.txt
echo "exit=0" >> "$GITHUB_OUTPUT"
exit 0
fi
EVALS_TIER=gate bun run scripts/test-paid-shards.ts --tier gate --report /tmp/gate-census-report | tee /tmp/gate-report.txt
echo "exit=${PIPESTATUS[0]}" >> "$GITHUB_OUTPUT"
status=0
: > /tmp/gate-report.txt
for arm in $(jq -r '.[]' <<<"$ARMS"); do
dir="/tmp/gate-census-report/$arm"
mkdir -p "$dir"
cp "/tmp/gate-census-plan/$arm/manifest.json" "$dir/manifest.json" || status=1
for slice in /tmp/gate-census-slices/gate-census-*-"$arm"; do if [ -d "$slice" ]; then mv "$slice" "$dir/"; fi; done
echo "=== gate census arm: $arm ===" | tee -a /tmp/gate-report.txt
EVALS_TIER=gate bun run scripts/test-paid-shards.ts --tier gate --report "$dir" | tee -a /tmp/gate-report.txt
code=${PIPESTATUS[0]}
if [ "$code" -ne 0 ]; then status=$code; fi
done
echo "exit=$status" >> "$GITHUB_OUTPUT"
- name: Stamp trial history series
if: always()
run: |
for file in /tmp/paid-report/trial-outcomes.jsonl /tmp/gate-census-report/trial-outcomes.jsonl; do
for file in /tmp/paid-report/trial-outcomes.jsonl /tmp/gate-census-report/*/trial-outcomes.jsonl; do
if [ -f "$file" ]; then bun --no-install run scripts/eval-trial-series.ts "$file"; fi
done
@@ -719,7 +794,7 @@ jobs:
with:
name: trial-outcomes-gate-census-a${{ github.run_attempt }}
path: |
/tmp/gate-census-report/trial-outcomes.jsonl
/tmp/gate-census-report/*/trial-outcomes.jsonl
if-no-files-found: ignore
retention-days: 90
@@ -732,7 +807,7 @@ jobs:
run: |
mkdir -p /tmp/exercised-map
dirs=()
for dir in /tmp/gate-census-report /tmp/paid-report; do [ -d "$dir" ] && dirs+=(--from-dir "$dir"); done
for dir in /tmp/gate-census-report/* /tmp/paid-report; do [ -d "$dir" ] && dirs+=(--from-dir "$dir"); done
status=0
bun --no-install run scripts/exercised-map.ts "${dirs[@]}" \
--run-id "$GITHUB_RUN_ID" --out /tmp/exercised-map/exercised-commands.json --report /tmp/exercised-map/report.md || status=$?
@@ -779,8 +854,16 @@ jobs:
[ "$1" = "0" ] && return 0
jq -e '.version == 2 and .verdict.redispatchEligible == true' "$2/collector-outcomes.json" >/dev/null 2>&1
}
eligible_arms() { # $1 exit, then one report dir per census arm: each must be green or INFRA/INCOMPLETE-only
[ "$1" = "0" ] && return 0
shift
local dir
for dir in "$@"; do
jq -e '.version == 2 and (.verdict.verdict == "GREEN" or .verdict.redispatchEligible == true)' "$dir/collector-outcomes.json" >/dev/null 2>&1 || return 1
done
}
if [ -z "$REDISPATCH_OF" ] && { [ "$PERIODIC_EXIT" != "0" ] || [ "$GATE_EXIT" != "0" ]; } \
&& eligible "$PERIODIC_EXIT" /tmp/paid-report && eligible "$GATE_EXIT" /tmp/gate-census-report; then
&& eligible "$PERIODIC_EXIT" /tmp/paid-report && eligible_arms "$GATE_EXIT" /tmp/gate-census-report/*/; then
echo "redispatch=true" >> "$GITHUB_OUTPUT"
else
echo "redispatch=false" >> "$GITHUB_OUTPUT"
@@ -793,7 +876,7 @@ jobs:
# comments on or closes main's issue. Every report-derived line goes
# through the one published-text sanitizer (scripts/lib/published-text.ts).
- name: Write the census report
if: always() && (steps.reconcile.outputs.exit != '0' || steps.gate-reconcile.outputs.exit != '0' || steps.pass-rates.outputs.exit != '0' || needs.eval-slices.result != 'success' || !contains(fromJSON('["success","skipped"]'), needs.eval-codex-slices.result) || needs.gate-census.result != 'success')
if: always() && (steps.reconcile.outputs.exit != '0' || steps.gate-reconcile.outputs.exit != '0' || steps.pass-rates.outputs.exit != '0' || (needs.plan-slices.outputs.periodic_lane == 'true' && needs.eval-slices.result != 'success') || !contains(fromJSON('["success","skipped"]'), needs.eval-codex-slices.result) || needs.gate-census.result != 'success')
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
REDISPATCH: ${{ steps.verdict.outputs.redispatch }}
@@ -827,7 +910,14 @@ jobs:
cat /tmp/paid-report/report-summary.md 2>/dev/null || echo "(no periodic report summary)"
echo
echo "### Gate census"
cat /tmp/gate-census-report/report-summary.md 2>/dev/null || echo "(no gate census report summary)"
found=0
for summary in /tmp/gate-census-report/*/report-summary.md; do
[ -f "$summary" ] || continue
found=1
echo "#### Arm $(basename "$(dirname "$summary")")"
cat "$summary"
done
[ "$found" = 1 ] || echo "(no gate census report summary)"
echo
echo "### Pass-rate history (ACTION REQUIRED)"
{ awk '/^ACTION REQUIRED/ { on = 1; print; next } on && /^ \[/ { print; next } { on = 0 } /history unavailable/ { print }' /tmp/pass-rates.txt 2>/dev/null \
@@ -851,7 +941,7 @@ jobs:
cat /tmp/census-report.md >> "$GITHUB_STEP_SUMMARY"
- name: Upload the census report
if: always() && (steps.reconcile.outputs.exit != '0' || steps.gate-reconcile.outputs.exit != '0' || steps.pass-rates.outputs.exit != '0' || needs.eval-slices.result != 'success' || !contains(fromJSON('["success","skipped"]'), needs.eval-codex-slices.result) || needs.gate-census.result != 'success')
if: always() && (steps.reconcile.outputs.exit != '0' || steps.gate-reconcile.outputs.exit != '0' || steps.pass-rates.outputs.exit != '0' || (needs.plan-slices.outputs.periodic_lane == 'true' && needs.eval-slices.result != 'success') || !contains(fromJSON('["success","skipped"]'), needs.eval-codex-slices.result) || needs.gate-census.result != 'success')
uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7
with:
name: census-report-a${{ github.run_attempt }}
@@ -860,7 +950,7 @@ jobs:
retention-days: 90
- name: Upsert tracking issue on failure
if: always() && github.ref == 'refs/heads/main' && (steps.reconcile.outputs.exit != '0' || steps.gate-reconcile.outputs.exit != '0' || steps.pass-rates.outputs.exit != '0' || needs.eval-slices.result != 'success' || !contains(fromJSON('["success","skipped"]'), needs.eval-codex-slices.result) || needs.gate-census.result != 'success')
if: always() && github.ref == 'refs/heads/main' && (steps.reconcile.outputs.exit != '0' || steps.gate-reconcile.outputs.exit != '0' || steps.pass-rates.outputs.exit != '0' || (needs.plan-slices.outputs.periodic_lane == 'true' && needs.eval-slices.result != 'success') || !contains(fromJSON('["success","skipped"]'), needs.eval-codex-slices.result) || needs.gate-census.result != 'success')
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
@@ -877,7 +967,7 @@ jobs:
fi
- name: Close the tracking issue on a green run
if: always() && github.ref == 'refs/heads/main' && steps.reconcile.outputs.exit == '0' && steps.gate-reconcile.outputs.exit == '0' && steps.pass-rates.outputs.exit == '0' && needs.eval-slices.result == 'success' && contains(fromJSON('["success","skipped"]'), needs.eval-codex-slices.result) && needs.gate-census.result == 'success'
if: always() && github.ref == 'refs/heads/main' && steps.reconcile.outputs.exit == '0' && steps.gate-reconcile.outputs.exit == '0' && steps.pass-rates.outputs.exit == '0' && needs.plan-slices.outputs.periodic_lane == 'true' && needs.eval-slices.result == 'success' && contains(fromJSON('["success","skipped"]'), needs.eval-codex-slices.result) && needs.gate-census.result == 'success'
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
REDISPATCH_OF: ${{ inputs.redispatch_of }}
@@ -892,7 +982,7 @@ jobs:
fi
- name: Fail the workflow when reconciliation failed
if: always() && (steps.reconcile.outputs.exit != '0' || steps.gate-reconcile.outputs.exit != '0' || steps.pass-rates.outputs.exit != '0' || needs.eval-slices.result != 'success' || !contains(fromJSON('["success","skipped"]'), needs.eval-codex-slices.result) || !contains(fromJSON('["success","skipped"]'), needs.gate-census.result))
if: always() && (steps.reconcile.outputs.exit != '0' || steps.gate-reconcile.outputs.exit != '0' || steps.pass-rates.outputs.exit != '0' || (needs.plan-slices.outputs.periodic_lane == 'true' && needs.eval-slices.result != 'success') || !contains(fromJSON('["success","skipped"]'), needs.eval-codex-slices.result) || !contains(fromJSON('["success","skipped"]'), needs.gate-census.result))
run: exit 1
# The one INFRA/INCOMPLETE re-dispatch (UC-E1). Its own job so the report
@@ -909,4 +999,5 @@ jobs:
- name: Re-dispatch the weekly census once
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: gh workflow run evals-periodic.yml --repo "$GITHUB_REPOSITORY" --ref "$GITHUB_REF_NAME" -f redispatch_of="$GITHUB_RUN_ID"
CENSUS_ARMS: ${{ needs.report.outputs.redispatch_census_arms }}
run: gh workflow run evals-periodic.yml --repo "$GITHUB_REPOSITORY" --ref "$GITHUB_REF_NAME" -f redispatch_of="$GITHUB_RUN_ID" ${CENSUS_ARMS:+-f census_arms="$CENSUS_ARMS"}
.github/workflows/free-durations-record.yml
+2 -1
View File
@@ -161,7 +161,7 @@ jobs:
- Files that failed while recording (durations kept; this PR's own free checks decide): $failed_line
- Seed growth ratchet (60 s ceiling, shrink-only allowlist): $ratchet_line
Data only. Stamp and merge per docs/ship-policy.md; the stamp push runs the full PR checks.
Data only. This run dispatched Free Tests (the required free-tests check), Windows Free Tests and Quality gate on this branch; those are this PR's checks. The pull_request runs wait as "action required" because a token-opened PR never starts them without approval. Stamp and merge per docs/ship-policy.md; the stamp push runs the full PR checks.
EOF
if [ -n "$number" ]; then
gh pr edit "$number" --body-file pr-body.md
@@ -170,3 +170,4 @@ jobs:
fi
gh workflow run free-tests.yml --repo "$GITHUB_REPOSITORY" --ref "$branch"
gh workflow run windows-free-tests.yml --repo "$GITHUB_REPOSITORY" --ref "$branch"
gh workflow run quality-gate.yml --repo "$GITHUB_REPOSITORY" --ref "$branch"
CHANGELOG.md
+43
View File
@@ -13,6 +13,49 @@
- **plan-review-prosons-hardstop-neg:** on Opus 5.5 one trial in three stopped with a provider refusal (`stop_reason: refusal`, category `reasoning_extraction`) on the turn that writes the captured question. Replays of the refused request were stopped 7 of 16 times with the capture prompt's "verbatim" and "Do NOT paraphrase. This is a format-capture test." wording and 0 of 24 without it. The shared prosons capture prompt now asks for "the text of the single AskUserQuestion you would have made", with the same required parts. The decision content and every assertion are unchanged; all four prosons cases pass 3/3.
- **Cookie workflow judge:** on `claude-sonnet-5-5` it scored clarity 3, completeness 4, actionability 3 against the old template. The rewritten template scores 4/4/4 with unchanged thresholds.
## [1.91.149.0] - 2026-10-19
**Paid eval cases can now run on the Codex host, and the Monday census runs two arms: Claude Opus 5.5 and Codex gpt-6.1-sol.** `EVALS_HOST=codex` runs the 52 adapter-only gate cases through a full Codex runtime per case. On its first pilot gpt-6.1-sol passed 48 of 52 with no retries, at $4.63 for the 52 cases, against $28.93 for the same cases on Fable (0.16×). Claude-only cases are skipped on Codex with a recorded reason and never count as failed. GSTA-49 TM2.
### Added
- **Codex host adapter:** `test/helpers/e2e-hosts.ts` holds the `EVALS_HOST` switch (`claude` default, `codex`) and the per-case host metadata. `test/helpers/codex-host-runner.ts` adds:
- the case runner, with sandbox settings and a reasoning effort (the model default unless set);
- file-change event mapping;
- a transcript translated into the Claude stream-json shape that existing assertions read;
- the native-lifecycle hooks.
The 26 rework cases stay Claude-only.
- **Census arms (`scripts/census-arms.ts`):** `evals-periodic.yml` gets two census schedules.
- **Monday:** a two-arm gate census, `claude-opus` and `codex-sol`.
- **Monthly (`0 6 1 * *`):** census jobs only, with `claude-fable` (claude-fable-5-1) and `codex-astra` (gpt-6-astra) arms and a `-monthly` concurrency key.
A `census_arms` dispatch input picks arms by hand. Artifact names and run IDs carry the arm, and a census-only run executes no periodic slice. Every arm keeps the census's `--skip-judges`.
### Changed
- **Codex cost is real:** `cost_known: false` is gone. Codex sessions price their `turn.completed` usage (input, cached input, cache-write input and output tokens) through `lib/pricing.ts`. The shared `execCodex` keeps the old runner's events and verdicts.
- **Plans, reports and the ledger carry the host** when it is not Claude. On Codex, the Anthropic preflight skips its `claude -p` ping.
- **Gate integrity:** no threshold, trial count, case kind, judge or Claude-host verdict changed. `HARNESS_VERSION` stays 6, and the changed harness files are recorded as non-behavioral. Five workflow tests now assert the census matrix per arm (one row per arm and slice, per-arm plan and report paths, a `periodic_lane` guard) in place of the single-arm shape; no assertion was dropped.
### If you…
- **…want one case on Codex:** `EVALS_HOST=codex GSTACK_CODEX_MODEL=gpt-6.1-sol bun run scripts/test-paid-shards.ts --tier gate --case <id> --trials 1`.
- **…want the monthly arms now:** dispatch `evals-periodic.yml` with `census_arms=claude-fable,codex-astra`.
## [1.91.148.0] - 2026-10-19
**Weekly seed PRs now get the credential scan as well as the free suites.** A pull request the recorder opens with the workflow token never starts its own `pull_request` checks. GitHub holds them as "action required". So the recorder dispatches its checks on the bot branch instead.
### Changed
- **`free-durations-record.yml` also dispatches Quality gate** on `bot/free-duration-seeds`, next to Free Tests (the required `free-tests` check) and Windows Free Tests.
- **The seed PR body says the dispatched runs are its checks** and explains why its pull_request runs wait for approval.
## [1.91.147.0] - 2026-10-19
**The free-suite duration seeds are current again.** This is the first refresh from the weekly recorder. It adds 14 Linux and 6 Windows test files that the shard packers had been placing at the 99th-percentile estimate.
### Changed
- **Seed allowlist:** `test/brain-sync.test.ts` (89 s) and `test/setup-codex-scope.test.ts` (64 s) are allowlisted with the existing split todo. `test/host-renders-prune.test.ts` (now 57 s) leaves the allowlist.
- **Editing the seed allowlist no longer selects paid evals.** Only the free seed ratchet reads `scripts/free-test-seed-allowlist.json`, but an edit to it used to pull in all 246 dependent gate cases. It is now classified free-only, like the two seeds.
## [1.91.146.0] - 2026-10-19
**`gstack-ship-queue` can run merge trains: several READY PRs share one full gate, merge one by one only while main's tree matches the prefix that gate tested, and a red train is bisected on its red cases alone.** The surface is off unless the base revision's `.gstack/ship-policy.json` declares a `train` block. Without one, `ready --pr <n>` prints exactly the block it prints today. gstack's own policy does not turn trains on yet: that waits for the workflow side (the train-nonce record, the `cases` and `prefix_shas` inputs and the dispatched screen) and one dry-run train. Walkthrough: [docs/ship-policy.md#run-a-merge-train](docs/ship-policy.md#run-a-merge-train). Plan GSTA-49, lane T1.
TODOS.md
+6 -5
View File
@@ -5476,10 +5476,11 @@ Garry for each; revisit 2026-10-29 unless a date says otherwise.
16-worker duration recording on 2026-10-15 the event had not landed
(`['paste', 'enter', 'end_turn']`). Wait for the CLI's own write instead of a
timer (docs/TESTING_INTERNALS.md#flake-ledger). **Effort:** S. **Priority:** P2.
- **Split the free files the 2026-10-15 seed put over 60 s** —
`test/setup-install-registry.test.ts` (82 s), `test/host-renders-prune.test.ts`
(64 s) and `test/setup-codex-scope.test.ts` (60.4 s) are allowlisted with this
todo in `scripts/free-test-seed-allowlist.json`; `test/brain-sync.test.ts`
(57 s) and `test/setup-codex-scope-namespaces.test.ts` (57 s) are next. Split
- **Split the free files the weekly seed puts over 60 s** —
`test/setup-install-registry.test.ts` (84 s), `test/brain-sync.test.ts` (89 s)
and `test/setup-codex-scope.test.ts` (64 s) are allowlisted with this todo in
`scripts/free-test-seed-allowlist.json` (2026-10-19 recording);
`test/host-renders-prune.test.ts` (57 s) and
`test/setup-codex-scope-namespaces.test.ts` are next. Split
each by describe block, rerun `bun run test:ubicloud --record-durations` and
delete the entries. **Effort:** S each. **Priority:** P2.
VERSION
+1 -1
View File
@@ -1 +1 @@
1.91.146.0
1.91.149.0
agents-digest/gstack-AGENTS.md
+1 -1
View File
@@ -1,4 +1,4 @@
# gstack digest v1.91.146.0 — regenerate/re-copy after upgrading gstack
# gstack digest v1.91.149.0 — regenerate/re-copy after upgrading gstack
Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed
for agent hosts without a full skill install. The full skills add workflows,
docs/TESTING_INTERNALS.md
+4 -1
View File
@@ -1379,7 +1379,10 @@ refresh to a maintainer.
`windows-free-tests.yml`'s `record_durations` path. When either recording adds
or drops a test file, it force-updates the `bot/free-duration-seeds` branch,
opens or refreshes one seed PR whose body states the ratchet result, and
dispatches the free lanes on it. A file that fails while recording turns its
dispatches Free Tests, Windows Free Tests and Quality gate on it. Those
dispatched runs are the seed PR's checks, and Free Tests supplies the required
`free-tests` check. GitHub holds the pull_request runs of a token-opened PR as
"action required" until someone approves them. A file that fails while recording turns its
job red but keeps its duration, and the PR body names it; the seed PR's own
free checks decide whether the tree is healthy. An interrupted recording
uploads no seed, and more than 5 red files on either OS proposes nothing. The
package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "gstack",
"version": "1.91.146",
"version": "1.91.149",
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
"license": "MIT",
"type": "module",
scripts/census-arms.ts
+81
View File
@@ -0,0 +1,81 @@
#!/usr/bin/env bun
/**
* Gate census arms for evals-periodic.yml (GSTA-49 TM2). Each arm is one host
* and model running the weekly gate census plan:
* - Monday cron (0 6 * * 1): claude-opus (the capture model, lib/eval-model.ts)
* and codex-sol (gpt-6.1-sol on the Codex host, adapter cases only);
* - monthly cron (0 6 1 * *): claude-fable and codex-astra, census jobs only;
* - dispatch: `census_arms` runs only the census with the named arms; without
* it a dispatch keeps the periodic lane plus the Monday arms when the census
* runs (main, or include_gate_census).
* Judges stay in the Claude lanes: every census plan skips them.
*
* CLI (GitHub step outputs and env lines):
* --select env SCHEDULE, CENSUS_ARMS, INCLUDE_GATE_CENSUS -> arms=<json>, periodic_lane=<bool>
* --env <arm> KEY=VALUE lines selecting the arm's host and model
* --matrix <dir> <arms> gate_matrix=<json> from <dir>/<arm>/manifest.json
*/
import * as fs from 'node:fs';
import * as path from 'node:path';
import type { EvalHost } from '../test/helpers/e2e-hosts';
export interface CensusArm { host: EvalHost; model?: string }
export const CENSUS_ARMS: Readonly<Record<string, CensusArm>> = Object.freeze({
// No model: the Claude runners' capture default (claude-opus-5-5 since TM1).
