Merge origin/main (v1.64.1.0) into garrytan/time-attack-fork-review

The code-smell wave refactored the tunnel start into the staged startTunnel helper; the merge adopts that structure and threads this branch's truthful consent strings through its consent parameter (the receipt now names the isPairAgentEnabled gate at both call sites). The eng-review PTY warmup takes both improvements: main's resolveClaudeBinary fallback and this branch's resolveEvalModel kind. Resolver imports union; carve budgets take the larger of both waves' measured values (parity suite green on the merged tree); conflicted generated SKILL.md files regenerated from resolved sources. VERSION stays 1.65.0.0 over main's 1.64.1.0; CHANGELOG stacks 1.65.0.0 > 1.64.1.0 > 1.64.0.0.
2026-09-10 06:58:59 +02:00 · 2026-08-15 10:01:18 -07:00
parent 7898b80686 c118e2402e
commit 3fffeab725
187 changed files with 2744 additions and 22778 deletions
@@ -28,9 +28,13 @@ RUN printf 'Acquire::Retries "5";\nAcquire::http::Timeout "30";\nAcquire::https:

 # System deps (retry apt-get update + install as a unit — even Hetzner can blip).
 # Includes xz-utils so the Node.js .tar.xz download below can decompress.
+# python3: bin/gstack-jsonl-merge, gstack-brain-sync, gstack-detach, and other
+#   bash bins shell out to it (macOS ships python3; the base image doesn't).
+# file: skill-validation's no-compiled-binaries-in-git check runs `file --mime-type`.
+# poppler-utils: make-pdf's e2e gates hard-require pdftotext/pdffonts/pdfinfo in CI.
 RUN for i in 1 2 3; do \
      apt-get update && apt-get install -y --no-install-recommends \
-        git curl unzip xz-utils ca-certificates jq bc gpg && break || \
+        git curl unzip xz-utils ca-certificates jq bc gpg python3 file poppler-utils && break || \
      (echo "apt retry $i/3 after failure"; sleep 10); \
    done \
    && rm -rf /var/lib/apt/lists/*
@@ -61,10 +65,14 @@ RUN curl --retry 5 --retry-delay 5 --retry-connrefused -fsSL "https://nodejs.org
    && node --version \
    && npm --version

-# Bun (install to /usr/local so non-root users can access it)
+# Bun (install to /usr/local so non-root users can access it).
+# The version MUST be passed as a positional arg — bun.sh/install ignores a
+# BUN_VERSION env var, so the old `| BUN_VERSION=x.y.z bash` form silently
+# installed latest on every image rebuild (observed: 1.3.13/1.3.14 drift vs
+# the 1.3.10 devs run locally).
 ENV BUN_INSTALL="/usr/local"
 RUN curl --retry 5 --retry-delay 5 --retry-connrefused -fsSL https://bun.sh/install \
-    | BUN_VERSION=1.3.10 bash
+    | bash -s "bun-v1.3.10"

 # Claude CLI
 RUN npm i -g @anthropic-ai/claude-code
@@ -82,8 +90,10 @@ RUN npx playwright install-deps chromium
 # (headed-xvfb, headed-orphan-cleanup) can exercise the Linux container
 # auto-spawn path on every CI run. Without Xvfb in the image, the most
 # common production --headed path goes untested.
+# fonts-noto-color-emoji: the make-pdf emoji render gate needs a color-emoji
+# fallback font (mirrors make-pdf-gate.yml's Ubuntu setup step).
 RUN for i in 1 2 3; do \
-      apt-get update && apt-get install -y --no-install-recommends fonts-liberation fontconfig xvfb x11-utils && break || \
+      apt-get update && apt-get install -y --no-install-recommends fonts-liberation fonts-noto-color-emoji fontconfig xvfb x11-utils && break || \
      (echo "fonts-liberation install retry $i/3"; sleep 10); \
    done \
    && fc-cache -f \
@@ -105,6 +115,7 @@ RUN npx playwright install chromium \

