Merge pull request #9609 from esengine/release-notes/v1.34.0

docs(release): 准备 v1.34.0 中英更新日志

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -7,7 +7,7 @@ body:
     attributes:
       value: |
         Thanks for filing a bug. Pick which version line you're on below — it gets
-        labeled (`v1`/`v2`) automatically, no maintainer action needed.
+        labeled (`v2`/`v3`) automatically, no maintainer action needed.
   - type: dropdown
     id: version-line
     attributes:
@@ -15,7 +15,7 @@ body:
       description: Which line are you running?
       options:
         - "v2 — Go rewrite (1.x), main-v2 (active development)"
-        - "v1 — Legacy TypeScript (0.x), maintenance only"
+        - "v3 — Studio (2.x), studio"
     validations:
       required: true
   - type: input

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -10,7 +10,7 @@ body:
       description: Which line is this for?
       options:
         - "v2 — Go rewrite (1.x), main-v2 (active development)"
-        - "v1 — Legacy TypeScript (0.x), maintenance only"
+        - "v3 — Studio (2.x), studio"
     validations:
       required: true
   - type: textarea

.github/pull_request_template.md

@@ -15,6 +15,12 @@ release workflow then asks that reporter to verify once the fix ships.
 
 -
 
+For a GSAP to WAAPI/CSS migration (or any cross-API replacement), document
+the source-to-target contract here: easing syntax, time units, callbacks,
+cancellation, reduced-motion behavior, and failure fallback. Verification must
+assert that the target API was actually called; a mock that silently skips it
+does not count.
+
 ## Documentation impact
 
 Documentation-impact: TODO

.github/workflows/ci.yml

@@ -145,14 +145,15 @@ jobs:
       # internal/agent 82s, 92s, 144s and 180s — a 2.2x spread from runner
       # variance alone, with four heavy packages sharing four vCPUs. At 3m the
       # step failed on slow runners without a code change; a hang still trips
-      # the 15 minute job budget above.
+      # the 15 minute job budget above. internal/control runs in its own
+      # Windows job below so its durable-session I/O does not compete here.
       - name: test (Windows smoke)
         if: env.RUN_STEPS == 'true' && runner.os == 'Windows' && github.event_name == 'pull_request'
         timeout-minutes: 15
         env:
           REASONIX_RELEASE_CACHE_GUARD: "1"
           WINDOWS_SANDBOX_WAIT_MS: "20000"
-        run: go test -p 4 -timeout=8m ./internal/agent/... ./internal/appidentity/... ./internal/boot/... ./internal/checkpoint/... ./internal/cli/... ./internal/control/... ./internal/desktoplauncher/... ./internal/filelock/... ./internal/fileutil/... ./internal/hook/... ./internal/instruction/... ./internal/mcplaunch/... ./internal/notify/... ./internal/proc/... ./internal/remote/... ./internal/repair/... ./internal/sandbox/... ./internal/sysproxy/... ./internal/workspacelease/... ./cmd/...
+        run: go test -p 4 -timeout=8m ./internal/agent/... ./internal/appidentity/... ./internal/boot/... ./internal/checkpoint/... ./internal/cli/... ./internal/desktoplauncher/... ./internal/filelock/... ./internal/fileutil/... ./internal/hook/... ./internal/instruction/... ./internal/mcplaunch/... ./internal/notify/... ./internal/proc/... ./internal/remote/... ./internal/repair/... ./internal/sandbox/... ./internal/sysproxy/... ./internal/workspacelease/... ./cmd/...
 
       # The general Windows PR smoke list intentionally omits internal/tool.
       # Keep the session-temp portability contract covered without widening the
@@ -171,9 +172,14 @@ jobs:
         timeout-minutes: 5
         run: go test -timeout=3m -run '^TestBashPowerShellExecuteDetailedContract$|^TestBashPowerShell51PreflightRejectsAndAndDetailed$|^TestBashPowerShellOutputIsUTF8$|^TestBashPowerShellSurfacesNonZeroExit$|^TestBashPowerShellRejectsChaining$' ./internal/tool/builtin
 