'claude-opus': { host: 'claude' },
'codex-sol': { host: 'codex', model: 'gpt-6.1-sol' },
'claude-fable': { host: 'claude', model: 'claude-fable-5-1' },
'codex-astra': { host: 'codex', model: 'gpt-6-astra' },
});
export const WEEKLY_CENSUS_SCHEDULE = '0 6 * * 1';
export const MONTHLY_CENSUS_SCHEDULE = '0 6 1 * *';
export const WEEKLY_CENSUS_ARMS: readonly string[] = ['claude-opus', 'codex-sol'];
export const MONTHLY_CENSUS_ARMS: readonly string[] = ['claude-fable', 'codex-astra'];
/** Which census arms run, and whether the periodic lane runs beside them. */
export function selectCensus(opts: { schedule?: string; censusArms?: string; includeGateCensus: boolean }): { arms: string[]; periodicLane: boolean } {
if (opts.schedule === MONTHLY_CENSUS_SCHEDULE) return { arms: [...MONTHLY_CENSUS_ARMS], periodicLane: false };
const named = (opts.censusArms ?? '').split(/[\s,]+/).filter(Boolean);
const unknown = named.filter(arm => !Object.hasOwn(CENSUS_ARMS, arm));
if (unknown.length) throw new Error(`unknown census arm(s): ${unknown.join(', ')}; known: ${Object.keys(CENSUS_ARMS).join(', ')}`);
if (named.length) return { arms: [...new Set(named)], periodicLane: false };
return { arms: opts.includeGateCensus ? [...WEEKLY_CENSUS_ARMS] : [], periodicLane: true };
}
/** The env one arm's planner and executor run with. */
export function censusArmEnv(arm: string): Record<string, string> {
const spec = CENSUS_ARMS[arm];
if (!spec) throw new Error(`unknown census arm: ${arm}`);
if (!spec.model) return { EVALS_HOST: spec.host };
return { EVALS_HOST: spec.host, [spec.host === 'codex' ? 'GSTACK_CODEX_MODEL' : 'EVALS_MODEL']: spec.model };
}
/** One executor per arm and planned slice, with that slice's planned CI ceiling. */
export function censusMatrix(arms: readonly string[], planDir: string): Array<{ arm: string; slice: number; timeout: number }> {
return arms.flatMap(arm => {
const manifest = JSON.parse(fs.readFileSync(path.join(planDir, arm, 'manifest.json'), 'utf8')) as
{ sliceCount: number; plan?: { ciTimeoutMinutes: number; sliceCiTimeoutMinutes?: number[] } };
if (!manifest.plan) throw new Error(`${arm}: census manifest has no budget plan`);
return Array.from({ length: manifest.sliceCount }, (_, i) => ({
arm, slice: i + 1, timeout: manifest.plan!.sliceCiTimeoutMinutes?.[i] ?? manifest.plan!.ciTimeoutMinutes,
}));
});
}
if (import.meta.main) {
const [mode, ...args] = process.argv.slice(2);
if (mode === '--select') {
const { arms, periodicLane } = selectCensus({ schedule: process.env.SCHEDULE, censusArms: process.env.CENSUS_ARMS,
includeGateCensus: process.env.INCLUDE_GATE_CENSUS === 'true' });
console.log(`arms=${JSON.stringify(arms)}\nperiodic_lane=${periodicLane}`);
} else if (mode === '--env' && args.length === 1) {
for (const [key, value] of Object.entries(censusArmEnv(args[0]!))) console.log(`${key}=${value}`);
} else if (mode === '--matrix' && args.length === 2) {
console.log(`gate_matrix=${JSON.stringify(censusMatrix(JSON.parse(args[1]!) as string[], args[0]!))}`);
} else {
console.error('usage: census-arms.ts --select | --env <arm> | --matrix <plan dir> <arms json>');
process.exit(2);
}
}
scripts/e2e-shard-reuse.ts
+1
View File
@@ -83,6 +83,7 @@ export function e2eReuseLaneProblem(env: NodeJS.ProcessEnv, profileMode: string
if (!/^(?:sha256:)?[a-f0-9]{64}$/.test(env.EVALS_CACHE_RUNTIME_ID ?? '')) return 'No immutable runtime identity';
if (env.EVALS_TIER !== 'gate' || env.EVALS_FRESH === '1') return 'Fresh validation requested';
if (['release', 'periodic', 'marathon'].includes(env.EVALS_CACHE_PURPOSE ?? '')) return 'Scheduled and release lanes execute fresh';
if ((env.EVALS_HOST ?? '').trim() && env.EVALS_HOST!.trim() !== 'claude') return 'Non-Claude hosts execute fresh';
if (env.NODE_OPTIONS || env.BUN_OPTIONS) return 'Preload options change execution outside the consumed source';
if (env.ANTHROPIC_BASE_URL && env.ANTHROPIC_BASE_URL !== 'https://api.anthropic.com') return 'Custom model endpoint';
return null;
scripts/free-test-durations-windows.json
+742 -736
View File
File diff suppressed because it is too large. Load diff
scripts/free-test-durations.json
+1269 -1255
View File
File diff suppressed because it is too large. Load diff
scripts/free-test-seed-allowlist.json
+2 -1
View File
@@ -3,6 +3,7 @@
{"file": "test/host-conformance.test.ts", "reason": "real ./setup per host and layout; the time is setup's own skill-linking loop, not fixture copies (shared fixture landed in W6c)"},
{"file": "test/shared-libs-stage-actor.test.ts", "reason": "re-runs the paid shared-libs runner body against git fixture repos per test; owned by the paid-harness value-bar review"},
{"file": "test/setup-install-registry.test.ts", "reason": "82s in the 2026-10-15 recording (58s on 2026-10-04): 11 cases each run the real ./setup, gstack-relink, gstack-config and gstack-uninstall against throwaway checkouts", "todo": "split by describe block so the packer can balance it, then rerun bun run test:ubicloud --record-durations (TODOS.md, fix wave 2 follow-ups)"},
{"file": "test/host-renders-prune.test.ts", "reason": "64s in the 2026-10-15 recording (unseeded before): every case runs a real ./setup or the gstack-upgrade migration over host render dirs", "todo": "split by describe block so the packer can balance it, then rerun bun run test:ubicloud --record-durations (TODOS.md, fix wave 2 follow-ups)"}
{"file": "test/brain-sync.test.ts", "reason": "89s in the 2026-10-19 weekly recording (58s on 2026-10-15): #3254 added the case-collision suite, and every case drains a real gstack-brain-sync against a local bare remote", "todo": "split by describe block so the packer can balance it, then rerun bun run test:ubicloud --record-durations (TODOS.md, fix wave 2 follow-ups)"},
{"file": "test/setup-codex-scope.test.ts", "reason": "64s in the 2026-10-19 weekly recording (59s on 2026-10-15): each case runs the real ./setup twice against a Codex install fixture", "todo": "split by describe block so the packer can balance it, then rerun bun run test:ubicloud --record-durations (TODOS.md, fix wave 2 follow-ups)"}
]
}
scripts/harness-version.json
+12 -10
View File
@@ -3,6 +3,7 @@
"patterns": [
"test/helpers/agent-sdk-runner.ts",
"test/helpers/codex-session-runner.ts",
"test/helpers/codex-host-runner.ts",
"test/helpers/claude-pty-runner.ts",
"test/helpers/pty/**",
"test/helpers/pty-screen.ts",
@@ -10,22 +11,23 @@
"test/helpers/llm-judge.ts"
],
"files": {
"scripts/lib/paid-cases.ts": {"blob":"9bacd52446192a7ecf3dfaae901ea443cf9c9ae2","since":6},
"scripts/lib/paid-plan.ts": {"blob":"45721ce128a112666a0caed6c13c66637b74ca54","since":6},
"scripts/lib/paid-report.ts": {"blob":"b66c41237611ccecaaa7bd6a4d7b7aac8dc548cd","since":6},
"scripts/lib/paid-cases.ts": {"blob":"f862cf5241580c7593b9ee62eacf5ef046248d26","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
"scripts/lib/paid-plan.ts": {"blob":"95e1798e7e2495ace350d2624e59f83412f341bc","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
"scripts/lib/paid-report.ts": {"blob":"f92c6bb723b158e328aa040fa5de6a0ee6d3916d","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
"scripts/lib/published-text.ts": {"blob":"3f2e4d616b5dd0204035710c66b64d49055c5714","since":6},
"scripts/lib/shard-engine.ts": {"blob":"3cd0b1aaa84018b00bf9ea0ce48093f3c8492f66","since":6},
"scripts/test-paid-shards.ts": {"blob":"8ddee5f11ed7856876135520dd8025ab989e2db9","since":6},
"scripts/test-pr-profile.ts": {"blob":"2029a89e14f511866cc91bebfee00b4fe9e7cf63","since":6},
"scripts/test-paid-shards.ts": {"blob":"19c9b2376d09090aee1a8acacfe721d66f55b0fc","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
"scripts/test-pr-profile.ts": {"blob":"579ca1bbd590f709c1ea3d6f28fa6c629688c79f","since":6,"nonBehavioral":"Classifies scripts/free-test-seed-allowlist.json as free-only; only the free seed ratchet reads it, so no verdict can change"},
"scripts/test-strict-output.ts": {"blob":"01185d20dc9761b04b9b2f751ec98664fe0eaf93","since":6},
"test/helpers/agent-sdk-runner.ts": {"blob":"210bba92d241a90df578b2c7fc943ac5755d0025","since":6},
"test/helpers/auq-substance-panel.ts": {"blob":"4881260ef793668e4963a062db6d06a5e1f7a40f","since":6},
"test/helpers/claude-pty-runner.ts": {"blob":"20cc5894532873aa6145fc6617fdeec8cef94a2d","since":6},
"test/helpers/codex-session-runner.ts": {"blob":"4eea35931a35a0afb006363402e3d4191e379737","since":6},
"test/helpers/codex-host-runner.ts": {"blob":"bff225017e235f0be6ece29f04971ac04b95b544","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
"test/helpers/codex-session-runner.ts": {"blob":"c040ebbfa815b8cce19ef80c6133bd5a5474149a","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
"test/helpers/e2e-gate.ts": {"blob":"efb7e197dd5f66c3ad0e34074b14e640754f7a45","since":6},
"test/helpers/e2e-helpers.ts": {"blob":"2d4a2a53063cfc1f003db366d2c861ab1e379e6e","since":6},
"test/helpers/e2e-helpers.ts": {"blob":"6ee6937e6c3ca081c77131b5a755278c7b714834","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
"test/helpers/eval-budgets.ts": {"blob":"667d0e09b20fe5d7366f57b77b5fb9b04baa37ef","since":6},
"test/helpers/eval-store.ts": {"blob":"609c6d099108ff2696eb014b47aa318a618dd2af","since":6},
"test/helpers/eval-store.ts": {"blob":"ed8721f13d39f4ef62e0a1d814efbe9352da781a","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
"test/helpers/hermetic-env.ts": {"blob":"cc072895461dc52ea317d1beff72121342420d30","since":6},
"test/helpers/llm-judge.ts": {"blob":"d0bc6bbbe9f478603d11a1ece95e66c812ad34e6","since":6},
"test/helpers/paid-test-set.ts": {"blob":"ff9bfe43c43ec2bdd11114f7b8ec7c5736116f75","since":6},
@@ -44,8 +46,8 @@
"test/helpers/pty/screen.ts": {"blob":"ba7a80bb68b1959296ab2a827cfacdaa46f4ba2d","since":6},
"test/helpers/pty/session.ts": {"blob":"58533cea9d81cc87bb3b499bdfe0db8e3a8709c5","since":6},
"test/helpers/session-drain-policy.ts": {"blob":"6211239dd0485e6495a700b824a7e0e61d1bcd97","since":6},
"test/helpers/session-ledger.ts": {"blob":"6e3c9e837e46f98addba2d12eaebff802da320bb","since":6},
"test/helpers/session-runner.ts": {"blob":"d40eb29e8b8fdc0675b511693e4a90823b5963fc","since":6},
"test/helpers/session-ledger.ts": {"blob":"425323284a368f5e77937e03884db4dea4e6134e","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
"test/helpers/session-runner.ts": {"blob":"cc65a66adafa9c053e3da3c6f17b5ac86c0eade7","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
"test/helpers/skill-fixture.ts": {"blob":"b188064594eb4201a54a80ba1bc6f28e31d7f49e","since":6},
"test/helpers/test-selection.ts": {"blob":"51655f89f66be7a5ec487e2abfe4744300ebd5f6","since":6},
"test/helpers/touchfiles.ts": {"blob":"15f369056d41b9dc42dcd86f81f60c878074704c","since":6}
scripts/lib/paid-cases.ts
+33 -4
View File
@@ -9,6 +9,7 @@ import type { EvalCaseKind, PanelShape } from '../../test/helpers/eval-store';
import { E2E_KINDS } from '../../test/helpers/touchfiles-data';
import { E2E_TOUCHFILES, E2E_TIERS } from '../../test/helpers/touchfiles';
import { type PaidTier, ROOT } from './paid-types';
import { type EvalHost, hostSkipReason, resolveEvalHost } from '../../test/helpers/e2e-hosts';
/**
* The E2E ids a paid file registers: the touchfile registrations that list the
@@ -226,12 +227,38 @@ export function partitionCaseExclusions(keys: string[]): { runnable: string[]; e
return { runnable, excluded };
}
/**
* Host exclusions (EVALS_HOST, test/helpers/e2e-hosts.ts): on a non-Claude
* host a case key whose case is Claude-only, or a file key none of whose
* `tier` cases runs on the host, is excluded with its reason. A file that
* keeps one host case stays runnable; its Claude-only cases skip at module
* load and the report deselects them. The Claude host excludes nothing.
*/
export function partitionHostExclusions(keys: string[], tier: PaidTier, host: EvalHost, rootDir = ROOT): { runnable: string[]; excluded: Array<{ file: string; reason: string }> } {
if (host === 'claude') return { runnable: keys, excluded: [] };
const excluded: Array<{ file: string; reason: string }> = [];
const runnable = keys.filter(key => {
const caseId = shardCaseId(key);
const ids = caseId !== null ? [caseId]
: fileCaseRegistration(shardFile(key), fs.readFileSync(path.join(rootDir, shardFile(key)), 'utf8')).registered.filter(id => E2E_TIERS[id] === tier);
if (ids.some(id => hostSkipReason(id, host) === null)) return true;
const reason = ids.length === 1 ? hostSkipReason(ids[0]!, host)!
: ids.length === 0 ? `Claude-only on the ${host} host: no Codex host metadata (no ${tier} case registered)`
: `Claude-only on the ${host} host: no case runs on it (${ids.join(', ')})`;
excluded.push({ file: key, reason: `skipped: ${reason}` });
return false;
});
return { runnable, excluded };
}
/**
* Codex access in the CI eval image, scoped per paid shard.
*
* The image installs the pinned Codex CLI off PATH (GSTACK_CI_CODEX_BIN_DIR)
* and the eval workflows log it in under a non-default home
* (GSTACK_CI_CODEX_HOME). A gate shard never sees either. A non-gate shard
* (GSTACK_CI_CODEX_HOME). On the Codex host (EVALS_HOST=codex) Codex is the
* agent, so every shard gets the CLI on PATH and the home as CODEX_HOME.