 # Verify everything works
 RUN bun --version && node --version && claude --version && jq --version && gh --version \
+    && python3 --version && command -v file && command -v pdftotext && command -v pdffonts && command -v pdfinfo \
    && npx playwright --version \
    && fc-match "Liberation Sans" | grep -qi "Liberation" \
        || (echo "ERROR: fonts-liberation not installed — make-pdf PDFs will render in DejaVu Sans" && exit 1)
@@ -0,0 +1,184 @@
+name: Free Tests
+# The full free suite (`bun test`: browse/test/ + test/ + make-pdf/test/ minus
+# paid evals) previously ran in NO CI job — only Windows curated shards, paid
+# evals, and doc-freshness gates existed. Two test files crashed at module load
+# for 48 versions without any signal. This job closes that hole.
+on:
+  pull_request:
+    branches: [main]
+  workflow_dispatch:
+
+concurrency:
+  group: free-tests-${{ github.head_ref }}
+  cancel-in-progress: true
+
+env:
+  IMAGE: ghcr.io/${{ github.repository }}/ci
+
+jobs:
+  # Same cached pre-baked toolchain image as evals.yml (only rebuilds on
+  # Dockerfile/lockfile change).
+  build-image:
+    runs-on: ubicloud-standard-8
+    permissions:
+      contents: read
+      packages: write
+    outputs:
+      image-tag: ${{ steps.meta.outputs.tag }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - id: meta
+        run: echo "tag=${{ env.IMAGE }}:${{ hashFiles('.github/docker/Dockerfile.ci', 'package.json', 'bun.lock') }}" >> "$GITHUB_OUTPUT"
+
+      - uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Check if image exists
+        id: check
+        run: |
+          if docker manifest inspect ${{ steps.meta.outputs.tag }} > /dev/null 2>&1; then
+            echo "exists=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "exists=false" >> "$GITHUB_OUTPUT"
+          fi
+
+      - if: steps.check.outputs.exists == 'false'
+        run: cp package.json bun.lock .github/docker/
+
+      - if: steps.check.outputs.exists == 'false'
+        uses: docker/build-push-action@v6
+        with:
+          context: .github/docker
+          file: .github/docker/Dockerfile.ci
+          push: true
+          tags: |
+            ${{ steps.meta.outputs.tag }}
+            ${{ env.IMAGE }}:latest
+
+  free-tests:
+    runs-on: ubicloud-standard-8
+    needs: build-image
+    container:
+      image: ${{ needs.build-image.outputs.image-tag }}
+      credentials:
+        username: ${{ github.actor }}
+        password: ${{ secrets.GITHUB_TOKEN }}
+      options: --user runner
+    timeout-minutes: 45
+    steps:
+      - uses: actions/checkout@v4
+
+      # Bun creates root-owned temp dirs during Docker build. GH Actions runs as
+      # runner user with HOME=/github/home. Redirect bun's cache to a writable dir.
+      - name: Fix bun temp
+        run: |
+          mkdir -p /home/runner/.cache/bun
+          {
+            echo "BUN_INSTALL_CACHE_DIR=/home/runner/.cache/bun"
+            echo "BUN_TMPDIR=/home/runner/.cache/bun"
+            echo "TMPDIR=/home/runner/.cache"
+          } >> "$GITHUB_ENV"
+
+      # Several test files exercise real git operations (gstack-artifacts-init,
+      # session-update-autostash, team-mode, brain-sync) and bins that read the
+      # current branch (gstack-decision-search). The container checkout is owned
+      # by a different uid than `runner`, so git needs safe.directory, and
+      # commit-making tests need an identity.
+      - name: Git identity for git-exercising tests
+        run: |
+          git config --global user.email "ci@gstack.invalid"
+          git config --global user.name "gstack CI"
+          git config --global --add safe.directory '*'
+
+      # Same restore rationale as evals.yml: recursive copy beats symlink
+      # (realpath escapes workspace) and hardlink (cross-device overlay-fs).
+      - name: Restore deps
+        run: |
+          if [ -d /opt/node_modules_cache ] && diff -q /opt/node_modules_cache/.package.json package.json >/dev/null 2>&1; then
+            cp -r /opt/node_modules_cache node_modules
+          else
+            bun install
+          fi
+
+      - run: bun run build
+
+      # Fail fast if the container can't launch Chromium — the browse
+      # integration tests need it.
+      - name: Verify Chromium
+        run: |
+          echo "whoami=$(whoami) HOME=$HOME TMPDIR=${TMPDIR:-unset}"
+          bun -e "import {chromium} from 'playwright';const b=await chromium.launch({args:['--no-sandbox']});console.log('Chromium OK');await b.close()"
+
+      # ONE BUN PROCESS PER FILE, on purpose. A single multi-file `bun test`
+      # run of this suite is structurally unreliable here — observed twice
+      # while building this job:
+      # 1. Silent truncation: server-lifecycle tests stub process.exit, and
+      #    shutdown's async timers can hit the REAL exit after restore,
+      #    killing the whole bun process mid-suite with exit 0 and NO
+      #    summary (died at file 47, then file 51, of 358).
+      # 2. Co-run state bleed: files green in isolation failed under
+      #    multi-file module sharing.
+      # Per-file spawning makes truncation impossible by construction (the
+      # census drives the loop; a killed child is a recorded failure, not a
+      # vanished suite) and also covers the old exit-0-on-module-load-error
+      # Bun behavior. Same isolation model as scripts/test-paid-shards.ts.
+      - name: Run free suite (per-file isolation)
+        shell: bash
+        run: |
+          set -o pipefail
+          # Container-incompatible files, each with a reason (same curated-