+      # Full push suite still uses the same 8m package budget as Windows smoke:
+      # agent/boot/control already hit 180s package timeouts under runner load,
+      # so 3m fails on slow machines without a code regression. Keep the step
+      # above normal full-suite wall time (~8-12m) so a hang still dies on the
+      # job budget rather than a false package timeout.
       - name: test (full)
         if: env.RUN_STEPS == 'true' && runner.os == 'Windows' && github.event_name != 'pull_request'
-        timeout-minutes: 10
+        timeout-minutes: 20
         env:
           # Run the prompt-cache prefix-stability guard (TestCacheHit*) in CI: a
           # regression there silently tanks the cache hit rate the project is
@@ -182,7 +188,7 @@ jobs:
           # Bound sandbox helper children in Windows tests so a failed OS-level
           # launch cannot pin the Actions step after Go's package timeout fires.
           WINDOWS_SANDBOX_WAIT_MS: "20000"
-        run: go test -p 4 -timeout=3m ./...
+        run: go test -p 4 -timeout=8m ./...
 
       - name: test (Scoop desktop launch)
         if: env.RUN_STEPS == 'true' && runner.os == 'Windows'
@@ -190,6 +196,30 @@ jobs:
         shell: powershell
         run: .\scripts\test-scoop-desktop-launch.ps1
 
+  windows-control:
+    needs: changes
+    if: always()
+    runs-on: windows-latest
+    env:
+      RUN_STEPS: ${{ github.event_name != 'pull_request' || needs.changes.outputs.code != 'false' }}
+    steps:
+      - if: env.RUN_STEPS == 'true'
+        uses: actions/checkout@v7
+
+      - if: env.RUN_STEPS == 'true'
+        uses: actions/setup-go@v7
+        with:
+          go-version-file: go.mod
+          cache: true
+
+      - name: test
+        if: env.RUN_STEPS == 'true'
+        timeout-minutes: 10
+        env:
+          REASONIX_RELEASE_CACHE_GUARD: "1"
+          WINDOWS_SANDBOX_WAIT_MS: "20000"
+        run: go test -p 1 -timeout=8m ./internal/control/...
+
   race:
     needs: changes
     if: always() && (github.event_name != 'pull_request' || needs.changes.outputs.code != 'false')
@@ -321,7 +351,7 @@ jobs:
       - name: Install Wails CLI
         run: |
           echo "$(go env GOPATH)/bin" >> "$GITHUB_PATH"
-          go install github.com/wailsapp/wails/v2/cmd/wails@v2.12.0
+          go install "github.com/wailsapp/wails/v2/cmd/wails@$(cat "$GITHUB_WORKSPACE/.wails-version")"
 
       - name: gofmt
         run: |
@@ -345,18 +375,43 @@ jobs:
       - name: Install Linux build deps
         run: |
           sudo apt-get update
-          sudo apt-get install -y gcc libgtk-3-dev libwebkit2gtk-4.0-dev
+          sudo apt-get install -y dbus-daemon gcc libgtk-3-dev libwebkit2gtk-4.0-dev xvfb
 
       - name: Build frontend
         run: |
           wails generate module
           pnpm --dir frontend install --frozen-lockfile
+          PLAYWRIGHT_BROWSERS_PATH=.pw-browsers pnpm --dir frontend exec playwright install --with-deps chromium webkit
           pnpm --dir frontend build
 
       - name: Test desktop frontend
         run: |
           pnpm --dir frontend test:terminal
           pnpm --dir frontend test:task-monitor
+          pnpm --dir frontend test:mcp-app
+          pnpm --dir frontend test:workspace
+          pnpm --dir frontend test:stream
+          pnpm --dir frontend test:motion
+          pnpm --dir frontend test:motion-browser
+          pnpm --dir frontend test:composer
+          pnpm --dir frontend test:todo-visibility
+          pnpm --dir frontend test:transcript
+          xvfb-run -a env REASONIX_TRANSCRIPT_NATIVE_THUMB=1 pnpm --dir frontend test:transcript-browser
+          PLAYWRIGHT_BROWSERS_PATH=.pw-browsers pnpm --dir frontend test:transcript-reader-browser
+
+      - name: Test WebKitGTK native transcript scrolling
+        timeout-minutes: 5
+        run: |
+          pnpm --dir frontend exec vite preview --host 127.0.0.1 --port 4173 --strictPort >/tmp/reasonix-transcript-preview.log 2>&1 &
+          preview_pid=$!
+          trap 'kill "$preview_pid" 2>/dev/null || true' EXIT
+          for _ in $(seq 1 100); do
+            curl -fsS http://127.0.0.1:4173/ >/dev/null && break
+            sleep 0.1
+          done
+          xvfb-run -a env WEBKIT_DISABLE_COMPOSITING_MODE=1 go run -tags reasonix_transcript_smoke ./cmd/transcript-native-smoke \
+            -url 'http://127.0.0.1:4173/?mock=bench&bench=1' \
+            -script transcript_native_smoke_contract.js
 