* Otherwise a gate shard never sees either. A non-gate shard
* whose every file exercises Codex gets the CLI on PATH and the home as
* CODEX_HOME. A file that mixes one Codex case with other cases keeps only
* the two variables, and that case opts in on its own session; hermetic
@@ -266,8 +293,10 @@ export const CODEX_CI_CASES: Readonly<Record<string, readonly string[]>> = {
export type CodexShardAccess = 'none' | 'case-opt-in' | 'path';
/** What one shard, given the test files behind its keys, may see of the CI Codex install in `tier`. */
export function codexShardAccess(files: readonly string[], tier: string | undefined): CodexShardAccess {
if (tier === 'gate' || files.length === 0) return 'none';
export function codexShardAccess(files: readonly string[], tier: string | undefined, host: EvalHost = 'claude'): CodexShardAccess {
if (files.length === 0) return 'none';
if (host === 'codex') return 'path';
if (tier === 'gate') return 'none';
if (files.every(file => CODEX_CI_FILES.includes(file))) return 'path';
return files.every(file => file in CODEX_CI_CASES) ? 'case-opt-in' : 'none';
}
@@ -277,7 +306,7 @@ export function scopeCodexAccess(env: NodeJS.ProcessEnv, files: readonly string[
const binDir = env[CODEX_CI_ENV.binDir];
if (!binDir) return;
const home = env[CODEX_CI_ENV.home];
const access = codexShardAccess(files, env.EVALS_TIER);
const access = codexShardAccess(files, env.EVALS_TIER, resolveEvalHost(env));
delete env.CODEX_HOME;
if (access === 'case-opt-in') return;
delete env[CODEX_CI_ENV.binDir];
scripts/lib/paid-plan.ts
+11 -4
View File
@@ -10,7 +10,8 @@ import { evalEntryOutcome, type EvalCaseKind } from '../../test/helpers/eval-sto
import { E2E_KINDS } from '../../test/helpers/touchfiles-data';
import { prProfileCaseAllowed, prProfileFileMap, type PrProfileSelection } from '../test-pr-profile';
import { E2E_TOUCHFILES, E2E_TIERS, LLM_JUDGE_TOUCHFILES } from '../../test/helpers/touchfiles';
import { CASE_KEY_SEPARATOR, CASE_SHARDED_FILES, type CaseTrialPlan, caseTrialPlan, codexShardAccess, expandCaseShards, expandTrialShards, isIsolatedCase, partitionCaseExclusions, sameTrialPlan, shardCaseId, shardFile, shardTrial } from './paid-cases';
import { CASE_KEY_SEPARATOR, CASE_SHARDED_FILES, type CaseTrialPlan, caseTrialPlan, codexShardAccess, expandCaseShards, expandTrialShards, isIsolatedCase, partitionCaseExclusions, partitionHostExclusions, sameTrialPlan, shardCaseId, shardFile, shardTrial } from './paid-cases';
import { EVAL_HOSTS, type EvalHost, resolveEvalHost } from '../../test/helpers/e2e-hosts';
import { DEFAULT_JOBS, OVERLAY_MAX_ACTIVE_SHARDS, PAID_TIERS, SLICE_UPLOAD_RESERVE_MS, type PaidCaseSelection, type PaidProfile, type PaidShardBudget, type PaidTier, ROOT, type ShardOutcome, type ShardStatus, type ShardTrialRecord, isOverlayTestFile } from './paid-types';
import { collectPaidTestFiles, computePaidCaseSelection, expectedPrCaseCount, isAllSkippedPass, paidShardWallUpperBoundMs, partitionShardsByDiffSelection, planPaidShards, prProfileFileSelected, resolvePaidShardBudget, resolvePaidShardTimeoutMs, sameBudget, selectPaidTestFiles, shardSlug, validatedProfile } from './paid-select';
@@ -58,6 +59,8 @@ export interface PaidRunManifest {
evalsAll: boolean;
sliceCount: number;
selectionReason: string;
/** The agent host every session runs on (EVALS_HOST); absent means claude. */
host?: EvalHost;
/** Legacy v1 manifests omit these; new plans bind case-level execution. */
profile?: PaidProfile;
selection?: PaidCaseSelection;
@@ -314,9 +317,11 @@ export function buildRunManifest(opts: {
const quarantine = opts.quarantine ?? CASE_QUARANTINE;
const notLive = [...Object.keys(kinds).filter(id => kinds[id] === 'behavior'), ...Object.keys(quarantine)].filter(id => !Object.hasOwn(E2E_TIERS, id));
if (notLive.length) throw new Error(`Only live E2E cases can be behavior or quarantined (judges sample their panel inside the case): ${notLive.join(', ')}`);
const caseKeys = partitionCaseExclusions(expandCaseShards(selected, opts.tier, rootDir));
const host = resolveEvalHost(env);
const ciKeys = partitionCaseExclusions(expandCaseShards(selected, opts.tier, rootDir));
const caseKeys = partitionHostExclusions(ciKeys.runnable, opts.tier, host, rootDir);
const excluded = [...tierSelection.excluded, ...(opts.skipJudges ? tierSelection.selected.filter(judge)
.map(file => ({ file, reason: 'skipped: LLM judges run in the periodic census and PR gate lanes' })) : []), ...caseKeys.excluded];
.map(file => ({ file, reason: 'skipped: LLM judges run in the periodic census and PR gate lanes' })) : []), ...ciKeys.excluded, ...caseKeys.excluded];
const expansion = expandTrialShards(caseKeys.runnable, opts.tier, rootDir, { kinds, quarantine });
const excludeOf = (key: string) => expansion.excludeCases[normalizeRelativePath(key)] ?? [];
const shards = planPaidShards(expansion.keys, { maxFilesPerShard: 1 });
@@ -346,7 +351,7 @@ export function buildRunManifest(opts: {
entries.sort((a, b) => (a.file < b.file ? -1 : 1));
return parseRunManifest(JSON.stringify({
version: 1, tier: opts.tier, evalsAll: opts.evalsAll, sliceCount: plan.slices.length,
selectionReason: cases.reason, profile, selection: cases.selection,
selectionReason: cases.reason, ...(host !== 'claude' ? { host } : {}), profile, selection: cases.selection,
...(cases.coverage ? { prCoverage: cases.coverage } : {}),
plan: { sliceBudgetMs: opts.sliceBudgetMs!, jobs: opts.jobs!, estimatedSliceMs: plan.estimatedSliceMs, ciTimeoutMinutes: plan.ciTimeoutMinutes,
sliceCiTimeoutMinutes: plan.sliceCiTimeoutMinutes, codexSlices: codexSlicesOf(opts.tier, entries) },
@@ -466,6 +471,7 @@ export function buildRunManifest(opts: {
evalsAll: opts.evalsAll,
sliceCount,
selectionReason: cases.reason,
...(host !== 'claude' ? { host } : {}),
profile,
selection: cases.selection,
...(cases.coverage ? { prCoverage: cases.coverage } : {}),
@@ -479,6 +485,7 @@ export function parseRunManifest(raw: string): PaidRunManifest {
if (parsed.version !== 1) throw new Error(`unsupported manifest version: ${(parsed as { version?: unknown }).version}`);
if (!PAID_TIERS.includes(parsed.tier)) throw new Error(`manifest tier invalid: ${parsed.tier}`);
if (parsed.profile !== undefined && parsed.profile !== 'pr' && parsed.profile !== 'full') throw new Error('manifest profile invalid');
if (parsed.host !== undefined && (parsed.host === 'claude' || !EVAL_HOSTS.includes(parsed.host))) throw new Error(`manifest host invalid: ${parsed.host}`);
if (parsed.selection !== undefined) {
for (const [key, inventory] of [['e2e', E2E_TOUCHFILES], ['judges', LLM_JUDGE_TOUCHFILES]] as const) {
const ids = parsed.selection?.[key];
scripts/lib/paid-report.ts
+8 -3
View File
@@ -17,6 +17,7 @@ import { E2E_KINDS } from '../../test/helpers/touchfiles-data';
import { manualReviewProblem } from '../../test/helpers/cookie-workflow-manual-review';
import { writeNegativeReceipt, writePanelReceipt } from '../e2e-shard-reuse';
import { E2E_TOUCHFILES, E2E_TIERS, LLM_JUDGE_TOUCHFILES } from '../../test/helpers/touchfiles';
import { type EvalHost, hostSkipReason } from '../../test/helpers/e2e-hosts';
import { CASE_TEST_NAMES, type CaseTrialPlan, caseTestNamePattern, caseTrialPlan, fileCaseRegistration, shardCaseId, shardFile, trialShardKey } from './paid-cases';
import { type ManifestEntry, PAID_TEST_DURATIONS_FILE, type PaidRunManifest, type SliceResult, collectorOutcomeCounts, formatProfileCoverage, loadPaidTestDurations, mergePaidTestDurations, parseRunManifest, trialPanelKey, verifySliceResults, writePaidTestDurations } from './paid-plan';
import { DEFAULT_JOBS, type PaidCaseSelection, type PaidTier, ROOT, type ShardTrialRecord } from './paid-types';
@@ -170,6 +171,8 @@ export interface JUnitShardContext {
selection?: PaidCaseSelection;
/** Ids this file shard leaves to their isolated trial shards. */
excludeCases?: readonly string[];
/** The run's agent host (manifest.host); absent means claude. */
host?: EvalHost;
}
export const DESELECTION_REASONS = {
@@ -205,6 +208,8 @@ export function attributeJUnitCase(tc: JUnitCase, ctx: JUnitShardContext,
const tier = tiers[id];
if (tier !== undefined && tier !== ctx.tier) return { kind: 'deselected', reason: `${tier}-tier case (this lane runs ${ctx.tier})` };
if (ctx.excludeCases?.includes(id)) return { kind: 'deselected', reason: DESELECTION_REASONS.isolated };
const hostReason = hostSkipReason(id, ctx.host ?? 'claude');
if (hostReason) return { kind: 'deselected', reason: hostReason };
const pool = tier !== undefined ? ctx.selection?.e2e : Object.hasOwn(LLM_JUDGE_TOUCHFILES, id) ? ctx.selection?.judges : null;
if (pool && !pool.includes(id)) return { kind: 'deselected', reason: DESELECTION_REASONS.selection };
return { kind: 'case', id };
@@ -241,7 +246,7 @@ export const CENSUS_RED_GUIDE = 'docs/evals/census-red.md';
export function sliceArtifactName(root: string, slice: number, attempt: number): string {
const name = path.basename(root);
return /^(?:paid-slice|gate-census)-\d+-a\d+$/.test(name) ? name : `slice ${slice} attempt ${attempt}`;
return /^(?:paid-slice|gate-census)-\d+-a\d+(?:-[a-z0-9-]+)?$/.test(name) ? name : `slice ${slice} attempt ${attempt}`;
}
export function junitCensus(manifest: PaidRunManifest, artifacts: ReportArtifact[], recordsByShard: Map<string, any[]>,
@@ -254,7 +259,7 @@ export function junitCensus(manifest: PaidRunManifest, artifacts: ReportArtifact
if (outcome.trial || outcome.files.length !== 1) continue;
let xml = '';
try { xml = fs.readFileSync(path.join(root, 'shards', shardSlug([key]), 'junit.xml'), 'utf8'); } catch { continue; }
const ctx: JUnitShardContext = { key, tier: manifest.tier, selection: manifest.selection, excludeCases: entries.get(key)?.excludeCases };
const ctx: JUnitShardContext = { key, tier: manifest.tier, selection: manifest.selection, excludeCases: entries.get(key)?.excludeCases, host: manifest.host };
const byCase = new Map<string, JUnitCase[]>();
const reasons = new Map<string, number>();
for (const tc of parseJUnitCases(xml)) {
@@ -530,7 +535,7 @@ export function runPaidReport(reportDir: string, options: { writeDurations?: boo
const results = artifacts.filter(a => (a.result.attempt ?? 1) === primary).map(a => a.result);
const verdict = verifySliceResults(manifest, results);
const planned = manifest.entries.filter((e) => e.status === 'planned').length;
const lane = `${manifest.tier}/${manifest.profile ?? 'full'}${manifest.evalsAll ? ' census' : ''}`;
const lane = `${manifest.tier}/${manifest.profile ?? 'full'}${manifest.evalsAll ? ' census' : ''}${manifest.host ? ` on ${manifest.host}` : ''}`;
console.log(`[test:paid] report: ${results.length}/${manifest.sliceCount} slices, ${planned} planned shards, tier=${manifest.tier}, attempt ${primary}${attempts.length > 1 ? ` (later attempts ${attempts.slice(1).join(', ')} reported, never replacing it)` : ''}`);
for (const line of formatProfileCoverage(manifest)) console.log(line);
for (const result of [...results].sort((a, b) => a.sliceIndex - b.sliceIndex)) {
scripts/test-paid-shards.ts
+4
View File
@@ -73,6 +73,7 @@ import { readSessionLedger, type SessionLedgerRow } from '../test/helpers/sessio
import { preflightAnthropicApi } from '../test/helpers/anthropic-preflight';
import { e2eReuseLaneProblem, prepareE2EShardReuse, selectPlanReceipts } from './e2e-shard-reuse';
import { E2E_TOUCHFILES, E2E_TIERS } from '../test/helpers/touchfiles';
import { resolveEvalHost } from '../test/helpers/e2e-hosts';
import { scopeCodexAccess, shardFile, shardCaseId, shardTrial, trialShardKey, type CaseTrialPlan, caseTrialPlan, excludedCasesNamePattern, caseTestNamePattern, expandCaseShards, expandTrialShards, fileCaseRegistration, partitionCaseExclusions } from './lib/paid-cases';
import { retriesForFiles, trialPanelKey, sliceExecutionOrder, buildRunManifest, parseRunManifest, type SliceResult, sliceExitCode, guardTrialRecords, formatSlicePlan, formatCapacityPreflight, sliceDeadlineMs } from './lib/paid-plan';
import { caseSelection, runCaseDiagnosis, formatPanelLine, runPaidReport } from './lib/paid-report';
@@ -909,6 +910,9 @@ async function main(): Promise<number> {
if (manifest.tier !== options.tier) {
throw new Error(`manifest tier ${manifest.tier} != requested tier ${options.tier} — refusing a cross-tier run`);
}
if ((manifest.host ?? 'claude') !== resolveEvalHost()) {
throw new Error(`manifest host ${manifest.host ?? 'claude'} != EVALS_HOST ${resolveEvalHost()} — refusing a cross-host run`);
}
const profile = manifest.profile ?? 'full';
if (options.profileExplicit && options.profile !== profile) throw new Error(`manifest profile ${profile} != requested profile ${options.profile}`);
if (options.sliceIndex > manifest.sliceCount) {
scripts/test-pr-profile.ts
+1
View File
@@ -231,6 +231,7 @@ export const FREE_ONLY_PR_FILES = [
'test/helpers/auq-parallel-worker.ts',
'test/helpers/stored-zip.ts', // Read only by the free test-health report tests.
'scripts/free-test-durations.json',
'scripts/free-test-seed-allowlist.json', // Read only by the free seed ratchet (test/free-seed-ratchet.test.ts).
'scripts/paid-test-durations.json',
'scripts/ubicloud/**',
'capy/skill/**', // The vendored Capy skill (Drive bootstrapper): run by Capy agents, read by no paid case; test/capy-skill-wrapper.test.ts covers it.
test/ci-native-evidence.test.ts
+17 -11
View File
@@ -3,6 +3,7 @@ import * as fs from 'node:fs';
import * as os from 'node:os';
import * as path from 'node:path';
import { runPaidShard, shardSlug } from '../scripts/test-paid-shards';
import { CENSUS_ARMS } from '../scripts/census-arms';
const ROOT = path.resolve(import.meta.dir, '..');
const workflows = ['evals.yml', 'evals-periodic.yml', 'evals-marathon.yml'].map(name => ({
@@ -52,19 +53,24 @@ test('every direct CI paid executor binds a safe unique run/attempt/job/slice id
else expect(step.run).toContain('--user "$(id -u):$(id -g)"');
const env = executorEnv(job, step);
expect(env.EVALS_RUN_ID).toBeString();
// The gate census matrix is one row per census arm and planned slice (scripts/census-arms.ts).
const armed = job.strategy.matrix.include !== undefined;
for (const run of ['36302678692', '36302678693']) {
for (const attempt of ['1', '2']) {
// The planner sizes the matrix; cover more slices than any live plan.
expect(job.strategy.matrix.slice).toMatch(/^\$\{\{ fromJSON\(needs\.plan-slices\.outputs\.(?:[a-z]+_)*slices\) \}\}$/);
for (let slice = 1; slice <= 64; slice++) {
const id = render(env.EVALS_RUN_ID, {
'github.run_id': `${run}${workflowIndex}`,
'github.run_attempt': attempt, 'matrix.slice': String(slice),
});
expect(id).toMatch(/^[A-Za-z0-9_-]+$/);
expect(id.length).toBeLessThan(120);
expect(ids.has(id)).toBe(false);
ids.add(id);
expect(armed ? job.strategy.matrix.include : job.strategy.matrix.slice)
.toMatch(armed ? /^\$\{\{ fromJSON\(needs\.plan-slices\.outputs\.gate_matrix\) \}\}$/ : /^\$\{\{ fromJSON\(needs\.plan-slices\.outputs\.(?:[a-z]+_)*slices\) \}\}$/);
for (const arm of armed ? Object.keys(CENSUS_ARMS) : ['']) {
for (let slice = 1; slice <= 64; slice++) {
const id = render(env.EVALS_RUN_ID, {
'github.run_id': `${run}${workflowIndex}`,
'github.run_attempt': attempt, 'matrix.slice': String(slice), 'matrix.arm': arm,
});
expect(id).toMatch(/^[A-Za-z0-9_-]+$/);
expect(id.length).toBeLessThan(120);
expect(ids.has(id)).toBe(false);
ids.add(id);
}
}
}
}
@@ -79,7 +85,7 @@ for (const { name, jobName, job, step } of executors) {
fs.mkdirSync(home); fs.mkdirSync(bin); fs.mkdirSync(path.join(root, 'test'));
const configured = executorEnv(job, step);
const runId = render(configured.EVALS_RUN_ID, {
'github.run_id': '36302678692', 'github.run_attempt': '2', 'matrix.slice': '4',
'github.run_id': '36302678692', 'github.run_attempt': '2', 'matrix.slice': '4', 'matrix.arm': 'codex-sol',
});
const evalDir = path.join(root, path.basename(configured.GSTACK_EVAL_DIR));
const file = 'test/native-launch.test.ts';
test/ci-paid-coordination.test.ts
+2 -1
View File
@@ -113,7 +113,8 @@ describe('paid CI coordination stays off the eval image', () => {
// A confirmed verdict reuse (R2a/R2) is the one PR run that executes no slice.
expect(executor.if).toBe("${{ !cancelled() && needs.build-image.result == 'success' && needs.plan-slices.result == 'success' && needs.plan-slices.outputs.gate_reuse != 'true' }}");
} else {
expect(executor.if).toBeUndefined();
// A census-only run (monthly cron or census_arms dispatch) executes no periodic slice.
expect(executor.if).toBe("${{ needs.plan-slices.outputs.periodic_lane == 'true' }}");
}
expect(executor.steps.some(step => step.run === 'bun run build')).toBe(true);
expect(executor.steps.some(step => step.uses === './.github/actions/restore-deps')).toBe(true);
test/codex-host.test.ts
+287
View File
@@ -0,0 +1,287 @@
/**
* The Codex host for paid gate cases (GSTA-49 TM2): host selection with
* skip-with-reason (never a failure), per-case host metadata over every gate
* case, real Codex cost accounting against captured `codex exec --json`
* usage events (Codex CLI 0.160.0, gpt-6.1-sol), and runner parity.
*/
import { afterEach, describe, expect, test } from 'bun:test';
import * as fs from 'node:fs';
import * as os from 'node:os';
import * as path from 'node:path';
import { spawnSync } from 'node:child_process';
import { CLAUDE_ONLY_REASONS, E2E_HOSTS, hostSkipReason, resolveEvalHost } from './helpers/e2e-hosts';
import { E2E_TIERS, E2E_TOUCHFILES } from './helpers/touchfiles';
import { addCodexTurnUsage, codexUsageCostUsd, NO_CODEX_USAGE, parseCodexJSONL, type CodexResult } from './helpers/codex-session-runner';
import { runRecordedCodexEval } from './helpers/codex-eval';
import { codexHostExecArgs, codexHostModel, codexHostToolCalls, codexHostTranscript, unwrapShellCommand } from './helpers/codex-host-runner';
import { coverageAuditReadEvidence } from './helpers/coverage-audit-evidence';
import { runSkillTest } from './helpers/session-runner';
import { readSessionLedger } from './helpers/session-ledger';
import { preflightAnthropicApi } from './helpers/anthropic-preflight';
import type { EvalTestEntry } from './helpers/eval-store';
import { buildRunManifest } from '../scripts/test-paid-shards';
import { codexShardAccess, fileCaseRegistration, partitionHostExclusions, scopeCodexAccess, shardCaseId, shardFile } from '../scripts/lib/paid-cases';
import { parseRunManifest } from '../scripts/lib/paid-plan';
import { attributeJUnitCase } from '../scripts/lib/paid-report';
const ROOT = path.resolve(import.meta.dir, '..');
const fixture = (name: string) => fs.readFileSync(path.join(ROOT, 'test/fixtures/codex-host', name), 'utf8').split('\n').filter(Boolean);
const COMMANDS = fixture('exec-commands.jsonl');
const FILE_CHANGE = fixture('exec-file-change.jsonl');
const gateCases = Object.keys(E2E_TIERS).filter(id => E2E_TIERS[id] === 'gate').sort();
const adapterCases = Object.keys(E2E_HOSTS).filter(id => E2E_HOSTS[id] === 'both');
const scratch: string[] = [];
const tempDir = (prefix: string) => { const dir = fs.mkdtempSync(path.join(os.tmpdir(), prefix)); scratch.push(dir); return dir; };
afterEach(() => { for (const dir of scratch.splice(0)) fs.rmSync(dir, { recursive: true, force: true }); });
describe('host selection: Claude-only cases skip with a reason, never fail', () => {
test('EVALS_HOST defaults to claude, accepts codex and refuses anything else', () => {
expect(resolveEvalHost({})).toBe('claude');
expect(resolveEvalHost({ EVALS_HOST: ' ' })).toBe('claude');
expect(resolveEvalHost({ EVALS_HOST: 'codex' })).toBe('codex');
expect(() => resolveEvalHost({ EVALS_HOST: 'gemini' })).toThrow('EVALS_HOST must be one of claude, codex');
});
test('the Anthropic preflight never pings claude on the Codex host', () => {
const pinged: string[] = [];
const spawn = ((cmd: string) => { pinged.push(cmd); return { status: 127, stdout: '', stderr: '' }; }) as unknown as typeof spawnSync;
expect(preflightAnthropicApi({ EVALS_HOST: 'codex' }, spawn)).toBe('skipped');
expect(pinged).toEqual([]);
expect(() => preflightAnthropicApi({}, spawn)).toThrow('`claude` not found on PATH');
expect(pinged).toEqual(['sh']);
});
test('every case runs on Claude; on Codex only adapter cases run and the rest carry their reason', () => {
for (const id of gateCases) expect(hostSkipReason(id, 'claude')).toBeNull();
for (const id of adapterCases) expect(hostSkipReason(id, 'codex')).toBeNull();
expect(hostSkipReason('plan-mode-no-op', 'codex')).toBe(`Claude-only on the codex host: ${CLAUDE_ONLY_REASONS.pty}`);
expect(hostSkipReason('ship-docsync-store', 'codex')).toContain('not ported to the Codex host');
expect(hostSkipReason('plan-ceo-review', 'codex')).toContain('no Codex host metadata');
});
test('the module selection drops Claude-only cases on the Codex host', () => {
const root = tempDir('codex-host-root-');
fs.mkdirSync(path.join(root, 'home', '.codex'), { recursive: true });
const run = spawnSync('bun', ['-e', "const h = await import('./test/helpers/e2e-helpers'); console.log(JSON.stringify(h.selectedTests))"], {
cwd: ROOT, encoding: 'utf8', timeout: 60_000,
env: { ...process.env, EVALS: '1', EVALS_TIER: 'gate', EVALS_HOST: 'codex', EVALS_PREFLIGHT_OK: '1', GSTACK_CODEX_HOST_ROOT: root,
EVALS_SELECTION_JSON: JSON.stringify({ selected: null, reason: 'test' }) },
});
expect(run.status, run.stderr).toBe(0);
expect((JSON.parse(run.stdout.trim().split('\n').at(-1)!) as string[]).sort()).toEqual([...adapterCases].sort());
expect(run.stderr).toContain(`EVALS_HOST=codex: ${adapterCases.length} tests; ${gateCases.length - adapterCases.length} Claude-only skipped`);
});
test('the planner excludes Claude-only shards with their reason and plans every adapter case', () => {
const manifest = buildRunManifest({ tier: 'gate', profile: 'full', sliceBudgetMs: 420_000, jobs: 2, evalsAll: true, skipJudges: true,
env: { EVALS_ALL: '1', EVALS_HOST: 'codex' }, rootDir: ROOT });
expect(manifest.host).toBe('codex');
const planned = manifest.entries.filter(entry => entry.status === 'planned');
const casesOf = (key: string) => {
const id = shardCaseId(key);
if (id !== null) return [id];
return fileCaseRegistration(shardFile(key), fs.readFileSync(path.join(ROOT, shardFile(key)), 'utf8')).registered.filter(c => E2E_TIERS[c] === 'gate');
};
const reachable = new Set(planned.flatMap(entry => casesOf(entry.file)).filter(id => E2E_HOSTS[id] === 'both'));
expect([...reachable].sort()).toEqual([...adapterCases].sort());
for (const entry of planned) expect(casesOf(entry.file).some(id => E2E_HOSTS[id] === 'both'), entry.file).toBe(true);
const hostExcluded = manifest.entries.filter(entry => entry.status === 'excluded' && entry.reason?.includes('Claude-only on the codex host'));
expect(hostExcluded.length).toBeGreaterThan(0);
for (const entry of hostExcluded) expect(entry.reason, entry.file).toStartWith('skipped: ');
expect(manifest.entries.some(entry => entry.file === 'test/skill-e2e-ship-docsync.test.ts#ship-docsync-store' && entry.status === 'excluded')).toBe(true);
});
test('the Claude host plans exactly as before, with no host on the manifest', () => {
const manifest = buildRunManifest({ tier: 'gate', profile: 'full', sliceBudgetMs: 420_000, jobs: 2, evalsAll: true, skipJudges: true,
env: { EVALS_ALL: '1' }, rootDir: ROOT });
expect(manifest.host).toBeUndefined();
expect(manifest.entries.some(entry => entry.reason?.includes('Claude-only'))).toBe(false);
expect(partitionHostExclusions(['a.test.ts', 'b.test.ts#x'], 'gate', 'claude')).toEqual({ runnable: ['a.test.ts', 'b.test.ts#x'], excluded: [] });
});
test('the report deselects a skipped Claude-only testcase on the Codex host (zero credit, never SKIPPED or failed)', () => {
const tc = { name: 'review-dashboard-via', classname: '', outcome: 'skipped' as const, timeMs: 0, line: 10 };
const key = 'test/skill-e2e-review-attribution.test.ts';
expect(attributeJUnitCase(tc, { key, tier: 'gate', host: 'codex' })).toEqual({ kind: 'deselected', reason: hostSkipReason('review-dashboard-via', 'codex')! });
expect(attributeJUnitCase(tc, { key, tier: 'gate' })).toEqual({ kind: 'case', id: 'review-dashboard-via' });
expect(attributeJUnitCase({ ...tc, name: 'review-base-branch' }, { key, tier: 'gate', host: 'codex' })).toEqual({ kind: 'case', id: 'review-base-branch' });
});
test('a manifest names only a non-default host, and the executor refuses a cross-host run', () => {
const base = { version: 1, tier: 'gate', evalsAll: true, sliceCount: 1, selectionReason: 'x', entries: [] };
expect(parseRunManifest(JSON.stringify({ ...base, host: 'codex' })).host).toBe('codex');
expect(() => parseRunManifest(JSON.stringify({ ...base, host: 'claude' }))).toThrow('manifest host invalid');
expect(() => parseRunManifest(JSON.stringify({ ...base, host: 'gemini' }))).toThrow('manifest host invalid');
const plan = path.join(tempDir('codex-host-plan-'), 'manifest.json');
fs.writeFileSync(plan, JSON.stringify({ ...base, host: 'codex' }));
const run = spawnSync('bun', ['run', 'scripts/test-paid-shards.ts', '--tier', 'gate', '--plan', plan, '--slice', '1', '--list'], {
cwd: ROOT, encoding: 'utf8', timeout: 60_000, env: { ...process.env, EVALS_HOST: 'claude', EVALS_TIER: 'gate' },
});
expect(run.status).not.toBe(0);
expect(run.stderr + run.stdout).toContain('manifest host codex != EVALS_HOST claude');
});
});
describe('per-case host metadata', () => {
test('covers every gate case exactly once, and nothing else', () => {
expect(Object.keys(E2E_HOSTS).sort()).toEqual(gateCases);
for (const id of Object.keys(E2E_HOSTS)) expect(Object.hasOwn(E2E_TOUCHFILES, id), id).toBe(true);
});
test('classifies 52 adapter-only, 29 Claude-specific, 26 rework and 1 host-neutral case', () => {
const counts: Record<string, number> = {};
for (const support of Object.values(E2E_HOSTS)) counts[support] = (counts[support] ?? 0) + 1;
expect(counts.both).toBe(52);
expect(counts.rework).toBe(26);
expect(counts['host-neutral']).toBe(1);
expect(['pty', 'sdk', 'subagents', 'skill-tool', 'hermetic', 'self-host'].reduce((sum, reason) => sum + (counts[reason] ?? 0), 0)).toBe(29);
});
});
describe('Codex cost accounting from captured usage events', () => {
test('parses every token class of turn.completed (cache reads and writes are subsets of input)', () => {
const commands = parseCodexJSONL(COMMANDS);
expect(commands.usage).toEqual({ input: 25009, cached_input: 12437, cache_write_input: 12566, output: 86, reasoning_output: 0 });
expect(commands.tokens).toBe(25095);
expect(parseCodexJSONL(FILE_CHANGE).usage).toEqual({ input: 25020, cached_input: 12440, cache_write_input: 12574, output: 137, reasoning_output: 0 });
expect(parseCodexJSONL(['{"type":"thread.started","thread_id":"t"}']).usage).toBeNull();
const twoTurns = [COMMANDS, FILE_CHANGE].map(lines => JSON.parse(lines.find(line => line.includes('turn.completed'))!).usage)
.reduce(addCodexTurnUsage, NO_CODEX_USAGE);
expect(twoTurns).toEqual({ input: 50029, cached_input: 24877, cache_write_input: 25140, output: 223, reasoning_output: 0 });
});
test('prices with lib/pricing.ts: uncached input (cache writes included) at input, cache reads at the cached rate', () => {
const usage = parseCodexJSONL(COMMANDS).usage!;
// gpt-6.1-sol: 12,572 x $2 + 12,437 x $0.10 + 86 x $10 per million.