+          # exclusion pattern as the Windows shards in test-free-shards.ts).
+          # Anything NOT on this list that fails still fails the job. Trimming
+          # this list is tracked follow-up work.
+          declare -A SKIP=(
+            [browse/test/compare-board.test.ts]="pre-existing env failure (also fails on dev machines; needs a display-shaped env)"
+            [browse/test/handoff.test.ts]="needs the headed Chrome-for-Testing build (headless-only container)"
+            [browse/test/snapshot.test.ts]="pre-existing env failure (viewport/tab timing under container load)"
+            [browse/test/extension-sender-auth.test.ts]="extension identity checks need a real chrome-extension origin"
+            [browse/test/security-sidepanel-dom.test.ts]="sidepanel DOM harness needs the extension loaded headed"
+            [browse/test/terminal-agent-integration.test.ts]="real PTY round-trip; container TTY semantics differ"
+            [browse/test/xvfb.test.ts]="tests xvfb management; container has no X server to manage"
+            [browse/test/security-audit-r2.test.ts]="one behavioral tmpdir-allowlist test breaks under this job's TMPDIR override (bun temp-dir workaround above)"
+            [design/test/variants-retry-after.test.ts]="known timing flake, tracked in TODOS.md (HTTP-date Retry-After rounding)"
+          )
+          FILES=$(bun run scripts/test-free-shards.ts --list | grep -E '^  (browse/|test/|make-pdf/|design/)' | sed 's/^  //')
+          TOTAL=$(echo "$FILES" | wc -l | tr -d ' ')
+          echo "Enumerated $TOTAL free test files"
+          FAILED=""
+          N=0
+          SKIPPED=0
+          for f in $FILES; do
+            N=$((N+1))
+            if [ -n "${SKIP[$f]:-}" ]; then
+              echo "SKIP [$N/$TOTAL] $f — ${SKIP[$f]}"
+              SKIPPED=$((SKIPPED+1))
+              continue
+            fi
+            if ! bun test "$f" > /tmp/one.log 2>&1; then
+              echo "FAIL [$N/$TOTAL] $f"
+              tail -30 /tmp/one.log
+              FAILED="$FAILED $f"
+            fi
+          done
+          echo "Skipped $SKIPPED container-incompatible files (reasons above)."
+          # Tree-mutation tripwire: a test that rewrites tracked files poisons
+          # every later file in the loop with confusing failures (observed:
+          # gstack-config's skill_prefix auto-relink patched 52 SKILL.md names,
+          # failing five unrelated suites downstream). Name the real culprit.
+          MUTATED=$(git status --porcelain --untracked-files=no)
+          if [ -n "$MUTATED" ]; then
+            echo ""
+            echo "A test mutated tracked files in the working tree — later failures may be collateral:"
+            echo "$MUTATED"
+            FAILED="$FAILED [tree-mutation]"
+          fi
+          if [ -n "$FAILED" ]; then
+            echo ""
+            echo "Failed files:$FAILED"
+            exit 1
+          fi
+          echo "All $((TOTAL-SKIPPED)) runnable files green."
@@ -15,27 +15,32 @@ jobs:
      - uses: actions/checkout@v4
      - uses: oven-sh/setup-bun@v2
      - run: bun install
-      - name: Check Claude host freshness
-        run: bun run gen:skill-docs
-      - name: Verify Claude skill docs are fresh
+      # One generation pass for ALL 10 hosts. gen-skill-docs --host all
+      # hard-fails on any per-host generation error (scripts/gen-skill-docs.ts
+      # aggregates failures and exits non-zero), so every host is gated on
+      # "generates cleanly." Known limitation, on purpose: the 9 gitignored
+      # host outputs (.agents/, .factory/, .kiro/, ...) are NOT byte-freshness
+      # checked — `git diff` on ignored untracked paths is always empty (the
+      # previous per-host `git diff -- .agents/` gates could never fail for
+      # exactly that reason). Byte-freshness is enforced only for tracked
+      # output (the Claude SKILL.md files), which the two steps below cover.
+      - name: Generate all host skill docs
+        run: bun run gen:skill-docs --host all
+      - name: Verify tracked skill docs are fresh
        run: |
          git diff --exit-code || {
-            echo "Generated SKILL.md files are stale. Run: bun run gen:skill-docs"
+            echo "Generated SKILL.md files are stale. Run: bun run gen:skill-docs --host all"
            exit 1
          }
-      - name: Check Codex host freshness
-        run: bun run gen:skill-docs --host codex
-      - name: Verify Codex skill docs are fresh
+      # git diff misses NEW untracked files (e.g. a freshly added skill whose
+      # generated SKILL.md was never committed). Fail on any untracked stray
+      # the generator produced outside the gitignored host dirs.
+      - name: Verify no untracked generated files
        run: |
-          git diff --exit-code -- .agents/ || {
-            echo "Generated Codex SKILL.md files are stale. Run: bun run gen:skill-docs --host codex"
+          STRAYS=$(git status --porcelain --untracked-files=all | grep '^??' || true)
+          if [ -n "$STRAYS" ]; then
+            echo "Generator produced untracked files that are neither committed nor gitignored:"
+            echo "$STRAYS"
+            echo "Commit them (bun run gen:skill-docs --host all) or gitignore them."
            exit 1
-          }
-      - name: Generate Factory skill docs
-        run: bun run gen:skill-docs --host factory
-      - name: Verify Factory skill docs are fresh
-        run: |
-          git diff --exit-code -- .factory/ || {
-            echo "Generated Factory SKILL.md files are stale. Run: bun run gen:skill-docs --host factory"
-            exit 1
-          }
+          fi