       - name: Test usage statistics frontend
         run: pnpm --dir frontend test:usage-stats
@@ -377,14 +432,46 @@ jobs:
       - name: test
         run: go test ./...
 
+      - name: WebKitGTK 4.0 native recovery smoke
+        run: xvfb-run -a env WEBKIT_DISABLE_COMPOSITING_MODE=1 go test -tags reasonix_webkit_smoke . -run '^TestWebKitNativeRecoverySmoke$'
+
       # The extension work added new shared-state paths to the desktop
       # runtime (tab/rebuild fences, extension UI). Race-sweep the module so
       # regressions are CI-blocked, not just author-verified locally.
       - name: test -race
         run: go test -race ./...
 
+  # Ubuntu 24.04 ships WebKitGTK 4.1 only. Keep this capability build separate
+  # from the 22.04/4.0 leg so neither runtime becomes a distro whitelist.
+  desktop-linux-webkit41:
+    needs: changes
+    if: always() && (github.event_name != 'pull_request' || needs.changes.outputs.desktop != 'false')
+    runs-on: ubuntu-24.04
+    defaults:
+      run:
+        working-directory: desktop
+    steps:
+      - uses: actions/checkout@v7
+
+      - uses: actions/setup-go@v7
+        with:
+          go-version-file: desktop/go.mod
+          cache: true
+          cache-dependency-path: desktop/go.sum
+
+      - name: Install WebKitGTK 4.1 build dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y dbus-daemon gcc libgtk-3-dev libwebkit2gtk-4.1-dev xvfb
+
+      - name: Build and test WebKitGTK 4.1 observer
+        run: go test -tags webkit2_41 ./...
+
+      - name: WebKitGTK 4.1 native recovery smoke
+        run: xvfb-run -a env WEBKIT_DISABLE_COMPOSITING_MODE=1 go test -tags 'webkit2_41 reasonix_webkit_smoke' . -run '^TestWebKitNativeRecoverySmoke$'
+
   # desktop/ is a separate module, so the root macOS matrix above does not
-  # compile or exercise the native PTY implementation.
+  # compile or exercise the native PTY and FSEvents implementations.
   desktop-macos:
     needs: changes
     if: always() && (github.event_name != 'pull_request' || needs.changes.outputs.desktop != 'false')
@@ -401,8 +488,51 @@ jobs:
           cache: true
           cache-dependency-path: desktop/go.sum
 