expect(codexUsageCostUsd(usage, 'gpt-6.1-sol')).toBe(0.027248);
expect(codexUsageCostUsd(parseCodexJSONL(FILE_CHANGE).usage!, 'gpt-6.1-sol')).toBe(0.027774);
// gpt-6-astra: 12,572 x $10 + 12,437 x $1 + 86 x $50 per million.
expect(codexUsageCostUsd(usage, 'gpt-6-astra')).toBe(0.142457);
expect(codexUsageCostUsd(usage, 'gpt-0-unpriced')).toBeNull();
});
test('runRecordedCodexEval records real cost and billing instead of cost_known: false', async () => {
const evalDir = tempDir('codex-host-ledger-');
const previous = process.env.GSTACK_EVAL_DIR;
process.env.GSTACK_EVAL_DIR = evalDir;
try {
const recorded: EvalTestEntry[] = [];
const result: CodexResult = { ...parseCodexJSONL(COMMANDS), exitCode: 0, durationMs: 5, rawLines: COMMANDS, stderr: '', model: 'gpt-6.1-sol' };
await runRecordedCodexEval({ name: 'cost-case', suite: 's', budgetMs: 10_000, run: async () => result, validate: () => {}, record: entry => recorded.push(entry) });
expect(recorded[0]).toMatchObject({ passed: true, cost_usd: 0.027248, model: 'gpt-6.1-sol', token_usage: result.usage });
expect(recorded[0]!.cost_known).toBeUndefined();
const noTurn: CodexResult = { ...parseCodexJSONL([]), exitCode: 0, durationMs: 5, rawLines: [], stderr: '' };
await runRecordedCodexEval({ name: 'no-turn', suite: 's', budgetMs: 10_000, run: async () => noTurn, validate: () => {}, record: entry => recorded.push(entry) });
expect(recorded[1]).toMatchObject({ cost_usd: 0, cost_known: false });
const rows = readSessionLedger(evalDir);
expect(rows.map(row => [row.test_name, row.billed])).toEqual([['cost-case', true], ['no-turn', false]]);
expect(rows[0]).toMatchObject({ runner: 'codex', model: 'gpt-6.1-sol', cost_usd: 0.027248, tokens: result.usage });
} finally {
if (previous === undefined) delete process.env.GSTACK_EVAL_DIR; else process.env.GSTACK_EVAL_DIR = previous;
}
});
});
describe('Codex runner parity', () => {
test('maps command_execution to Bash (unwrapped, with output) and file_change to Write/Edit', () => {
expect(codexHostToolCalls(COMMANDS)).toEqual([
{ tool: 'Bash', input: { command: "printf 'hi' > hello.txt\nprintf 'hello' > hello.txt\ncat hello.txt" }, output: 'hello' },
]);
expect(codexHostToolCalls(FILE_CHANGE)).toEqual([
{ tool: 'Write', input: { file_path: '/tmp/codex-host-fixture/notes.md', kind: 'add' }, output: '' },
{ tool: 'Edit', input: { file_path: '/tmp/codex-host-fixture/notes.md', kind: 'update' }, output: '' },
]);
});
test('the transcript is the Claude stream-json shape the case observers read', () => {
const output = '`cat hello.txt` output: `hello`';
const transcript = codexHostTranscript(COMMANDS, '/tmp/codex-host-fixture', output);
expect(transcript[0]).toEqual({ type: 'system', subtype: 'init', cwd: '/tmp/codex-host-fixture', session_id: '01a150b3-ae5a-7932-ba51-4c295c66adf4', tools: [] });
expect(transcript.slice(1).map(event => [event.type, event.message?.content[0].type ?? event.subtype])).toEqual([
['assistant', 'text'], ['assistant', 'tool_use'], ['user', 'tool_result'], ['assistant', 'text'], ['result', 'success']]);
expect(transcript[2].message.content[0]).toEqual({ type: 'tool_use', id: 'item_1', name: 'Bash', input: { command: "printf 'hi' > hello.txt\nprintf 'hello' > hello.txt\ncat hello.txt" } });
expect(transcript[3].message.content[0]).toEqual({ type: 'tool_result', tool_use_id: 'item_1', content: 'hello', is_error: false });
expect(transcript.at(-1)).toMatchObject({ type: 'result', result: output });
const edits = codexHostTranscript(FILE_CHANGE, '/tmp/codex-host-fixture', '').filter(event => event.type === 'assistant' && event.message.content[0].type === 'tool_use');
expect(edits.map(event => [event.message.content[0].name, event.message.content[0].input.file_path])).toEqual([
['Write', '/tmp/codex-host-fixture/notes.md'], ['Edit', '/tmp/codex-host-fixture/notes.md']]);
// A Codex `cat` of a fixture file is a read the coverage-audit evidence credits, as a native Bash read is.
const source = { path: '/w/src/billing.ts', content: 'export const a = 1;\n' };
const tests = { path: '/w/test/billing.test.ts', content: 'test("a", () => {});\n' };
const read = (id: string, file: string, out: string) => JSON.stringify({ type: 'item.completed', item: { id, type: 'command_execution', command: `/bin/bash -lc 'cat ${file}'`, aggregated_output: out, exit_code: 0, status: 'completed' } });
const lines = ['{"type":"thread.started","thread_id":"t1"}', read('item_0', 'src/billing.ts', source.content), read('item_1', 'test/billing.test.ts', tests.content)];
expect(coverageAuditReadEvidence(codexHostTranscript(lines, '/w', ''), { cwd: '/w', source, tests })).toEqual({ sourceRead: true, testsRead: true });
const failed = lines.map(line => line.replace('"exit_code":0', '"exit_code":1'));
expect(coverageAuditReadEvidence(codexHostTranscript(failed, '/w', ''), { cwd: '/w', source, tests })).toEqual({ sourceRead: false, testsRead: false });
});
test('unwraps only a single well-formed bash -lc word', () => {
expect(unwrapShellCommand("/bin/bash -lc 'git diff main...HEAD'")).toBe('git diff main...HEAD');
expect(unwrapShellCommand("/bin/bash -lc 'echo '\"'\"'x'\"'\"''")).toBe("echo 'x'");
expect(unwrapShellCommand('/bin/bash -lc "echo \\"\\$HOME\\""')).toBe('echo "$HOME"');
expect(unwrapShellCommand('bash -lc ls')).toBe('ls');
expect(unwrapShellCommand('git status')).toBe('git status');
expect(unwrapShellCommand("/bin/bash -lc 'unterminated")).toBe("/bin/bash -lc 'unterminated");
expect(unwrapShellCommand("/bin/bash -lc 'a' 'b'")).toBe("/bin/bash -lc 'a' 'b'");
});
test('sandbox, effort and model settings', () => {
expect(codexHostExecArgs('gpt-6.1-sol', 'go', {})).toEqual(['exec', '--json', '-s', 'danger-full-access', '--skip-git-repo-check', '--model', 'gpt-6.1-sol', 'go']);
expect(codexHostExecArgs('gpt-6.1-sol', 'go', { GSTACK_CODEX_EFFORT: 'high' })).toContain('model_reasoning_effort="high"');
expect(codexHostExecArgs('m', 'go', { GSTACK_CODEX_SANDBOX: 'workspace-write' })).toEqual(
['exec', '--json', '-s', 'workspace-write', '--skip-git-repo-check', '--model', 'm', '-c', 'sandbox_workspace_write.network_access=true', 'go']);
expect(() => codexHostExecArgs('m', 'go', { GSTACK_CODEX_SANDBOX: 'none' })).toThrow('GSTACK_CODEX_SANDBOX');
expect(() => codexHostExecArgs('m', 'go', { GSTACK_CODEX_EFFORT: 'high" -c x="y' })).toThrow('GSTACK_CODEX_EFFORT');
expect(codexHostModel('claude-opus-4-7', { GSTACK_CODEX_MODEL: 'gpt-6.1-sol' })).toBe('gpt-6.1-sol');
expect(codexHostModel('gpt-6-astra', { GSTACK_CODEX_MODEL: 'gpt-6.1-sol' })).toBe('gpt-6-astra');
expect(codexHostModel(undefined, {})).toBe('gpt-6-astra');
});
test('every shard on the Codex host gets the CI Codex install', () => {
expect(codexShardAccess(['test/skill-e2e-review.test.ts'], 'gate')).toBe('none');
expect(codexShardAccess(['test/skill-e2e-review.test.ts'], 'gate', 'codex')).toBe('path');
const env: NodeJS.ProcessEnv = { EVALS_HOST: 'codex', EVALS_TIER: 'gate', PATH: '/usr/bin', GSTACK_CI_CODEX_BIN_DIR: '/opt/codex/bin', GSTACK_CI_CODEX_HOME: '/home/runner/.ci-codex' };
scopeCodexAccess(env, ['test/skill-e2e-review.test.ts']);
expect(env.PATH).toBe(`/opt/codex/bin${path.delimiter}/usr/bin`);
expect(env.CODEX_HOME).toBe('/home/runner/.ci-codex');
});
test('runSkillTest on EVALS_HOST=codex runs codex exec and returns a priced SkillTestResult', async () => {
const dir = tempDir('codex-host-run-');
const root = path.join(dir, 'runtime');
fs.mkdirSync(path.join(root, 'home', '.codex'), { recursive: true });
const bin = path.join(dir, 'bin');
fs.mkdirSync(bin);
const argsFile = path.join(dir, 'args.txt');
fs.writeFileSync(path.join(bin, 'codex'), `#!/bin/sh\nprintf '%s\\n' "$@" > '${argsFile}'\nprintf '%s\\n' "$CODEX_HOME" >> '${argsFile}'\ncat '${path.join(ROOT, 'test/fixtures/codex-host/exec-commands.jsonl')}'\n`, { mode: 0o755 });
const evalDir = path.join(dir, 'evals');
const saved = { ...process.env };
Object.assign(process.env, { EVALS_HOST: 'codex', GSTACK_CODEX_MODEL: 'gpt-6.1-sol', GSTACK_CODEX_HOST_ROOT: root, GSTACK_EVAL_DIR: evalDir, PATH: `${bin}${path.delimiter}${process.env.PATH}` });
try {
const result = await runSkillTest({ prompt: 'Run the fixture.', workingDirectory: dir, model: 'claude-opus-4-7', timeout: 30_000, testName: 'host-switch' });
expect(result).toMatchObject({ exitReason: 'success', model: 'gpt-6.1-sol', output: '`cat hello.txt` output: `hello`', browseErrors: [] });
expect(result.toolCalls.map(call => call.input.command)).toEqual(["printf 'hi' > hello.txt\nprintf 'hello' > hello.txt\ncat hello.txt"]);
expect(result.costEstimate).toMatchObject({ estimatedCost: 0.027248, estimatedTokens: 25095, turnsUsed: 3 });
expect(result.tokenUsage).toEqual(parseCodexJSONL(COMMANDS).usage!);
const args = fs.readFileSync(argsFile, 'utf8').trim().split('\n');
expect(args.slice(0, 7)).toEqual(['exec', '--json', '-s', 'danger-full-access', '--skip-git-repo-check', '--model', 'gpt-6.1-sol']);
expect(args.at(-2)).toBe('Run the fixture.');
expect(args.at(-1)).toBe(path.join(root, 'home', '.codex'));
expect(readSessionLedger(evalDir)).toEqual([expect.objectContaining({ runner: 'codex', test_name: 'host-switch', end: 'completed', billed: true, cost_usd: 0.027248 })]);
// The native lifecycle sees the codex group owner at spawn and settles after its exit.
const seen: string[] = [];
await runSkillTest({ prompt: 'Run the fixture.', workingDirectory: dir, timeout: 30_000, testName: 'host-lifecycle', nativeLifecycle: {
onSpawn: pid => { seen.push(`spawn ${pid > 0}`); },
onSettled: async ({ deadline, exited }) => { seen.push(`settled ${exited} ${deadline > Date.now()}`); },
} });
expect(seen).toEqual(['spawn true', 'settled true true']);
await expect(runSkillTest({ prompt: 'Run the fixture.', workingDirectory: dir, timeout: 30_000, testName: 'host-lifecycle-refused', nativeLifecycle: {
onSpawn: () => { throw new Error('native process is not group owner'); },
onSettled: async () => {},
} })).rejects.toThrow('native process is not group owner');
} finally {
for (const key of Object.keys(process.env)) if (!(key in saved)) delete process.env[key];
Object.assign(process.env, saved);
}
});
});
test/evals-workflow-wiring.test.ts
+153 -6
View File
@@ -22,7 +22,10 @@
import { describe, test, expect } from 'bun:test';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
import { spawnSync } from 'child_process';
import { buildRunManifest, isCodexShard, isOverlayTestFile, parseCliOptions, resolvePaidShardTimeoutMs, sliceExecutionOrder, sliceSupervisedWallMs, CI_SETUP_ALLOWANCE_MINUTES } from '../scripts/test-paid-shards';
import { CENSUS_ARMS, MONTHLY_CENSUS_ARMS, MONTHLY_CENSUS_SCHEDULE, WEEKLY_CENSUS_ARMS, WEEKLY_CENSUS_SCHEDULE, censusArmEnv, censusMatrix, selectCensus } from '../scripts/census-arms';
const ROOT = path.join(import.meta.dir, '..');
const read = (rel: string) => fs.readFileSync(path.join(ROOT, rel), 'utf-8');
@@ -40,7 +43,7 @@ function plannerSites(source: string): Array<{ manifest: string; budgetSeconds:
type Step = { id?: string; name?: string; run?: string; uses?: string; env?: Record<string, string>; with?: Record<string, string> };
type Job = { needs?: string[]; env?: Record<string, string>; outputs?: Record<string, string>; 'timeout-minutes': string | number;
strategy?: { 'max-parallel': number; matrix: { slice: string } }; steps: Step[] };
strategy?: { 'max-parallel': number; matrix: { slice?: string; include?: string } }; steps: Step[] };
/**
* An executor's matrix and timeout must come from the planner step that wrote
@@ -159,7 +162,6 @@ describe('evals.yml sliced-lane wiring (post-matrix)', () => {
describe('evals-periodic.yml sliced-lane wiring', () => {
const lanes = [
{ source: periodicYml, name: 'evals-periodic.yml', executor: 'eval-slices', prefix: 'periodic_', tier: 'periodic' },
{ source: periodicYml, name: 'evals-periodic.yml', executor: 'gate-census', prefix: 'gate_', tier: 'gate' },
{ source: evalsYml, name: 'evals.yml', executor: 'eval-slices', prefix: '', tier: 'gate' },
{ source: marathonYml, name: 'evals-marathon.yml', executor: 'eval-slices', prefix: '', tier: 'marathon' },
] as const;
@@ -200,6 +202,64 @@ describe('evals-periodic.yml sliced-lane wiring', () => {
});
}
test('evals-periodic.yml:gate-census — one row per census arm and planned slice with its plan\'s ceiling, and every row of a scheduled census starts at once', () => {
const workflow = Bun.YAML.parse(periodicYml) as { env?: Record<string, string>; jobs: Record<string, Job> };
const planner = workflow.jobs['plan-slices']!;
const executor = workflow.jobs['gate-census']!;
expect(executor.needs).toContain('plan-slices');
expect(executor.strategy!.matrix).toEqual({ include: '${{ fromJSON(needs.plan-slices.outputs.gate_matrix) }}' });
expect(executor['timeout-minutes']).toBe('${{ matrix.timeout }}');
expect(executor.steps[0]!.run).toBe('echo "GSTACK_SLICE_JOB_STARTED_AT=$(date +%s)" >> "$GITHUB_ENV"');
expect(planner.outputs!.gate_matrix).toBe('${{ steps.gate-matrix.outputs.gate_matrix }}');
expect(planner.steps.find(step => step.id === 'gate-matrix')!.run).toBe('bun --no-install run scripts/census-arms.ts --matrix /tmp/gate-census-plan "$ARMS" >> "$GITHUB_OUTPUT"');
const emit = planner.steps.filter(step => step.run?.includes('--emit-plan "/tmp/gate-census-plan/$arm/manifest.json" '));
expect(emit).toHaveLength(1);
expect(emit[0]!.run).toContain('mapfile -t arm_env < <(bun --no-install run scripts/census-arms.ts --env "$arm")');
expect(emit[0]!.run).toContain('env "${arm_env[@]}" EVALS_TIER=gate bun run scripts/test-paid-shards.ts');
const execute = executor.steps.filter(step => step.run?.includes('--plan '));
expect(execute).toHaveLength(1);
expect(execute[0]!.run).toContain('--plan /tmp/gate-census-plan/${{ matrix.arm }}/manifest.json --slice ${{ matrix.slice }}');
// The executor runs with its arm's host and model, and downloads every arm's plan.
expect(executor.steps.find(step => step.name === "Select the census arm's host and model")!.run).toBe('bun --no-install run scripts/census-arms.ts --env "$ARM" >> "$GITHUB_ENV"');
expect(executor.steps.some(step => step.with?.path === '/tmp/gate-census-plan')).toBe(true);
const cliArgs = (run: string) => {
const command = /\bbun(?: --no-install)? run scripts\/test-paid-shards\.ts (.*)$/m.exec(run)!;
return command[1]!.replace(/\$\{\{\s*matrix\.slice\s*\}\}/g, '1').replace(/\$\{\{\s*matrix\.arm\s*\}\}/g, 'claude-opus').trim().split(/\s+/);
};
const planned = parseCliOptions(cliArgs(emit[0]!.run!), { ...workflow.env, ...emit[0]!.env, EVALS_ALL: '1', EVALS_PROFILE: 'full' });
const active = parseCliOptions(cliArgs(execute[0]!.run!), { ...workflow.env, ...executor.env, ...execute[0]!.env, EVALS_PROFILE: 'full' });
expect(planned.tier).toBe('gate');
expect(active.tier).toBe('gate');
expect(active.jobs).toBe(planned.jobs);
expect(execute[0]!.env?.EVALS_JOBS).toBe(String(planned.jobs));
const planDir = fs.mkdtempSync(path.join(os.tmpdir(), 'census-arms-'));
try {
for (const arm of Object.keys(CENSUS_ARMS)) {
const env = { ...workflow.env, ...emit[0]!.env, EVALS_ALL: '1', EVALS_PROFILE: 'full', ...censusArmEnv(arm) };
const manifest = buildRunManifest({ tier: 'gate', profile: 'full', sliceBudgetMs: planned.sliceBudgetMs!, jobs: planned.jobs,
evalsAll: true, env, rootDir: ROOT, skipJudges: planned.skipJudges });
expect(manifest.host ?? 'claude').toBe(CENSUS_ARMS[arm]!.host);
const sliceFiles = Array.from({ length: manifest.sliceCount }, (_, i) => sliceExecutionOrder(
manifest.entries.filter(entry => entry.status === 'planned' && entry.slice === i + 1)).map(entry => entry.file));
const ceilings = sliceFiles.map(files => Math.ceil(Math.max(2 * planned.sliceBudgetMs!,
...files.map(file => resolvePaidShardTimeoutMs([file])),
files.some(isOverlayTestFile) ? sliceSupervisedWallMs(files, planned.jobs) : 0) / 60_000) + CI_SETUP_ALLOWANCE_MINUTES);
expect(manifest.plan!.sliceCiTimeoutMinutes).toEqual(ceilings);
expect(manifest.plan!.ciTimeoutMinutes).toBeLessThanOrEqual(360);
fs.mkdirSync(path.join(planDir, arm));
fs.writeFileSync(path.join(planDir, arm, 'manifest.json'), JSON.stringify(manifest));
expect(censusMatrix([arm], planDir)).toEqual(ceilings.map((timeout, i) => ({ arm, slice: i + 1, timeout })));
}
for (const arms of [WEEKLY_CENSUS_ARMS, MONTHLY_CENSUS_ARMS]) {
const rows = censusMatrix(arms, planDir);
expect(new Set(rows.map(row => `${row.arm}/${row.slice}`)).size).toBe(rows.length);
expect(rows.length, `${arms.join('+')} rows exceed max-parallel`).toBeLessThanOrEqual(executor.strategy!['max-parallel']);
}
} finally {
fs.rmSync(planDir, { recursive: true, force: true });
}
});
test('planner/executor/report tier=periodic agree and plan with the ~7-minute budget (W5c)', () => {
expect(periodicYml).toMatch(/EVALS_TIER=periodic bun --no-install run scripts\/test-paid-shards\.ts --tier periodic --emit-plan/);
expect(periodicYml).toMatch(/EVALS_TIER=periodic bun run scripts\/test-paid-shards\.ts --tier periodic --plan .* --slice /);
@@ -207,7 +267,7 @@ describe('evals-periodic.yml sliced-lane wiring', () => {
// Periodic work and the full gate census have distinct immutable plans.
expect(plannerSites(periodicYml)).toEqual([
{ manifest: '/tmp/paid-plan/manifest.json', budgetSeconds: 420, jobs: 2 },
{ manifest: '/tmp/gate-census-plan/manifest.json', budgetSeconds: 420, jobs: 2 },
{ manifest: '"/tmp/gate-census-plan/$arm/manifest.json"', budgetSeconds: 420, jobs: 2 },
]);
});
});
@@ -228,7 +288,7 @@ describe('evals-periodic.yml host-run Codex slices', () => {
expect(matrixStep.run).toContain('} >> "$GITHUB_OUTPUT"');
expect(planner.outputs!.periodic_codex_slices).toBe('${{ steps.periodic-matrix.outputs.codex_slices }}');
expect(codex.needs).toEqual(['build-image', 'plan-slices']);
expect(codex.if).toBe("${{ needs.plan-slices.outputs.periodic_codex_slices != '[]' }}");
expect(codex.if).toBe("${{ needs.plan-slices.outputs.periodic_lane == 'true' && needs.plan-slices.outputs.periodic_codex_slices != '[]' }}");
expect(codex.strategy!.matrix.slice).toBe('${{ fromJSON(needs.plan-slices.outputs.periodic_codex_slices) }}');
expect(codex['timeout-minutes']).toBe('${{ fromJSON(needs.plan-slices.outputs.periodic_slice_timeouts)[matrix.slice] }}');
expect(codex.steps[0]!.run).toBe('echo "GSTACK_SLICE_JOB_STARTED_AT=$(date +%s)" >> "$GITHUB_ENV"');
@@ -350,7 +410,7 @@ describe('panel verdict surfaces (eval reliability policy)', () => {
test('planners size the capacity preflight with their executor cap', () => {
for (const [source, executor, manifest] of [[evalsYml, 'eval-slices', '/tmp/paid-plan/manifest.json'],
[periodicYml, 'eval-slices', '/tmp/paid-plan/manifest.json'], [periodicYml, 'gate-census', '/tmp/gate-census-plan/manifest.json']] as const) {
[periodicYml, 'eval-slices', '/tmp/paid-plan/manifest.json'], [periodicYml, 'gate-census', '"/tmp/gate-census-plan/$arm/manifest.json"']] as const) {
const jobs = jobsOf(source);
const emit = jobs['plan-slices']!.steps.find(step => step.run?.includes(`--emit-plan ${manifest} `))!;
const cap = Number(/--max-parallel (\d+)/.exec(emit.run!)?.[1]);
@@ -401,6 +461,10 @@ describe('panel verdict surfaces (eval reliability policy)', () => {
expect(redispatch.permissions).toEqual({ actions: 'write' });
expect(redispatch.if).toBe("${{ !cancelled() && needs.report.outputs.redispatch == 'true' }}");
expect(redispatch.steps[0]!.run).toContain('-f redispatch_of="$GITHUB_RUN_ID"');
// A census-only run re-dispatches with its own arms, never as a weekly run.
expect(redispatch.steps[0]!.run).toContain('${CENSUS_ARMS:+-f census_arms="$CENSUS_ARMS"}');
expect(redispatch.steps[0]!.env?.CENSUS_ARMS).toBe('${{ needs.report.outputs.redispatch_census_arms }}');
expect(report.outputs!.redispatch_census_arms).toBe("${{ needs.plan-slices.outputs.periodic_lane != 'true' && join(fromJSON(needs.plan-slices.outputs.census_arms), ',') || '' }}");
const classify = report.steps.find(step => step.id === 'verdict')!;
expect(classify.run).toContain('.verdict.redispatchEligible == true');
expect(classify.run).toContain('[ -z "$REDISPATCH_OF" ]');
@@ -426,7 +490,13 @@ describe('scheduled paid lanes: concurrency and branch dispatch scope', () => {
test('a branch dispatch of evals-periodic runs the periodic lane only unless it opts into the gate census', () => {
const wf = parse(periodicYml);
expect(wf.on.workflow_dispatch!.inputs!.include_gate_census).toMatchObject({ type: 'boolean', default: false });
expect(wf.jobs['gate-census']!.if).toBe("${{ github.ref == 'refs/heads/main' || inputs.include_gate_census }}");
// The planner selects the census arms (scripts/census-arms.ts); no arm, no census job.
expect(wf.jobs['gate-census']!.if).toBe("${{ needs.plan-slices.outputs.gate_matrix != '[]' }}");
const select = wf.jobs['plan-slices']!.steps.find(step => step.id === 'census')!;
expect(select.env?.INCLUDE_GATE_CENSUS).toBe("${{ github.ref == 'refs/heads/main' || inputs.include_gate_census }}");
expect(select.run).toBe('bun --no-install run scripts/census-arms.ts --select >> "$GITHUB_OUTPUT"');
expect(selectCensus({ schedule: '', censusArms: '', includeGateCensus: false })).toEqual({ arms: [], periodicLane: true });
expect(selectCensus({ schedule: WEEKLY_CENSUS_SCHEDULE, includeGateCensus: true })).toEqual({ arms: [...WEEKLY_CENSUS_ARMS], periodicLane: true });
const report = wf.jobs.report!.steps;
const reconcile = report.find(step => step.name === 'Reconcile gate census against the manifest (fail-closed)')!;
expect(reconcile.env?.GATE_CENSUS).toBe('${{ needs.gate-census.result }}');
@@ -436,3 +506,80 @@ describe('scheduled paid lanes: concurrency and branch dispatch scope', () => {
expect(fail.if).toContain(`!contains(fromJSON('["success","skipped"]'), needs.gate-census.result)`);
});
});
describe('evals-periodic.yml census arms: Monday two-arm census, monthly Fable/Astra census', () => {
type CensusStep = Step & { if?: string };
type CensusWf = { on: { schedule: Array<{ cron: string }>; workflow_dispatch: { inputs: Record<string, { type?: string; default?: unknown }> } };
concurrency: { group: string }; jobs: Record<string, { if?: string; outputs?: Record<string, string>; steps: CensusStep[] }> };
const wf = Bun.YAML.parse(periodicYml) as CensusWf;
const planner = wf.jobs['plan-slices']!;
const census = wf.jobs['gate-census']!;
const report = wf.jobs.report!;
test('each arm is one host and model: the capture default and gpt-6.1-sol weekly, claude-fable-5-1 and gpt-6-astra monthly', () => {
expect(WEEKLY_CENSUS_ARMS).toEqual(['claude-opus', 'codex-sol']);
expect(MONTHLY_CENSUS_ARMS).toEqual(['claude-fable', 'codex-astra']);
// claude-opus pins no model: the Claude runners' capture default (lib/eval-model.ts) applies.
expect(censusArmEnv('claude-opus')).toEqual({ EVALS_HOST: 'claude' });
expect(censusArmEnv('codex-sol')).toEqual({ EVALS_HOST: 'codex', GSTACK_CODEX_MODEL: 'gpt-6.1-sol' });
expect(censusArmEnv('claude-fable')).toEqual({ EVALS_HOST: 'claude', EVALS_MODEL: 'claude-fable-5-1' });
expect(censusArmEnv('codex-astra')).toEqual({ EVALS_HOST: 'codex', GSTACK_CODEX_MODEL: 'gpt-6-astra' });
expect(() => censusArmEnv('codex-luna')).toThrow('unknown census arm');
// The report files slice artifacts by arm suffix: no arm id may end another one.
const ids = Object.keys(CENSUS_ARMS);
for (const a of ids) for (const b of ids) if (a !== b) expect(a.endsWith(`-${b}`)).toBe(false);
for (const id of ids) expect(id).toMatch(/^[a-z]+-[a-z]+$/);
});
test('the monthly cron runs only the census, under its own concurrency group; the Monday and daily canary schedules are unchanged', () => {
expect(wf.on.schedule.map(entry => entry.cron)).toEqual([WEEKLY_CENSUS_SCHEDULE, '30 7 * * *', MONTHLY_CENSUS_SCHEDULE]);
expect(MONTHLY_CENSUS_SCHEDULE).toBe('0 6 1 * *');
expect(wf.concurrency.group.endsWith("${{ github.event.schedule == '0 6 1 * *' && '-monthly' || '' }}")).toBe(true);
expect(wf.concurrency.group).toContain("(github.event.schedule == '30 7 * * *' || inputs.schema_canary_only) && '-schema-canary'");
expect(selectCensus({ schedule: MONTHLY_CENSUS_SCHEDULE, includeGateCensus: true })).toEqual({ arms: [...MONTHLY_CENSUS_ARMS], periodicLane: false });
const select = planner.steps.find(step => step.id === 'census')!;
expect(select.env).toMatchObject({ SCHEDULE: '${{ github.event.schedule }}', CENSUS_ARMS: '${{ inputs.census_arms }}' });
expect(planner.outputs).toMatchObject({ periodic_lane: '${{ steps.census.outputs.periodic_lane }}', census_arms: '${{ steps.census.outputs.arms }}' });
// Without the periodic lane no periodic plan is emitted, executed or reconciled.
for (const step of planner.steps.filter(step => step.run?.includes('/tmp/paid-plan/manifest.json') || step.with?.name === 'paid-plan')) {
expect(step.if, step.name ?? step.with?.name).toBe("steps.census.outputs.periodic_lane == 'true'");
}
const reconcile = report.steps.find(step => step.id === 'reconcile')!;
expect(reconcile.env?.PERIODIC_LANE).toBe('${{ needs.plan-slices.outputs.periodic_lane }}');
expect(reconcile.run).toContain('if [ "$PERIODIC_LANE" != "true" ]; then');
// A census-only green run never closes the weekly tracking issue.
expect(report.steps.find(step => step.name === 'Close the tracking issue on a green run')!.if)
.toContain("needs.plan-slices.outputs.periodic_lane == 'true' && needs.eval-slices.result == 'success'");
});
test('a census_arms dispatch runs only the named arms and refuses unknown ones', () => {
expect(wf.on.workflow_dispatch.inputs.census_arms).toMatchObject({ type: 'string', default: '' });
expect(selectCensus({ censusArms: 'codex-sol', includeGateCensus: true })).toEqual({ arms: ['codex-sol'], periodicLane: false });
expect(selectCensus({ censusArms: 'claude-opus, codex-sol,codex-sol', includeGateCensus: false })).toEqual({ arms: ['claude-opus', 'codex-sol'], periodicLane: false });
expect(() => selectCensus({ censusArms: 'codex-sol,gpt', includeGateCensus: false })).toThrow('unknown census arm(s): gpt');
const cli = (args: string[], env: Record<string, string>) => {
const proc = spawnSync(process.execPath, ['--no-install', 'run', 'scripts/census-arms.ts', ...args],
{ cwd: ROOT, env: { PATH: process.env.PATH ?? '', ...env }, encoding: 'utf8', timeout: 15_000 });
expect(proc.status, proc.stderr).toBe(0);
return proc.stdout;
};
expect(cli(['--select'], { SCHEDULE: MONTHLY_CENSUS_SCHEDULE })).toBe('arms=["claude-fable","codex-astra"]\nperiodic_lane=false\n');
expect(cli(['--select'], { CENSUS_ARMS: 'codex-sol', INCLUDE_GATE_CENSUS: 'true' })).toBe('arms=["codex-sol"]\nperiodic_lane=false\n');
expect(cli(['--env', 'codex-sol'], {})).toBe('EVALS_HOST=codex\nGSTACK_CODEX_MODEL=gpt-6.1-sol\n');
});
test('census artifacts and reconciliation are per arm', () => {
const upload = census.steps.find(step => step.name === 'Upload census results')!;
expect(upload.with!.name).toBe('gate-census-${{ matrix.slice }}-a${{ github.run_attempt }}-${{ matrix.arm }}');
expect(census.steps.find(step => step.name?.startsWith('Run gate census slice'))!.name).toContain('(${{ matrix.arm }})');
expect(report.steps.some(step => step.with?.pattern === 'gate-census-[0-9]*' && step.with?.path === '/tmp/gate-census-slices')).toBe(true);
const reconcile = report.steps.find(step => step.id === 'gate-reconcile')!;
expect(reconcile.env?.ARMS).toBe('${{ needs.plan-slices.outputs.census_arms }}');
expect(reconcile.run).toContain('cp "/tmp/gate-census-plan/$arm/manifest.json" "$dir/manifest.json" || status=1');
expect(reconcile.run).toContain('for slice in /tmp/gate-census-slices/gate-census-*-"$arm"; do');
expect(reconcile.run).toContain('EVALS_TIER=gate bun run scripts/test-paid-shards.ts --tier gate --report "$dir"');
// Every arm's report counts: one red arm fails the census.
expect(reconcile.run).toContain('if [ "$code" -ne 0 ]; then status=$code; fi');
expect(reconcile.run).toContain('echo "exit=$status" >> "$GITHUB_OUTPUT"');
});
});
test/fixtures/codex-host/exec-commands.jsonl
Vendored
+7
View File
@@ -0,0 +1,7 @@
{"type":"thread.started","thread_id":"01a150b3-ae5a-7932-ba51-4c295c66adf4"}
{"type":"turn.started"}
{"type":"item.completed","item":{"id":"item_0","type":"agent_message","text":"I’ll write and overwrite `hello.txt` with `printf`, then read it with `cat`.\n"}}
{"type":"item.started","item":{"id":"item_1","type":"command_execution","command":"/bin/bash -lc \"printf 'hi' > hello.txt\nprintf 'hello' > hello.txt\ncat hello.txt\"","aggregated_output":"","exit_code":null,"status":"in_progress"}}
{"type":"item.completed","item":{"id":"item_1","type":"command_execution","command":"/bin/bash -lc \"printf 'hi' > hello.txt\nprintf 'hello' > hello.txt\ncat hello.txt\"","aggregated_output":"hello","exit_code":0,"status":"completed"}}
{"type":"item.completed","item":{"id":"item_2","type":"agent_message","text":"`cat hello.txt` output: `hello`"}}
{"type":"turn.completed","usage":{"input_tokens":25009,"cached_input_tokens":12437,"cache_write_input_tokens":12566,"output_tokens":86,"reasoning_output_tokens":0}}
test/fixtures/codex-host/exec-file-change.jsonl
Vendored
+9
View File
@@ -0,0 +1,9 @@
{"type":"thread.started","thread_id":"01a150b3-be24-7f22-aa81-7eb4f79018e0"}
{"type":"turn.started"}
{"type":"item.completed","item":{"id":"item_0","type":"agent_message","text":"I’ll create `notes.md` with `draft`, then change it to `final` using two patches.\n"}}
{"type":"item.started","item":{"id":"item_1","type":"file_change","changes":[{"path":"/tmp/codex-host-fixture/notes.md","kind":"add"}],"status":"in_progress"}}
{"type":"item.completed","item":{"id":"item_1","type":"file_change","changes":[{"path":"/tmp/codex-host-fixture/notes.md","kind":"add"}],"status":"completed"}}
{"type":"item.started","item":{"id":"item_2","type":"file_change","changes":[{"path":"/tmp/codex-host-fixture/notes.md","kind":"update"}],"status":"in_progress"}}
{"type":"item.completed","item":{"id":"item_2","type":"file_change","changes":[{"path":"/tmp/codex-host-fixture/notes.md","kind":"update"}],"status":"completed"}}
{"type":"item.completed","item":{"id":"item_3","type":"agent_message","text":"Created `notes.md` with `draft`, then changed it to `final` using two `apply_patch` calls."}}
{"type":"turn.completed","usage":{"input_tokens":25020,"cached_input_tokens":12440,"cache_write_input_tokens":12574,"output_tokens":137,"reasoning_output_tokens":0}}
test/free-durations-record-workflow.test.ts
+5 -1
View File
@@ -81,7 +81,11 @@ test('the propose step touches only the two seeds, never the allowlist, on one b
expect(script).not.toContain('free-test-seed-allowlist.json');
expect(script).toContain('branch=bot/free-duration-seeds');
expect(script).toContain('bun test test/free-seed-ratchet.test.ts');
expect(script).toContain('gh workflow run free-tests.yml');
for (const workflow of ['free-tests.yml', 'windows-free-tests.yml', 'quality-gate.yml']) {
expect(script).toContain(`gh workflow run ${workflow} --repo "$GITHUB_REPOSITORY" --ref "$branch"`);
expect(load(workflow).on).toHaveProperty('workflow_dispatch');
}
expect(script).toContain('those are this PR\'s checks');
expect(proposeStep.env.OPEN_PR).toBe("${{ github.ref == 'refs/heads/main' && (github.event_name == 'schedule' || inputs.open_pr) }}");
expect(script.indexOf('if [ "$OPEN_PR" != true ]')).toBeLessThan(script.indexOf('git push'));
expect(recorder.on.workflow_dispatch.inputs.open_pr).toMatchObject({ type: 'boolean', default: true });
test/free-fixtures.test.ts
+10
View File
@@ -107,6 +107,16 @@ describe('PR selection over the W1a single-file fallbacks', () => {
}
});
test('seed data and the seed allowlist select no paid case; a derived paid-surface file still selects its dependents (#3289)', () => {
// #3289: the allowlist edit derived 246 gate cases, though only test/free-seed-ratchet.test.ts reads it.
const seed = select(['scripts/free-test-seed-allowlist.json', 'scripts/free-test-durations.json', 'scripts/free-test-durations-windows.json']);
expect({ mode: seed.mode, unknown: seed.unknownFiles, derived: seed.derivedFiles, e2e: seed.e2e, judges: seed.judges })
.toEqual({ mode: 'pr', unknown: [], derived: [], e2e: [], judges: [] });
const paid = select(['design/src/evolve.ts']);
expect(paid.derivedFiles.map(entry => entry.file)).toEqual(['design/src/evolve.ts']);
expect(paid.e2e.length).toBeGreaterThan(0);
});
test('the paid workflow itself still restores the full gate (36493452542)', () => {
const result = select(['.github/workflows/evals.yml']);
expect(result.mode).toBe('full-fallback');
test/helpers/anthropic-preflight.ts
+6 -1
View File
@@ -11,9 +11,14 @@
*
* Lives in its own module (not e2e-helpers) so the runner can import it
* without dragging in bun:test.