-      - name: Test integrated terminal and PTY lifecycle
-        run: go test -race -run 'Test(ResolveTerminal|Terminal|EmptyTerminal|UnixTerminalProcess)' .
+      - uses: pnpm/[email protected]
+        with:
+          version: 10
+          run_install: false
+
+      - uses: actions/setup-node@v7
+        with:
+          node-version: "24"
+          cache: pnpm
+          cache-dependency-path: desktop/frontend/pnpm-lock.yaml
+
+      - name: Install Wails CLI and build frontend
+        run: |
+          echo "$(go env GOPATH)/bin" >> "$GITHUB_PATH"
+          go install "github.com/wailsapp/wails/v2/cmd/wails@$(cat "$GITHUB_WORKSPACE/.wails-version")"
+          wails generate module
+          pnpm --dir frontend install --frozen-lockfile
+          pnpm --dir frontend build
+
+      - name: Test WKWebView native transcript scrolling
+        timeout-minutes: 5
+        env:
+          REASONIX_NATIVE_SMOKE_ISOLATED_CI: "1"
+        run: |
+          pnpm --dir frontend exec vite preview --host 127.0.0.1 --port 4173 --strictPort >/tmp/reasonix-transcript-preview.log 2>&1 &
+          preview_pid=$!
+          trap 'kill "$preview_pid" 2>/dev/null || true' EXIT
+          for _ in $(seq 1 100); do
+            curl -fsS http://127.0.0.1:4173/ >/dev/null && break
+            sleep 0.1
+          done
+          go run -tags reasonix_transcript_smoke ./cmd/transcript-native-smoke \
+            -url 'http://127.0.0.1:4173/?mock=bench&bench=1' \
+            -script transcript_native_smoke_contract.js
+
+      - name: Test integrated terminal, PTY, and FSEvents lifecycle
+        run: go test -race -run 'Test(DarwinWorkspaceWatcher|WorkspaceChangeHub|ResolveTerminal|Terminal|EmptyTerminal|UnixTerminalProcess)' .
+
+      # The production Wails build uses CGO. Keep the explicit unavailable
+      # backend buildable as a fail-closed portability contract instead of
+      # silently falling back to kqueue's per-file descriptor usage.
+      - name: Test macOS build without CGO
+        env:
+          CGO_ENABLED: "0"
+        run: go test -run '^TestDarwinWorkspaceWatcherWithoutCGOIsUnavailable$' .
 
       # desktop/*_darwin.go is the one build-tag set the lint job cannot reach:
       # the main-thread watchdog is cgo, so it only type-checks with a real
@@ -449,7 +579,7 @@ jobs:
       - name: Install Wails CLI
         run: |
           echo "$(go env GOPATH)/bin" >> "$GITHUB_PATH"
-          go install github.com/wailsapp/wails/v2/cmd/wails@v2.12.0
+          go install "github.com/wailsapp/wails/v2/cmd/wails@$(cat "$GITHUB_WORKSPACE/.wails-version")"
 
       # go:embed of frontend/dist needs a built frontend before the package
       # compiles, same as the ubuntu desktop leg.
@@ -459,10 +589,81 @@ jobs:
           pnpm --dir frontend install --frozen-lockfile
           pnpm --dir frontend build
 
+      - name: Test native motion contracts
+        run: pnpm --dir frontend test:motion
+
+      # Chromium is the closest deterministic browser replay available on the
+      # Windows runner; the native smoke below separately exercises the actual
+      # installed WebView2 runtime. Keep both paths so transcript geometry is
+      # covered before the shell-level smoke starts.
+      - name: Test transcript browser replay on Windows
+        timeout-minutes: 10
+        env:
+          PLAYWRIGHT_BROWSERS_PATH: ${{ github.workspace }}/desktop/frontend/.pw-browsers
+        run: |
+          pnpm --dir frontend exec playwright install chromium
+          pnpm --dir frontend test:transcript-browser
+
+      - name: Test WebView2 native transcript and composer scrolling
+        timeout-minutes: 5
+        run: |
+          pnpm --dir frontend exec vite preview --host 127.0.0.1 --port 4173 --strictPort > "$RUNNER_TEMP/reasonix-transcript-preview.log" 2>&1 &
+          preview_pid=$!
+          trap 'kill "$preview_pid" 2>/dev/null || true' EXIT
+          for _ in $(seq 1 100); do
+            curl -fsS http://127.0.0.1:4173/ >/dev/null && break
+            sleep 0.1
+          done
+          go run -tags reasonix_transcript_smoke ./cmd/transcript-native-smoke \
+            -url 'http://127.0.0.1:4173/?mock=bench&bench=1&nativeComposer=1' \
+            -script transcript_native_smoke_contract.js
+
+      - name: Test WebView2 native smoke state machine
+        shell: pwsh
+        run: ../scripts/test-webview2-native-smoke.ps1 -SelfTest
+
+      - name: Test WebView2 transcript selection compositor
+        shell: pwsh
+        timeout-minutes: 5
+        run: ../scripts/test-transcript-selection-webview2.ps1 -Iterations 3
+
+      - name: Upload WebView2 transcript selection evidence
+        if: failure()
+        uses: actions/upload-artifact@v7
+        with:
+          name: webview2-transcript-selection-${{ github.run_id }}-${{ github.run_attempt }}
+          path: ${{ runner.temp }}/reasonix-transcript-selection-smoke
+          if-no-files-found: warn
+          retention-days: 14
+
+      # Build the real Wails executable on every desktop PR and exercise the
+      # exact production startup path in Microsoft's installed WebView2 runtime.
+      # The frontend and bindings were already built above, so this skips only
+      # duplicate build work, not the native shell.
+      - name: Build Wails executable for native startup smoke
+        timeout-minutes: 10
+        run: wails build -clean -s -skipbindings -nopackage -platform windows/amd64 -webview2 embed
+
+      - name: Smoke-test Wails/WebView2 native startup
+        shell: pwsh
+        timeout-minutes: 2
+        run: |
+          ../scripts/test-webview2-native-smoke.ps1 `
+            -ExecutablePath "build/bin/reasonix-desktop.exe" `
+            -TimeoutSeconds 60 `
+            -HealthySeconds 5
+
       - name: test (Windows desktop and update helper)
         timeout-minutes: 15
         run: go test ./...
 