*
* On the Codex host (EVALS_HOST=codex) Codex is the agent and no session
* spawns `claude`, so the ping is skipped; Codex API failures surface per
* session as error_api.
*/
import { spawnSync } from 'child_process';
import { resolveEvalHost } from './e2e-hosts';
export type PreflightResult = 'skipped' | 'ok';
@@ -21,7 +26,7 @@ export function preflightAnthropicApi(
env: NodeJS.ProcessEnv = process.env,
spawn: typeof spawnSync = spawnSync,
): PreflightResult {
if (env.EVALS_PREFLIGHT_OK === '1') return 'skipped';
if (env.EVALS_PREFLIGHT_OK === '1' || resolveEvalHost(env) === 'codex') return 'skipped';
const check = spawn(
'sh',
['-c', 'echo "ping" | claude -p --max-turns 1 --output-format stream-json --verbose --dangerously-skip-permissions'],
test/helpers/codex-eval.ts
+8 -4
View File
@@ -1,5 +1,5 @@
/** One terminal record per Codex eval attempt, using the assertions as the oracle. */
import { CODEX_DRAIN_GRACE_MS, CodexHarnessError, type CodexResult } from './codex-session-runner';
import { CODEX_DRAIN_GRACE_MS, CodexHarnessError, codexUsageCostUsd, type CodexResult } from './codex-session-runner';
import { EvalCollector, getProjectEvalDir, shardSlugOfEvalDir, type EvalTestEntry } from './eval-store';
import * as path from 'node:path';
import * as fs from 'node:fs';
@@ -198,10 +198,13 @@ export async function runRecordedCodexEval(opts: CodexEvalOptions): Promise<Code
: 'validation_failed';
const message = failure instanceof Error ? failure.message : String(failure);
const diagnostic = result?.stderr && !message.includes(result.stderr) ? `${message}\n${result.stderr}` : message;
const model = result?.model ?? opts.model;
const cost = result?.usage ? codexUsageCostUsd(result.usage, model) : null;
appendSessionLedger({ key: sessionKey('codex', opts.name), test_name: opts.name, runner: 'codex', started_at: new Date(started).toISOString(),
budget_ms: opts.budgetMs, elapsed_ms: performance.now() - startMono,
end: exitReason === 'timeout' ? 'session_timeout' : passed || exitReason === 'validation_failed' ? 'completed' : 'error',
...(exitReason === 'timeout' ? { evidence: `armed ${opts.budgetMs}ms Codex budget expired` } : {}), billed: false });
...(exitReason === 'timeout' ? { evidence: `armed ${opts.budgetMs}ms Codex budget expired` } : {}), billed: cost !== null,
...(model ? { model } : {}), ...(cost !== null ? { cost_usd: cost, tokens: result!.usage! } : {}) });
// addTest appends retry attempts. Never pre-record a failure and then
// overwrite it: that would manufacture two attempts from one execution.
@@ -211,14 +214,15 @@ export async function runRecordedCodexEval(opts: CodexEvalOptions): Promise<Code
tier: 'e2e',
passed,
duration_ms: failure instanceof CodexEvalTimeout ? Date.now() - started : result?.durationMs ?? Date.now() - started,
cost_usd: 0, cost_known: false,
cost_usd: cost ?? 0, ...(cost === null ? { cost_known: false } : {}),
...(result?.usage ? { token_usage: result.usage } : {}),
...(result ? {
output: result.output.slice(0, opts.outputLimit ?? 2000),
turns_used: result.toolCalls.length,
tokens_used: result.tokens,
last_tool_call: result.toolCalls.at(-1),
} : {}),
...(opts.model ? { model: opts.model } : {}),
...(model ? { model } : {}),
exit_reason: exitReason,
...(failure !== undefined ? { error: diagnostic }
: result?.stderr ? { error: result.stderr } : {}),
test/helpers/codex-host-runner.ts
+306
View File
@@ -0,0 +1,306 @@
/**
* The Codex host for runSkillTest (EVALS_HOST=codex, GSTA-49 TM2): runs a
* Claude-authored gate case through `codex exec --json` and returns the same
* SkillTestResult shape, so the case's own assertions judge the outcome.
*
* Parity with the Claude runner (session-runner.ts):
* - runtime: the full gstack Codex runtime (`./setup --host codex`), installed
* once per process into a private CODEX_HOME holding the login's auth.json;
* - events: command_execution -> Bash ({ command } unwrapped from Codex's
* `bash -lc`, its output); file_change -> Write (add), Edit (update) or
* Delete per path; web_search -> WebSearch; mcp_tool_call -> mcp__server__tool;
* the last agent message is the output;
* - transcript: the Claude stream-json shape the cases' observers read: one
* system/init event (cwd, the Codex thread id as session_id), assistant text
* and tool_use events, user tool_result events (is_error from the exit code)
* and a final result event;
* - sandbox: GSTACK_CODEX_SANDBOX, default danger-full-access (the counterpart
* of claude -p --dangerously-skip-permissions; cases write outside their
* working directory, start loopback servers and browsers); workspace-write
* gets network access;
* - effort: GSTACK_CODEX_EFFORT sets model_reasoning_effort; unset keeps the
* model's default;
* - model: a non-Claude options.model, else GSTACK_CODEX_MODEL, else
* CODEX_FRONTIER_MODEL; a case's Claude model pin does not apply here;
* - cost: real accounting from `turn.completed` usage at lib/pricing.ts rates,
* recorded on the result, the eval record and the session ledger.
* - nativeLifecycle: onSpawn gets the codex process-group owner right after
* spawn; onSettled runs after its exit and group kill, within the drain grace.
* Not translated: maxTurns (Codex has no turn cap), allowedTools/tools (Codex
* has its own tool surface) and startupGraceMs (the timeout bounds the session).
*/
import * as fs from 'fs';
import * as os from 'os';
import * as path from 'path';
import { spawnSync } from 'child_process';
import { CODEX_DRAIN_GRACE_MS, CodexHarnessError, codexUsageCostUsd, execCodex, type CodexResult } from './codex-session-runner';
import { getProjectEvalDir } from './eval-store';
import { hermeticChildEnv } from './hermetic-env';
import { appendSessionLedger, sessionKey, type SessionEnd } from './session-ledger';
import { sanitizeTestName, scanBrowseErrors, type SkillTestResult } from './session-runner';
import { CODEX_FRONTIER_MODEL } from '../../scripts/resolvers/constants';
const ROOT = path.resolve(import.meta.dir, '..', '..');
const SETUP_TIMEOUT_MS = 300_000;
export const CODEX_SANDBOXES = ['read-only', 'workspace-write', 'danger-full-access'] as const;
const EFFORT = /^[a-z]+$/;
/** The Codex model for a session: a Claude pin never reaches `codex --model`. */
export function codexHostModel(explicit: string | undefined, env: NodeJS.ProcessEnv = process.env): string {
if (explicit && !/^claude-/.test(explicit)) return explicit;
return env.GSTACK_CODEX_MODEL || CODEX_FRONTIER_MODEL;
}
/** `codex exec` arguments for one session; the prompt is the last argument. */
export function codexHostExecArgs(model: string, prompt: string, env: NodeJS.ProcessEnv = process.env): string[] {
const sandbox = env.GSTACK_CODEX_SANDBOX || 'danger-full-access';
if (!(CODEX_SANDBOXES as readonly string[]).includes(sandbox)) {
throw new Error(`GSTACK_CODEX_SANDBOX must be one of ${CODEX_SANDBOXES.join(', ')}; got "${sandbox}"`);
}
const effort = env.GSTACK_CODEX_EFFORT;
if (effort && !EFFORT.test(effort)) throw new Error(`GSTACK_CODEX_EFFORT must be a bare effort name; got "${effort}"`);
return ['exec', '--json', '-s', sandbox, '--skip-git-repo-check', '--model', model,
...(sandbox === 'workspace-write' ? ['-c', 'sandbox_workspace_write.network_access=true'] : []),
...(effort ? ['-c', `model_reasoning_effort="${effort}"`] : []),
prompt];
}
/** The command inside Codex's `/bin/bash -lc <word>` wrapper, else the command unchanged. */
export function unwrapShellCommand(command: string): string {
const match = /^(?:\/(?:usr\/)?bin\/)?(?:ba|z)?sh -lc (.+)$/s.exec(command);
if (!match) return command;
const word = match[1]!;
let out = '';
let i = 0;
while (i < word.length) {
const c = word[i]!;
if (c === "'") {
const end = word.indexOf("'", i + 1);
if (end < 0) return command;
out += word.slice(i + 1, end);
i = end + 1;
} else if (c === '"') {
i++;
let closed = false;
while (i < word.length) {
if (word[i] === '\\' && i + 1 < word.length && '"\\$`\n'.includes(word[i + 1]!)) { out += word[i + 1]; i += 2; }
else if (word[i] === '"') { i++; closed = true; break; }
else out += word[i++];
}
if (!closed) return command;
} else if (c === '\\' && i + 1 < word.length) {
out += word[i + 1];
i += 2;
} else if (/\s/.test(c)) {
return command;
} else {
out += c;
i++;
}
}
return out;
}
export type HostToolCall = SkillTestResult['toolCalls'][number];
const FILE_CHANGE_TOOLS: Record<string, string> = { add: 'Write', update: 'Edit', delete: 'Delete' };
/** Claude-shaped tool calls from completed Codex items, in order. */
export function codexHostToolCalls(rawLines: readonly string[]): HostToolCall[] {
const calls: HostToolCall[] = [];
for (const line of rawLines) {
let event: any;
try { event = JSON.parse(line); } catch { continue; }
if (event?.type !== 'item.completed' || !event.item) continue;
const item = event.item;
if (item.type === 'command_execution') {
calls.push({ tool: 'Bash', input: { command: unwrapShellCommand(String(item.command ?? '')) }, output: String(item.aggregated_output ?? '') });
} else if (item.type === 'file_change') {
for (const change of Array.isArray(item.changes) ? item.changes : []) {
calls.push({ tool: FILE_CHANGE_TOOLS[change?.kind] ?? 'Edit', input: { file_path: String(change?.path ?? ''), kind: change?.kind }, output: '' });
}
} else if (item.type === 'web_search') {
calls.push({ tool: 'WebSearch', input: { query: item.query }, output: '' });
} else if (item.type === 'mcp_tool_call') {
calls.push({ tool: `mcp__${item.server}__${item.tool}`, input: item.arguments ?? {}, output: typeof item.result === 'string' ? item.result : JSON.stringify(item.result ?? '') });
}
}
return calls;
}
/**
* Codex events as the Claude stream-json transcript the cases' observers read
* (system/init, assistant text and tool_use, user tool_result, result).
*/
export function codexHostTranscript(rawLines: readonly string[], cwd: string, output: string): any[] {
const events: any[] = [];
let session = '';
const say = (role: 'assistant' | 'user', content: any[]) => events.push({ type: role, session_id: session, parent_tool_use_id: null, message: { role, content } });
for (const line of rawLines) {
let event: any;
try { event = JSON.parse(line); } catch { continue; }
if (event?.type === 'thread.started') {
session = String(event.thread_id ?? '');
events.push({ type: 'system', subtype: 'init', cwd, session_id: session, tools: [] });
continue;
}
if (event?.type !== 'item.completed' || !event.item) continue;
const item = event.item;
const id = String(item.id ?? `item_${events.length}`);
if (item.type === 'agent_message' && item.text) say('assistant', [{ type: 'text', text: String(item.text) }]);
else if (item.type === 'command_execution') {
say('assistant', [{ type: 'tool_use', id, name: 'Bash', input: { command: unwrapShellCommand(String(item.command ?? '')) } }]);
say('user', [{ type: 'tool_result', tool_use_id: id, content: String(item.aggregated_output ?? ''), is_error: item.exit_code !== 0 }]);
} else if (item.type === 'file_change') {
(Array.isArray(item.changes) ? item.changes : []).forEach((change: any, index: number) => {
const useId = `${id}_${index}`;
say('assistant', [{ type: 'tool_use', id: useId, name: FILE_CHANGE_TOOLS[change?.kind] ?? 'Edit', input: { file_path: String(change?.path ?? '') } }]);
say('user', [{ type: 'tool_result', tool_use_id: useId, content: '', is_error: item.status !== 'completed' }]);
});
}
}
events.push({ type: 'result', subtype: 'success', session_id: session, result: output });
return events;
}
let runtimeRoot: string | undefined;
/**
* Install the full gstack Codex runtime once per process: `./setup --host codex`
* into a private HOME/CODEX_HOME, with the login home's auth.json copied in.
* Returns the root holding home/.codex and tmp/ (Codex will not create its
* helper aliases when CODEX_HOME sits under its own TMPDIR). A caller that
* already prepared one passes it as GSTACK_CODEX_HOST_ROOT.
*/
export function prepareCodexHostRuntime(env: NodeJS.ProcessEnv = process.env): string {
if (runtimeRoot) return runtimeRoot;
const preset = env.GSTACK_CODEX_HOST_ROOT;
if (preset) {
if (!fs.existsSync(path.join(preset, 'home', '.codex'))) throw new Error(`GSTACK_CODEX_HOST_ROOT ${preset} has no home/.codex`);
fs.mkdirSync(path.join(preset, 'tmp'), { recursive: true });
return runtimeRoot = preset;
}
const root = fs.mkdtempSync(path.join(os.tmpdir(), 'codex-host-'));
const home = path.join(root, 'home');
const codexHome = path.join(home, '.codex');
const tmp = path.join(root, 'tmp');
for (const dir of [codexHome, tmp]) fs.mkdirSync(dir, { recursive: true });
const auth = path.join(env.CODEX_HOME || path.join(os.homedir(), '.codex'), 'auth.json');
if (fs.existsSync(auth)) fs.copyFileSync(auth, path.join(codexHome, 'auth.json'));
const setup = spawnSync(path.join(ROOT, 'setup'), ['--host', 'codex'], {
cwd: ROOT, encoding: 'utf8', timeout: SETUP_TIMEOUT_MS,
env: hermeticChildEnv({ HOME: home, CODEX_HOME: codexHome, TMPDIR: tmp }, { extraAllow: ['OPENAI_API_KEY', 'CODEX_*'] }),
});
if (setup.status !== 0) {
fs.rmSync(root, { recursive: true, force: true });
throw new Error(`./setup --host codex failed (exit ${setup.status}${setup.error ? `, ${setup.error.message}` : ''}): ${(setup.stderr || setup.stdout || '').slice(-2000)}`);
}
process.once('exit', () => { try { fs.rmSync(root, { recursive: true, force: true }); } catch { /* best effort */ } });
runtimeRoot = root;
return root;
}
type RunSkillTestOptions = Parameters<typeof import('./session-runner').runSkillTest>[0];
function exitReasonOf(result: CodexResult, aborted: boolean): string {
if (result.exitCode === 124) return 'timeout';
const failedTurn = result.rawLines.some(line => /"type":"(?:turn\.failed|error)"/.test(line));
if (result.exitCode === 0) return failedTurn ? 'error_api' : 'success';
if (aborted) return 'timeout';
return failedTurn && !result.rawLines.some(line => line.includes('"type":"item.completed"')) ? 'error_api' : `exit_code_${result.exitCode}`;
}
const SESSION_ENDS: Record<string, SessionEnd> = { success: 'completed', timeout: 'session_timeout', error_api: 'api_error' };
/** runSkillTest on the Codex host. `appendSystemPrompt` arrives with any completion notice already applied. */
export async function runCodexHostSkillTest(options: RunSkillTestOptions): Promise<SkillTestResult> {
const startTime = Date.now();
const startMono = performance.now();
const { workingDirectory, timeout = 120_000, testName, runId, signal } = options;
const deadline = startTime + timeout;
const model = codexHostModel(options.model);
const prompt = options.appendSystemPrompt ? `${options.appendSystemPrompt}\n\n${options.prompt}` : options.prompt;
const root = prepareCodexHostRuntime();
const safeName = testName ? sanitizeTestName(testName) : null;
let runDir: string | null = null;
if (runId) {
try {
runDir = path.join(path.dirname(getProjectEvalDir()), 'e2e-runs', runId);
fs.mkdirSync(runDir, { recursive: true });
} catch { runDir = null; }
}
let firstResponseMs = 0;
let lastItemMs = 0;
let maxInterTurnMs = 0;
const onLine = (line: string, elapsedMs: number) => {
if (!firstResponseMs) firstResponseMs = Math.max(1, elapsedMs);
if (runDir && safeName) { try { fs.appendFileSync(path.join(runDir, `${safeName}.ndjson`), line + '\n'); } catch { /* non-fatal */ } }
if (!line.includes('"type":"item.completed"') || !/"type":"(?:command_execution|file_change)"/.test(line)) return;
if (lastItemMs) maxInterTurnMs = Math.max(maxInterTurnMs, elapsedMs - lastItemMs);
lastItemMs = elapsedMs;
};
let result: CodexResult;
let harnessReason: string | undefined;
let started = true;
const lifecycle = options.nativeLifecycle;
try {
result = await execCodex(codexHostExecArgs(model, prompt), {
cwd: workingDirectory, startTime, deadline, signal, onLine, ...(lifecycle ? { onSpawn: (pid: number) => lifecycle.onSpawn(pid) } : {}),
env: hermeticChildEnv(
{ GSTACK_HEADLESS: '1', ...options.env, CODEX_HOME: path.join(root, 'home', '.codex'), TMPDIR: options.env?.TMPDIR ?? path.join(root, 'tmp') },
{ extraAllow: ['OPENAI_API_KEY', 'CODEX_*'] },
),
});
} catch (error) {
if (!(error instanceof CodexHarnessError) || !error.result) throw error;
result = error.result;
started = !error.message.startsWith('Could not start Codex');
harnessReason = /drain/.test(error.message) ? 'error_output_drain' : 'error_output_stream';
}
if (lifecycle) {
const settleDeadline = Date.now() + CODEX_DRAIN_GRACE_MS;
let hookTimer: ReturnType<typeof setTimeout> | undefined;
try {
await Promise.race([
lifecycle.onSettled({ deadline: settleDeadline, exited: started }),
new Promise<never>((_, reject) => { hookTimer = setTimeout(() => reject(new Error('native lifecycle settlement deadline exceeded')), CODEX_DRAIN_GRACE_MS); }),
]);
} finally { clearTimeout(hookTimer); }
}
const exitReason = harnessReason ?? exitReasonOf(result, !!signal?.aborted);
const toolCalls = codexHostToolCalls(result.rawLines);
const events = result.rawLines.flatMap(line => { try { return [JSON.parse(line)]; } catch { return []; } });
const messages = events.filter(event => event?.type === 'item.completed' && event.item?.type === 'agent_message');
const output = String(messages.at(-1)?.item?.text ?? '');
const turnsUsed = events.filter(event => event?.type === 'item.completed' && event.item?.type !== 'reasoning').length;
const transcript = codexHostTranscript(result.rawLines, workingDirectory, output);
const cost = result.usage ? codexUsageCostUsd(result.usage, model) : null;
const browseErrors = scanBrowseErrors(toolCalls.filter(call => call.tool === 'Bash').map(call => call.output).join('\n') + '\n' + result.stderr);
const duration = Date.now() - startTime;
appendSessionLedger({ key: sessionKey('codex', testName), ...(testName ? { test_name: testName } : {}), runner: 'codex',
started_at: new Date(startTime).toISOString(), budget_ms: timeout, elapsed_ms: performance.now() - startMono,
end: exitReason === 'timeout' && signal?.aborted ? 'aborted' : SESSION_ENDS[exitReason] ?? 'error',
...(exitReason === 'timeout' ? { evidence: `armed ${timeout}ms session timeout fired` } : exitReason !== 'success' && result.stderr ? { evidence: result.stderr } : {}),
billed: cost !== null, model, ...(cost !== null ? { cost_usd: cost, tokens: result.usage! } : {}) });
if (exitReason !== 'success' || browseErrors.length > 0) {
try {
const failureDir = runDir || path.join(workingDirectory, '.gstack', 'test-transcripts');
fs.mkdirSync(failureDir, { recursive: true });
fs.writeFileSync(path.join(failureDir, safeName ? `${safeName}-failure.json` : `e2e-${new Date().toISOString().replace(/[:.]/g, '-')}.json`),
JSON.stringify({ host: 'codex', model, prompt: prompt.slice(0, 500), testName: testName || 'unknown', exitReason, browseErrors, duration,
stderr: result.stderr.slice(0, 2000), output: output.slice(0, 500) }, null, 2));
} catch { /* non-fatal */ }
}
return {
toolCalls, browseErrors, exitReason, duration, output, transcript, model, firstResponseMs, maxInterTurnMs,
costEstimate: { inputChars: prompt.length, outputChars: output.length,
estimatedTokens: (result.usage?.input ?? 0) + (result.usage?.output ?? 0), estimatedCost: cost ?? 0, turnsUsed },
...(result.usage ? { tokenUsage: result.usage } : {}),
...(cost === null ? { costKnown: false } : {}),
};
}
test/helpers/codex-session-runner.ts
+243 -156
View File
@@ -21,6 +21,7 @@ import { hermeticChildEnv } from './hermetic-env';
import { extractSkillSections } from './skill-fixture';
import { killProcessGroup } from '../../scripts/test-strict-output';
import { CODEX_FRONTIER_MODEL } from '../../scripts/resolvers/constants';
import { estimateCostUsd, hasPricing } from '../../lib/pricing';
// --- Interfaces ---
@@ -34,6 +35,47 @@ export interface CodexResult {
sessionId: string | null; // Thread ID for session continuity
rawLines: string[]; // Raw JSONL lines for debugging
stderr: string; // Stderr output (skill loading errors, auth failures)
usage?: CodexTokenUsage | null; // Summed turn.completed usage; null when no turn completed
model?: string; // The --model this session ran
}
/**
* Token classes of Codex `turn.completed` usage. `cached_input` (cache reads)
* and `cache_write_input` are subsets of `input`; `reasoning_output` is a
* subset of `output`.
*/
export interface CodexTokenUsage {
input: number;
cached_input: number;
cache_write_input: number;
output: number;
reasoning_output: number;
}
export const NO_CODEX_USAGE: CodexTokenUsage = Object.freeze({ input: 0, cached_input: 0, cache_write_input: 0, output: 0, reasoning_output: 0 });
const count = (value: unknown) => (typeof value === 'number' && Number.isFinite(value) && value > 0 ? value : 0);
/** Add one `turn.completed` usage object to a running total. */
export function addCodexTurnUsage(total: CodexTokenUsage, usage: Record<string, unknown> | undefined): CodexTokenUsage {
return {
input: total.input + count(usage?.input_tokens),
cached_input: total.cached_input + count(usage?.cached_input_tokens),
cache_write_input: total.cache_write_input + count(usage?.cache_write_input_tokens),
output: total.output + count(usage?.output_tokens),
reasoning_output: total.reasoning_output + count(usage?.reasoning_output_tokens),
};
}
/**
* A session's cost at lib/pricing.ts rates: cache reads at the cached-input
* rate, all other input (cache writes included) at the input rate, output at
* the output rate. Null when the model has no price row.
*/
export function codexUsageCostUsd(usage: CodexTokenUsage, model: string | undefined): number | null {
if (!hasPricing(model)) return null;
const cached = Math.min(usage.cached_input, usage.input);
return estimateCostUsd({ input: usage.input - cached, cached, output: usage.output }, model);
}
/** Existing pipe-drain allowance, separate from the model's work budget. */
@@ -54,6 +96,7 @@ export interface ParsedCodexJSONL {
toolCalls: string[];
tokens: number;
sessionId: string | null;
usage: CodexTokenUsage | null;
}
/**
@@ -71,6 +114,7 @@ export function parseCodexJSONL(lines: string[]): ParsedCodexJSONL {
const toolCalls: string[] = [];
let tokens = 0;
let sessionId: string | null = null;
let usage: CodexTokenUsage | null = null;
for (const line of lines) {
if (!line.trim()) continue;
@@ -95,9 +139,9 @@ export function parseCodexJSONL(lines: string[]): ParsedCodexJSONL {
if (cmd) toolCalls.push(cmd);
}
} else if (t === 'turn.completed') {
const usage = obj.usage || {};
const turnTokens = (usage.input_tokens || 0) + (usage.output_tokens || 0);
tokens += turnTokens;
const turn = obj.usage || {};
tokens += (turn.input_tokens || 0) + (turn.output_tokens || 0);
usage = addCodexTurnUsage(usage ?? NO_CODEX_USAGE, turn);
}
} catch { /* skip malformed lines */ }
}
@@ -108,6 +152,7 @@ export function parseCodexJSONL(lines: string[]): ParsedCodexJSONL {
toolCalls,
tokens,
sessionId,
usage,
};
}
@@ -166,6 +211,192 @@ export function installSkillToTempHome(
return home;
}
// --- Spawn core ---
/**
* Spawn `codex <args>` in its own process group and collect its JSONL until
* exit, the deadline or an abort, with the existing drain grace. Shared by
* runCodexSkill and the Codex host (codex-host-runner.ts). `onLine` sees each
* JSONL line as it arrives with the elapsed milliseconds since `startTime`.
*/
export async function execCodex(args: string[], opts: {
cwd: string;
env: Record<string, string>;
startTime: number;
deadline: number;
signal?: AbortSignal;
onLine?: (line: string, elapsedMs: number) => void;
/** Called with the group-owning pid right after spawn; a throw kills the group. */
onSpawn?: (pid: number) => void;
}): Promise<CodexResult> {
const { cwd, env, startTime, deadline, signal, onLine } = opts;
const proc = spawn('codex', args, {
cwd,
stdio: ['ignore', 'pipe', 'pipe'],
detached: process.platform !== 'win32',
env,
});
if (opts.onSpawn) {
try {
if (proc.pid === undefined) throw new Error('Codex did not start');
opts.onSpawn(proc.pid);
} catch (error) {
killProcessGroup(proc, 'SIGKILL');
proc.stdout!.destroy();
proc.stderr!.destroy();
throw error;
}
}
const collectedLines: string[] = [];
// work --exit--> drain (<=5s) --> result
// \--timeout/abort--> kill group + close pipes --> timeout result
// Exit status comes from 'exit'; a forced drain after exit 0 is an error.
let stdoutBuffer = '';
let stderr = '';
let exitCode: number | undefined;
let timedOut = false;
let drainExpired = false;
let streamError: { stream: 'stdout' | 'stderr'; error: Error } | undefined;
let spawnError: Error | undefined;
let stdoutDone = false;
let stderrDone = false;
let stdoutEnded = false;
let stderrEnded = false;
let finalized = false;
const stdoutDecoder = new StringDecoder('utf8');
const stderrDecoder = new StringDecoder('utf8');
let workTimer: ReturnType<typeof setTimeout> | undefined;
let drainTimer: ReturnType<typeof setTimeout> | undefined;
let finish!: () => void;
const finished = new Promise<void>((resolve) => { finish = resolve; });
const maybeFinish = () => {
if (exitCode !== undefined && stdoutDone && stderrDone) finish();
};
const closePipes = () => {
// Destroy both streams: canceling stdout alone cannot release an
// inherited stderr pipe held by a descendant in another process group.
proc.stdout!.destroy();
proc.stderr!.destroy();
};
const expireDrain = () => {
drainExpired = !stdoutDone || !stderrDone;
killProcessGroup(proc, 'SIGKILL');
closePipes();
// Also bound the rare case where a failed group kill produces no exit.
finish();
};
const stopRun = () => {
// A real auth/crash exit that preceded a pipe stall stays a real exit.
if (exitCode === undefined) timedOut = true;
else drainExpired ||= !stdoutDone || !stderrDone;
killProcessGroup(proc, 'SIGKILL');
closePipes();
clearTimeout(drainTimer);
drainTimer = setTimeout(expireDrain, CODEX_DRAIN_GRACE_MS);
maybeFinish();
};
const onExit = (code: number | null, exitSignal: NodeJS.Signals | null) => {
exitCode = code ?? (exitSignal ? 128 + (os.constants.signals[exitSignal] ?? 0) : 1);
clearTimeout(workTimer);
clearTimeout(drainTimer);
// 'exit' means the child is gone; 'close' also waits for descendant
// pipes. Start the drain allowance at actual exit, never at close.
drainTimer = setTimeout(expireDrain, CODEX_DRAIN_GRACE_MS);
maybeFinish();
};
const onSpawnError = (error: Error) => {
if (finalized) return;
spawnError = error;
exitCode = 1;
closePipes();
finish();
};
// Closure releases lifecycle waits, but only 'end' proves all bytes were
// drained. A destroyed pipe can emit 'close' without either EOF or error.
const onStdoutDone = () => { if (!finalized) { stdoutDone = true; maybeFinish(); } };
const onStderrDone = () => { if (!finalized) { stderrDone = true; maybeFinish(); } };
const onStdoutEnd = () => { if (!finalized) { stdoutBuffer += stdoutDecoder.end(); stdoutEnded = true; onStdoutDone(); } };
const onStderrEnd = () => { if (!finalized) { stderr += stderrDecoder.end(); stderrEnded = true; onStderrDone(); } };
const onStreamError = (stream: 'stdout' | 'stderr', error: Error) => {
if (!finalized) streamError ??= { stream, error };
};
const onStdout = (chunk: Buffer) => {
if (finalized) return;
stdoutBuffer += stdoutDecoder.write(chunk);
const lines = stdoutBuffer.split('\n');
stdoutBuffer = lines.pop() || '';
for (const line of lines) {
if (!line.trim()) continue;
collectedLines.push(line);
onLine?.(line, Date.now() - startTime);
try {
const event = JSON.parse(line);
if (event.type === 'item.completed' && event.item) {
const item = event.item;
const elapsed = Math.round((Date.now() - startTime) / 1000);
if (item.type === 'command_execution' && item.command) {
process.stderr.write(` [codex ${elapsed}s] ran: ${item.command.slice(0, 100)}\n`);
} else if (item.type === 'agent_message' && item.text) {
process.stderr.write(` [codex ${elapsed}s] message: ${item.text.slice(0, 100)}\n`);
}
}
} catch { /* malformed JSONL is ignored by parseCodexJSONL too */ }
}
};
const onStderr = (chunk: Buffer) => { if (!finalized) stderr += stderrDecoder.write(chunk); };
proc.on('exit', onExit);
proc.on('error', onSpawnError);
proc.stdout!.on('data', onStdout);
proc.stderr!.on('data', onStderr);
proc.stdout!.on('end', onStdoutEnd).on('close', onStdoutDone).on('error', error => onStreamError('stdout', error));
proc.stderr!.on('end', onStderrEnd).on('close', onStderrDone).on('error', error => onStreamError('stderr', error));
signal?.addEventListener('abort', stopRun, { once: true });
workTimer = setTimeout(stopRun, Math.max(0, deadline - Date.now()));
if (signal?.aborted || Date.now() >= deadline) stopRun();
try {
await finished;
if (stdoutBuffer.trim()) collectedLines.push(stdoutBuffer);
const parsed = parseCodexJSONL(collectedLines);
const result: CodexResult = {
...parsed,
exitCode: timedOut ? 124 : exitCode ?? 1,
durationMs: Date.now() - startTime,
rawLines: collectedLines,
stderr,
};
if (stderr.trim()) process.stderr.write(` [codex stderr] ${stderr.trim().slice(0, 200)}\n`);
if (spawnError) throw new CodexHarnessError(`Could not start Codex: ${spawnError.message}`, result);
const incompleteStreams = [!stdoutEnded && 'stdout', !stderrEnded && 'stderr'].filter(Boolean).join(' and ');
if (result.exitCode === 0 && (drainExpired || streamError || incompleteStreams)) {
throw new CodexHarnessError(
drainExpired ? `Codex output drain exceeded ${CODEX_DRAIN_GRACE_MS}ms after exit 0`
: streamError ? `Codex ${streamError.stream} stream failed: ${streamError.error.message}`
: `Codex ${incompleteStreams} closed before EOF after exit 0`,
result,
);
}
return result;
} finally {
finalized = true;
clearTimeout(workTimer);
clearTimeout(drainTimer);
signal?.removeEventListener('abort', stopRun);
// Child exit and closed pipes do not prove its descendants exited:
// background tools may redirect both streams. Reap the owned group on
// every result, including ordinary success and genuine process failure.
killProcessGroup(proc, 'SIGKILL');
closePipes();
proc.removeListener('exit', onExit);
// Retain the harmless error listener through stream teardown so a late
// OS spawn error cannot turn into an unhandled event after cleanup.
proc.stdout!.removeListener('data', onStdout);
proc.stderr!.removeListener('data', onStderr);
}
}
// --- Main runner ---
/**
@@ -209,7 +440,7 @@ export async function runCodexSkill(opts: {
const emptyResult = (exitCode: number, output = ''): CodexResult => ({
output, reasoning: [], toolCalls: [], tokens: 0, exitCode,
durationMs: Date.now() - startTime, sessionId: null, rawLines: [], stderr: '',
durationMs: Date.now() - startTime, sessionId: null, rawLines: [], stderr: '', usage: null,
});
if (signal?.aborted || Date.now() >= deadline) return emptyResult(124);
@@ -257,7 +488,8 @@ export async function runCodexSkill(opts: {
// exactly that. Empirically verified against codex on this machine.
const args = ['exec', '--json', '-s', sandbox, '--skip-git-repo-check'];
if (ignoreUserConfig) args.push('--ignore-user-config');
args.push('--model', model ?? process.env.GSTACK_CODEX_MODEL ?? CODEX_FRONTIER_MODEL);
const sessionModel = model ?? process.env.GSTACK_CODEX_MODEL ?? CODEX_FRONTIER_MODEL;
args.push('--model', sessionModel);
for (const override of configOverrides) args.push('-c', override);
args.push(prompt);
@@ -275,162 +507,17 @@ export async function runCodexSkill(opts: {
// dir beside CODEX_HOME instead of the shard TMPDIR that holds tempHome.
const tempTmpDir = path.join(tempHome, 'tmp');
fs.mkdirSync(tempTmpDir, { recursive: true });
const proc = spawn('codex', args, {
cwd: cwd || skillDir,
stdio: ['ignore', 'pipe', 'pipe'],
detached: process.platform !== 'win32',
const result = await execCodex(args, {
cwd: cwd || skillDir, startTime, deadline, signal,
env: hermeticChildEnv(
{ HOME: tempHome, CODEX_HOME: tempCodexDir, TMPDIR: tempTmpDir },
{ extraAllow: ['OPENAI_API_KEY', 'CODEX_*'] },
),
}).catch((error: unknown) => {
if (error instanceof CodexHarnessError && error.result) error.result.model = sessionModel;
throw error;
});
const collectedLines: string[] = [];
// work --exit--> drain (<=5s) --> result
// \--timeout/abort--> kill group + close pipes --> timeout result
// Exit status comes from 'exit'; a forced drain after exit 0 is an error.
let stdoutBuffer = '';
let stderr = '';
let exitCode: number | undefined;
let timedOut = false;
let drainExpired = false;
let streamError: { stream: 'stdout' | 'stderr'; error: Error } | undefined;
let spawnError: Error | undefined;
let stdoutDone = false;
let stderrDone = false;
let stdoutEnded = false;
let stderrEnded = false;
let finalized = false;
const stdoutDecoder = new StringDecoder('utf8');
const stderrDecoder = new StringDecoder('utf8');
let workTimer: ReturnType<typeof setTimeout> | undefined;
let drainTimer: ReturnType<typeof setTimeout> | undefined;
let finish!: () => void;
const finished = new Promise<void>((resolve) => { finish = resolve; });
const maybeFinish = () => {
if (exitCode !== undefined && stdoutDone && stderrDone) finish();
};
const closePipes = () => {
// Destroy both streams: canceling stdout alone cannot release an
// inherited stderr pipe held by a descendant in another process group.
proc.stdout!.destroy();
proc.stderr!.destroy();
};
const expireDrain = () => {
drainExpired = !stdoutDone || !stderrDone;
killProcessGroup(proc, 'SIGKILL');
closePipes();
// Also bound the rare case where a failed group kill produces no exit.
finish();
};
const stopRun = () => {
// A real auth/crash exit that preceded a pipe stall stays a real exit.
if (exitCode === undefined) timedOut = true;
else drainExpired ||= !stdoutDone || !stderrDone;
killProcessGroup(proc, 'SIGKILL');
closePipes();
clearTimeout(drainTimer);
drainTimer = setTimeout(expireDrain, CODEX_DRAIN_GRACE_MS);
maybeFinish();
};
const onExit = (code: number | null, exitSignal: NodeJS.Signals | null) => {
exitCode = code ?? (exitSignal ? 128 + (os.constants.signals[exitSignal] ?? 0) : 1);
clearTimeout(workTimer);
clearTimeout(drainTimer);
// 'exit' means the child is gone; 'close' also waits for descendant
// pipes. Start the drain allowance at actual exit, never at close.
drainTimer = setTimeout(expireDrain, CODEX_DRAIN_GRACE_MS);
maybeFinish();
};
const onSpawnError = (error: Error) => {
if (finalized) return;
spawnError = error;
exitCode = 1;
closePipes();
finish();
};
// Closure releases lifecycle waits, but only 'end' proves all bytes were
// drained. A destroyed pipe can emit 'close' without either EOF or error.
const onStdoutDone = () => { if (!finalized) { stdoutDone = true; maybeFinish(); } };
const onStderrDone = () => { if (!finalized) { stderrDone = true; maybeFinish(); } };
const onStdoutEnd = () => { if (!finalized) { stdoutBuffer += stdoutDecoder.end(); stdoutEnded = true; onStdoutDone(); } };
const onStderrEnd = () => { if (!finalized) { stderr += stderrDecoder.end(); stderrEnded = true; onStderrDone(); } };
const onStreamError = (stream: 'stdout' | 'stderr', error: Error) => {
if (!finalized) streamError ??= { stream, error };
};
const onStdout = (chunk: Buffer) => {
if (finalized) return;
stdoutBuffer += stdoutDecoder.write(chunk);
const lines = stdoutBuffer.split('\n');
stdoutBuffer = lines.pop() || '';
for (const line of lines) {
if (!line.trim()) continue;
collectedLines.push(line);
try {
const event = JSON.parse(line);
if (event.type === 'item.completed' && event.item) {
const item = event.item;
const elapsed = Math.round((Date.now() - startTime) / 1000);
if (item.type === 'command_execution' && item.command) {
process.stderr.write(` [codex ${elapsed}s] ran: ${item.command.slice(0, 100)}\n`);
} else if (item.type === 'agent_message' && item.text) {
process.stderr.write(` [codex ${elapsed}s] message: ${item.text.slice(0, 100)}\n`);
}
}
} catch { /* malformed JSONL is ignored by parseCodexJSONL too */ }
}
};
const onStderr = (chunk: Buffer) => { if (!finalized) stderr += stderrDecoder.write(chunk); };
proc.on('exit', onExit);
proc.on('error', onSpawnError);
proc.stdout!.on('data', onStdout);
proc.stderr!.on('data', onStderr);
proc.stdout!.on('end', onStdoutEnd).on('close', onStdoutDone).on('error', error => onStreamError('stdout', error));
proc.stderr!.on('end', onStderrEnd).on('close', onStderrDone).on('error', error => onStreamError('stderr', error));
signal?.addEventListener('abort', stopRun, { once: true });
workTimer = setTimeout(stopRun, Math.max(0, deadline - Date.now()));
if (signal?.aborted || Date.now() >= deadline) stopRun();
try {
await finished;
if (stdoutBuffer.trim()) collectedLines.push(stdoutBuffer);
const parsed = parseCodexJSONL(collectedLines);
const result: CodexResult = {
...parsed,
exitCode: timedOut ? 124 : exitCode ?? 1,
durationMs: Date.now() - startTime,
rawLines: collectedLines,
stderr,
};
if (stderr.trim()) process.stderr.write(` [codex stderr] ${stderr.trim().slice(0, 200)}\n`);
if (spawnError) throw new CodexHarnessError(`Could not start Codex: ${spawnError.message}`, result);
const incompleteStreams = [!stdoutEnded && 'stdout', !stderrEnded && 'stderr'].filter(Boolean).join(' and ');
if (result.exitCode === 0 && (drainExpired || streamError || incompleteStreams)) {
throw new CodexHarnessError(
drainExpired ? `Codex output drain exceeded ${CODEX_DRAIN_GRACE_MS}ms after exit 0`
: streamError ? `Codex ${streamError.stream} stream failed: ${streamError.error.message}`
: `Codex ${incompleteStreams} closed before EOF after exit 0`,
result,
);
}
return result;
} finally {
finalized = true;
clearTimeout(workTimer);
clearTimeout(drainTimer);
signal?.removeEventListener('abort', stopRun);
// Child exit and closed pipes do not prove its descendants exited:
// background tools may redirect both streams. Reap the owned group on
// every result, including ordinary success and genuine process failure.
killProcessGroup(proc, 'SIGKILL');
closePipes();
proc.removeListener('exit', onExit);
// Retain the harmless error listener through stream teardown so a late
// OS spawn error cannot turn into an unhandled event after cleanup.
proc.stdout!.removeListener('data', onStdout);
proc.stderr!.removeListener('data', onStderr);
}
return { ...result, model: sessionModel };
} finally {
// Clean up temp HOME
test/helpers/e2e-helpers.ts
+14
View File
@@ -16,6 +16,7 @@ import { WorktreeManager } from '../../lib/worktree';
import type { HarvestResult } from '../../lib/worktree';
import { preflightAnthropicApi } from './anthropic-preflight';
import { isHermeticEnabled } from './hermetic-env';
import { hostSkipReason, resolveEvalHost } from './e2e-hosts';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
@@ -133,6 +134,17 @@ if (evalsEnabled && process.env.EVALS_TIER) {
process.stderr.write(`EVALS_TIER=${tier}: ${selectedTests.length} tests\n\n`);
}
// EVALS_HOST=codex: Claude-only cases are skipped with their reason, never run
// (and never failed); the report deselects them (test/helpers/e2e-hosts.ts).
if (evalsEnabled && resolveEvalHost() !== 'claude') {
const host = resolveEvalHost();
const candidates = selectedTests ?? Object.keys(E2E_TIERS);
const skipped = candidates.filter(id => hostSkipReason(id, host));
selectedTests = candidates.filter(id => !hostSkipReason(id, host));
process.stderr.write(`EVALS_HOST=${host}: ${selectedTests.length} tests; ${skipped.length} Claude-only skipped (${skipped.join(', ') || 'none'})\n\n`);
(await import('./codex-host-runner')).prepareCodexHostRuntime();
}
export const describeE2E = evalsEnabled ? describe : describe.skip;
/**
@@ -261,6 +273,8 @@ export function recordE2E(
...(!passed && isPreTurnInfraFailure(result) ? { failure_class: 'infra' as const } : {}),
duration_ms: result.duration,
cost_usd: result.costEstimate.estimatedCost,
...(result.costKnown === false ? { cost_known: false } : {}),
...(result.tokenUsage ? { token_usage: result.tokenUsage } : {}),
transcript: result.transcript,
output: result.output?.slice(0, 2000),
turns_used: result.costEstimate.turnsUsed,
test/helpers/e2e-hosts.ts
+126
View File
@@ -0,0 +1,126 @@
/**
* Agent host selection for paid E2E cases (GSTA-49 TM2). EVALS_HOST picks the
* agent every runSkillTest session runs on: `claude` (default) or `codex`
* (codex exec, test/helpers/codex-host-runner.ts). E2E_HOSTS is the per-case
* host metadata over every gate case (classification in the GSTA-49 TM2
* scoping): `both` runs on either host with the shared adapter; every other
* value is the reason the case is Claude-only. On the Codex host a Claude-only
* case is SKIPPED with its reason, planned as excluded and deselected by the
* report with zero credit, never counted as failed. A case without metadata
* (every non-gate case) is Claude-only.