+      # A cold nested-module cache can spend several minutes compiling the
+      # real WebView2 cookie integration test. Keep its budget independent of
+      # the already-complete desktop suite and retain a Go timeout stack dump.
+      - name: test (vendored WebView2 edge)
+        timeout-minutes: 10
+        run: (cd third_party/go-webview2 && go test -timeout=8m ./pkg/edge)
+
       # Installer packaging is packaging validation, not a code gate: run it
       # on pushes to main-v2 (the release pipeline builds installers again
       # anyway), but let pull requests stop after the test step.
@@ -489,9 +690,33 @@ jobs:
           go-version-file: go.mod
           cache: true
 
+      - if: github.event_name != 'pull_request' || needs.changes.outputs.desktop != 'false'
+        uses: pnpm/[email protected]
+        with:
+          version: 10
+          run_install: false
+
+      - if: github.event_name != 'pull_request' || needs.changes.outputs.desktop != 'false'
+        uses: actions/setup-node@v7
+        with:
+          node-version: "24"
+          cache: pnpm
+          cache-dependency-path: desktop/frontend/pnpm-lock.yaml
+
+      - name: required native motion contracts
+        if: github.event_name != 'pull_request' || needs.changes.outputs.desktop != 'false'
+        run: |
+          pnpm --dir desktop/frontend install --frozen-lockfile
+          pnpm --dir desktop/frontend test:motion
+
       - name: repo standards
         run: go run ./tools/repolint
 
+      - name: wails version pin
+        run: |
+          bash scripts/check-wails-pin.sh
+          bash scripts/check-wails-pin.test.sh
+
       # `make lint-install` reads the same file, so a local run and this job
       # cannot drift onto different linter versions.
       - id: golangci
@@ -512,9 +737,9 @@ jobs:
           set -euo pipefail
           command -v golangci-lint
           for target in "darwin ." "windows ." "windows desktop"; do
-            set -- $target
-            echo "::group::golangci-lint GOOS=$1 ($2)"
-            (cd "$2" && GOOS="$1" golangci-lint run --timeout=5m ./...)
+            read -r target_os target_dir <<< "$target"
+            echo "::group::golangci-lint GOOS=$target_os ($target_dir)"
+            (cd "$target_dir" && GOOS="$target_os" golangci-lint run --timeout=5m ./...)
             echo "::endgroup::"
           done
 
@@ -529,7 +754,9 @@ jobs:
             .github/workflows/release-npm.yml \
             .github/workflows/release-desktop.yml \
             .github/workflows/release-verify-issues.yml \
-            .github/workflows/docs-impact.yml
+            .github/workflows/docs-impact.yml \
+            .github/workflows/transcript-native-smoke.yml \
+            .github/workflows/ci.yml
           bash scripts/release-workflows.test.sh
           node scripts/check-single-release-public-contract.mjs
 