*/
export type EvalHost = 'claude' | 'codex';
export const EVAL_HOSTS: readonly EvalHost[] = ['claude', 'codex'];
export function resolveEvalHost(env: NodeJS.ProcessEnv = process.env): EvalHost {
const raw = (env.EVALS_HOST ?? '').trim();
if (!raw) return 'claude';
if ((EVAL_HOSTS as readonly string[]).includes(raw)) return raw as EvalHost;
throw new Error(`EVALS_HOST must be one of ${EVAL_HOSTS.join(', ')}; got "${raw}"`);
}
export const CLAUDE_ONLY_REASONS = {
pty: 'drives the interactive Claude Code TUI (plan mode, native AskUserQuestion) through the PTY harness',
sdk: 'uses the Claude Agent SDK (canUseTool answers and PreToolUse hooks)',
subagents: 'asserts Claude Agent/Task subagent events',
'skill-tool': 'depends on the Claude Skill tool load and registration',
hermetic: 'a claude -p hermetic canary; the Codex host needs its own canary twin',
'self-host': 'the Claude host calling /codex; on the Codex host /codex is the agent itself',
rework: 'parses Claude stream-json tool events or prescribes native Claude tools; not ported to the Codex host',
'host-neutral': 'runs no model session, so a second host adds nothing',
} as const;
export type ClaudeOnlyReason = keyof typeof CLAUDE_ONLY_REASONS;
export type HostSupport = 'both' | ClaudeOnlyReason;
/** Adapter-only cases: final output, files, git state, Bash commands, server logs or browseErrors. */
const ADAPTER_ONLY: readonly string[] = [
'benchmark-workflow',
'browse-basic',
'browse-snapshot',
'canary-workflow',
'context-recovery-artifacts',
'context-restore-loads-latest',
'context-save-writes-file',
'cso-diff-mode',
'design-review-detector-shim',
'design-review-detector-shim-dom',
'design-review-plugin-handoff',
'diagram-triplet',
'document-release',
'gstack-upgrade-happy-path',
'land-and-deploy-first-run',
'land-and-deploy-review-gate',
'land-and-deploy-workflow',
'learnings-show',
'operational-learning',
'plan-design-review-no-ui-scope',
'plan-eng-coverage-audit',
'plan-review-report',
'plan-tune-inspect',
'qa-bootstrap',
'qa-quick',
'retro-base-branch',
'review-army-delivery-audit',
'review-army-json-findings',
'review-army-migration-safety',
'review-army-quality-score',
'review-base-branch',
'review-coverage-audit',
'review-enum-completeness',
'review-sql-injection',
'review-test-value',
'safety-pair-agent-block',
'safety-ship-stale-evidence',
'setup-deploy-workflow',
'ship-base-branch',
'ship-coverage-audit',
'ship-coverage-value',
'ship-local-workflow',
'ship-triage',
'skillmd-no-local-binary',
'skillmd-outside-git',
'skillmd-setup-discovery',
'test-audit-report-only',
'tpa-absent-darwin',
'tpa-absent-linux',
'tpa-apple-ban',
'tpa-broken',
'tpa-present'
];
const CLAUDE_ONLY: Readonly<Record<ClaudeOnlyReason, readonly string[]>> = {
pty: ['autoplan-guard-pty', 'office-hours-auto-mode', 'plan-ceo-finding-floor', 'plan-ceo-review-plan-mode',
'plan-design-with-ui-scope', 'plan-devex-finding-floor', 'plan-devex-review-plan-mode', 'plan-mode-no-op'],
sdk: ['auq-format-gate', 'investigate-owned-abort', 'investigate-owned-completion', 'investigate-owned-ending-error',
'shared-libs-review-index-flags', 'shared-libs-review-lifecycle', 'shared-libs-review-path-eligibility',
'shared-libs-review-prior-coverage', 'shared-libs-review-revalidation', 'ship-local-hook-preservation',
'ship-managed-hook-refresh', 'ship-skipped-queued-finding', 'ship-unmanaged-hook-consent'],
subagents: ['docsync-spawned', 'review-army-perf-n-plus-one'],
'skill-tool': ['skillify-approval-reject', 'skillify-happy-path', 'skillify-provenance-refusal'],
hermetic: ['hermetic-canary', 'hermetic-sentinel'],
'self-host': ['safety-codex-consult-embed'],
rework: ['qa-functional-cli-fix', 'qa-functional-cli-report', 'qa-functional-webhook-fix', 'qa-functional-webhook-report',
'qa-only-no-fix', 'review-dashboard-via', 'review-exploratory-small-cli', 'review-gate-integrity',
'shared-libs-read-only', 'shared-libs-unsupported-git', 'ship-docsync-completion', 'ship-docsync-current',
'ship-docsync-failure', 'ship-docsync-late-result', 'ship-docsync-launch-failure', 'ship-docsync-missing-asset',
'ship-docsync-missing-marker', 'ship-docsync-recovery', 'ship-docsync-stale-after', 'ship-docsync-stale-before',
'ship-docsync-store', 'ship-docsync-timeout-unsettled', 'ship-exploratory-late-input', 'ship-exploratory-plan-checks',
'ship-exploratory-small-cli', 'ship-exploratory-unavailable'],
'host-neutral': ['timeline-event-flow'],
};
export const E2E_HOSTS: Readonly<Record<string, HostSupport>> = Object.freeze(Object.fromEntries([
...ADAPTER_ONLY.map(id => [id, 'both'] as const),
...(Object.entries(CLAUDE_ONLY) as Array<[ClaudeOnlyReason, readonly string[]]>).flatMap(([reason, ids]) => ids.map(id => [id, reason] as const)),
]));
/** Why a case does not run on `host`, or null when it does. */
export function hostSkipReason(id: string, host: EvalHost, hosts: Readonly<Record<string, HostSupport>> = E2E_HOSTS): string | null {
if (host === 'claude') return null;
const support = hosts[id];
if (support === 'both') return null;
if (support === undefined) return `Claude-only on the ${host} host: no Codex host metadata (E2E_HOSTS covers the gate cases)`;
return `Claude-only on the ${host} host: ${CLAUDE_ONLY_REASONS[support]}`;
}
test/helpers/eval-store.ts
+3
View File
@@ -14,6 +14,7 @@ import * as os from 'os';
import { spawnSync } from 'child_process';
import { isManualReviewEntry } from './cookie-workflow-manual-review';
import type { ManualJudgeReview } from './cookie-workflow-manual-review';
import type { CodexTokenUsage } from './codex-session-runner';
// v2: EvalTestEntry.harvest gains optional {insertions, deletions, net} and
// may be explicitly null (arm-benchmark harvest-failure taxonomy). Readers
@@ -67,6 +68,8 @@ export interface EvalTestEntry {
cost_usd: number;
/** False when the harness captured no billing, so cost_usd 0 means unknown. Absent means known. */
cost_known?: boolean;
/** Codex sessions: the token classes behind cost_usd. */
token_usage?: CodexTokenUsage;
/** Absent in older records means executed; reuse is never a new model run. */
execution?: 'executed' | 'reused';
reused_from?: { input_key: string; run_id: string; revision: string; completed_at: string };
test/helpers/free-fixtures-data.ts
+1
View File
@@ -54,6 +54,7 @@ export const FREE_FIXTURES: Readonly<Record<string, readonly string[]>> = {
'test/fixtures/claude-agent-payload-2.1.292.json': ['test/autoplan-publication-payload.test.ts', 'test/autoplan-schema-canary-compare.test.ts'],
'test/fixtures/claude-native-journal-roots-2.1.284.json': ['test/autoplan-publication-hook.test.ts', 'test/plan-count-transcript.test.ts'],
'test/fixtures/codex-boundary-commands.json': ['test/codex-boundary-evidence.test.ts'],
'test/fixtures/codex-host/**': ['test/codex-host.test.ts'],
'test/fixtures/codex-review-sandbox-unavailable-37158847998.json': ['test/outside-voice-evidence.test.ts'],
'test/fixtures/codex-review/**': ['test/codex-hardening.test.ts', 'test/outside-review-severity.test.ts', 'test/outside-voice-evidence.test.ts', 'test/skill-validation.test.ts'],
'test/fixtures/codex-sandbox/**': ['test/codex-eval-recording.test.ts', 'test/codex-model-probe.test.ts', 'test/outside-review-result.test.ts', 'test/outside-voice-invocation.test.ts'],
test/helpers/session-ledger.ts
+5
View File
@@ -12,6 +12,7 @@
*/
import * as fs from 'fs';
import * as path from 'path';
import type { CodexTokenUsage } from './codex-session-runner';
export const SESSION_LEDGER_FILE = 'session-ledger.jsonl';
export const SESSION_EVIDENCE_MAX = 200;
@@ -48,6 +49,10 @@ export interface SessionLedgerRow {
liveness?: LivenessSummary;
/** Whether the runner captured this session's billing (a terminal result with total_cost_usd). */
billed?: boolean;
/** Codex sessions: the model, its billed cost and token classes. */
model?: string;
cost_usd?: number;
tokens?: CodexTokenUsage;
}
/** One line, control characters stripped, mentions neutralized, capped. */
test/helpers/session-runner.ts
+16 -7
View File
@@ -17,6 +17,8 @@ import { hermeticChildEnv, isHermeticEnabled } from './hermetic-env';
import { killProcessGroup } from '../../scripts/test-strict-output';
import { resolveEvalModel } from '../../lib/eval-model';
import { SessionObserver, appendSessionLedger, sessionKey, type SessionEnd } from './session-ledger';
import { resolveEvalHost } from './e2e-hosts';
import type { CodexTokenUsage } from './codex-session-runner';
const GSTACK_DEV_DIR = path.join(os.homedir(), '.gstack-dev');
const HEARTBEAT_PATH = path.join(GSTACK_DEV_DIR, 'e2e-live.json'); // heartbeat stays global
@@ -55,6 +57,10 @@ export interface SkillTestResult {
firstResponseMs: number;
/** Peak latency between consecutive tool calls, in ms */
maxInterTurnMs: number;
/** Codex host: token classes behind costEstimate.estimatedCost. */
tokenUsage?: CodexTokenUsage;
/** Codex host: false when the session completed no turn or its model has no price row. */
costKnown?: boolean;
}
/** Local default startup grace: 90s covers observed API queue latency
@@ -76,6 +82,14 @@ const BROWSE_ERROR_PATTERNS = [
/no such file or directory.*\bbrowse(?:\.exe)?(?=$|[\s'":),])/i,
];
/** First match of each browse failure pattern in tool output plus stderr. */
export function scanBrowseErrors(text: string): string[] {
return BROWSE_ERROR_PATTERNS.flatMap(pattern => {
const match = text.match(pattern);
return match ? [match[0].slice(0, 200)] : [];
});
}
// --- Testable NDJSON parser ---
export interface ParsedNDJSON {
@@ -300,6 +314,7 @@ Setup, CLI startup and API queueing consume this same window; it never resets.
Before source Reads, use Bash to run exactly \`date -u +%Y-%m-%dT%H:%M:%SZ\`. After each saved checkpoint, compare the latest evidence capture's printed completedAt with the times above; run that clock read again only when no capture has completed since your last clock read. When remaining time is at most ${reserve / 1000} seconds, prioritize the remaining required completion outputs and verification. No required content or gate may be skipped. If the clock read fails, report timing unavailable; do not invent remaining time or restart the deadline.`;
systemPrompt = systemPrompt ? `${systemPrompt}\n\n${notice}` : notice;
}
if (resolveEvalHost() === 'codex') return (await import('./codex-host-runner')).runCodexHostSkillTest({ ...options, appendSystemPrompt: systemPrompt, completionReserveMs: undefined });
// Set up per-run log directory if runId is provided
let runDir: string | null = null;
@@ -661,13 +676,7 @@ Before source Reads, use Bash to run exactly \`date -u +%Y-%m-%dT%H:%M:%SZ\`. Af
const { transcript, resultLine, toolCalls } = parsed;
const browseErrors: string[] = [];
const allText = toolCalls.filter(call => call.tool === 'Bash').map(call => call.output).join('\n') + '\n' + stderr;
for (const pattern of BROWSE_ERROR_PATTERNS) {
const match = allText.match(pattern);
if (match) {
browseErrors.push(match[0].slice(0, 200));
}
}
browseErrors.push(...scanBrowseErrors(toolCalls.filter(call => call.tool === 'Bash').map(call => call.output).join('\n') + '\n' + stderr));
// Native Claude uses exit 1 for its structured max-turns result. Preserve
// that existing semantic outcome only after a complete, uncancelled drain;
test/paid-retry-supervision.test.ts
+19 -10
View File
@@ -217,8 +217,9 @@ test('eval:bg runs the PR and release commands with their declared workers (cap:
const cliOptions = (step: { run: string; env?: Record<string, string> }) => {
const prefix = /\bbun(?: --no-install)? run scripts\/test-paid-shards\.ts /.exec(step.run);
expect(prefix).not.toBeNull();
const args = step.run.slice(prefix!.index + prefix![0].length)
.replace(/\$\{\{\s*matrix\.slice\s*\}\}/g, '1').trim().split(/\s+/);
// One command line: a census arm loop continues past it.
const args = step.run.slice(prefix!.index + prefix![0].length).split('\n')[0]!
.replace(/\$\{\{\s*matrix\.slice\s*\}\}/g, '1').replace(/\$\{\{\s*matrix\.arm\s*\}\}/g, 'claude-opus').trim().split(/\s+/);
return parseCliOptions(args, step.env ?? {});
};
@@ -242,10 +243,16 @@ test('both gate executors plan the complete census and supervise every planned s
expect(planned.skipJudges).toBe(skipJudges);
expect(execute[0].env.EVALS_CONCURRENCY).toBe('2');
expect(executor.strategy['fail-fast']).toBe(false);
expect(executor.strategy.matrix.slice).toBe(`\${{ fromJSON(needs.plan-slices.outputs.${prefix}slices) }}`);
// Per-slice ceilings (W2c/ENG-2), or the largest of them as one job cap.
expect([`\${{ fromJSON(needs.plan-slices.outputs.${prefix}slice_timeouts)[matrix.slice] }}`,
`\${{ fromJSON(needs.plan-slices.outputs.${prefix}timeout_minutes) }}`]).toContain(executor['timeout-minutes']);
if (jobName === 'gate-census') {
// One row per census arm and planned slice, each with its arm's planned slice ceiling (scripts/census-arms.ts).
expect(executor.strategy.matrix.include).toBe('${{ fromJSON(needs.plan-slices.outputs.gate_matrix) }}');
expect(executor['timeout-minutes']).toBe('${{ matrix.timeout }}');
} else {
expect(executor.strategy.matrix.slice).toBe(`\${{ fromJSON(needs.plan-slices.outputs.${prefix}slices) }}`);
// Per-slice ceilings (W2c/ENG-2), or the largest of them as one job cap.
expect([`\${{ fromJSON(needs.plan-slices.outputs.${prefix}slice_timeouts)[matrix.slice] }}`,
`\${{ fromJSON(needs.plan-slices.outputs.${prefix}timeout_minutes) }}`]).toContain(executor['timeout-minutes']);
}
const manifest = buildRunManifest({ tier: 'gate', sliceBudgetMs: planned.sliceBudgetMs!, jobs: planned.jobs, evalsAll: true, env: { EVALS_ALL: '1' }, skipJudges });
const files = [...new Set(manifest.entries.filter(row => row.status === 'planned').map(row => shardFile(row.file)))];
expect(files).toContain('test/skill-e2e-ship-skip.test.ts');
@@ -262,8 +269,8 @@ test('both gate executors plan the complete census and supervise every planned s
expect(manifest.sliceCount).toBeLessThanOrEqual(executor.strategy['max-parallel']);
if (jobName === 'gate-census') {
expect(emit[0].env.EVALS_ALL).toBe('1');
expect(emit[0].run).toContain('--emit-plan /tmp/gate-census-plan/manifest.json');
expect(execute[0].run).toContain('--plan /tmp/gate-census-plan/manifest.json --slice ${{ matrix.slice }}');
expect(emit[0].run).toContain('--emit-plan "/tmp/gate-census-plan/$arm/manifest.json"');
expect(execute[0].run).toContain('--plan /tmp/gate-census-plan/${{ matrix.arm }}/manifest.json --slice ${{ matrix.slice }}');
expect(executor.steps.some((step: any) => step.with?.name === 'gate-census-plan')).toBe(true);
expect(executor.steps.filter((step: any) => step.run?.includes('--emit-plan '))).toHaveLength(0);
}
@@ -305,8 +312,10 @@ test('gate census requires all seven distinct slice results and its own reconcil
const reconcile = report.steps.find((step: any) => step.id === 'gate-reconcile');
expect(report.needs).toContain('gate-census');
expect(reconcile.if).toBe('always()');
expect(reconcile.run).toContain('EVALS_TIER=gate bun run scripts/test-paid-shards.ts --tier gate --report /tmp/gate-census-report');
expect(reconcile.run).toContain('exit=${PIPESTATUS[0]}');
// One reconciliation per census arm, each against its own plan and slices.
expect(reconcile.run).toContain('dir="/tmp/gate-census-report/$arm"');
expect(reconcile.run).toContain('EVALS_TIER=gate bun run scripts/test-paid-shards.ts --tier gate --report "$dir"');
expect(reconcile.run).toContain('code=${PIPESTATUS[0]}');
const failureGuards = report.steps.filter((step: any) => /Upsert tracking|Fail the workflow/.test(step.name ?? ''));
expect(failureGuards).toHaveLength(2);
for (const step of failureGuards) {
test/paid-shards.test.ts
+1 -1
View File
@@ -178,7 +178,7 @@ describe('tier lane skip (B5)', () => {
}
const workflow = fs.readFileSync(path.join(ROOT, '.github/workflows/evals-periodic.yml'), 'utf8');
expect(workflow.match(/--skip-judges/g)).toHaveLength(1);
expect(workflow).toMatch(/--tier gate --emit-plan \/tmp\/gate-census-plan\/manifest\.json --slice-budget 420 --jobs 2 --skip-judges/);
expect(workflow).toMatch(/--tier gate --emit-plan "\/tmp\/gate-census-plan\/\$arm\/manifest\.json" --slice-budget 420 --jobs 2 --skip-judges/);
});
});