.github/workflows/deploy-crash-worker.yml

@@ -7,6 +7,22 @@ on:
       - 'workers/crash-report/**'
       - '.github/workflows/deploy-crash-worker.yml'
   workflow_dispatch:
+    inputs:
+      firebase_data_action:
+        description: Firebase crash history operation (migration actions do not deploy the Worker)
+        required: true
+        default: none
+        type: choice
+        options:
+          - none
+          - dry-run
+          - apply
+          - verify-only
+      confirmation:
+        description: Enter APPLY_FIREBASE_CRASH_DATA when selecting apply
+        required: false
+        default: ''
+        type: string
 
 permissions:
   contents: read
@@ -17,6 +33,7 @@ concurrency:
 
 jobs:
   deploy:
+    if: github.event_name == 'push' || inputs.firebase_data_action == 'none'
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v7
@@ -25,14 +42,44 @@ jobs:
           node-version: '22'
           cache: npm
           cache-dependency-path: workers/crash-report/package-lock.json
+      - name: Validate
+        working-directory: workers/crash-report
+        run: |
+          npm ci
+          npm run typecheck
+          npm test
+      - name: Apply and verify diagnostics v2 D1 migration
+        working-directory: workers/crash-report
+        env:
+          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+        run: npm run migrate:diagnostics-v2
+      - name: Apply and verify Firebase crash D1 migration
+        working-directory: workers/crash-report
+        env:
+          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+        run: npm run migrate:firebase-crash
+      - name: Sync Firebase crash secrets
+        working-directory: workers/crash-report
+        env:
+          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+          FIREBASE_DATABASE_URL: ${{ secrets.FIREBASE_DATABASE_URL }}
+          FIREBASE_CLIENT_EMAIL: ${{ secrets.FIREBASE_CLIENT_EMAIL }}
+          FIREBASE_PRIVATE_KEY: ${{ secrets.FIREBASE_PRIVATE_KEY }}
+        run: |
+          configured=0
+          [ -n "$FIREBASE_DATABASE_URL" ] && configured=$((configured + 1))
+          [ -n "$FIREBASE_CLIENT_EMAIL" ] && configured=$((configured + 1))
+          [ -n "$FIREBASE_PRIVATE_KEY" ] && configured=$((configured + 1))
+          if [ "$configured" -ne 0 ] && [ "$configured" -ne 3 ]; then
+            echo "Firebase crash secrets must be either all configured or all absent."
+            exit 1
+          fi
+          node -e 'process.stdout.write(JSON.stringify({FIREBASE_DATABASE_URL:process.env.FIREBASE_DATABASE_URL||null,FIREBASE_CLIENT_EMAIL:process.env.FIREBASE_CLIENT_EMAIL||null,FIREBASE_PRIVATE_KEY:process.env.FIREBASE_PRIVATE_KEY||null}))' | npx wrangler secret bulk
       - name: Deploy
         working-directory: workers/crash-report
         env:
           CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
         run: |
-          npm ci
-          npm run typecheck
-          npm test
           npx wrangler deploy
       # Mirrors the ALERT_WEBHOOK repo secret into the worker so the ingest
       # sentinel can push alerts (see runIngestSentinel). Managed here so
@@ -50,3 +97,67 @@ jobs:
             exit 0
           fi
           printf '%s' "$ALERT_WEBHOOK" | npx wrangler secret put ALERT_WEBHOOK
+
+  migrate-firebase-data:
+    if: github.event_name == 'workflow_dispatch' && inputs.firebase_data_action != 'none'
+    runs-on: ubuntu-latest
+    environment: canary
+    steps:
+      - uses: actions/checkout@v7
+      - name: Require the protected production branch
+        run: |
+          if [ "$GITHUB_REF" != "refs/heads/main-v2" ]; then
+            echo "Firebase crash data migration must run from main-v2."
+            exit 1
+          fi
+      - uses: actions/setup-node@v7
+        with:
+          node-version: '22'
+          cache: npm
+          cache-dependency-path: workers/crash-report/package-lock.json
+      - name: Validate
+        working-directory: workers/crash-report
+        run: |
+          npm ci
+          npm run typecheck
+          npm test
+      - name: Run Firebase crash history operation
+        working-directory: workers/crash-report
+        env:
+          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+          FIREBASE_DATABASE_URL: ${{ secrets.FIREBASE_DATABASE_URL }}
+          FIREBASE_CLIENT_EMAIL: ${{ secrets.FIREBASE_CLIENT_EMAIL }}
+          FIREBASE_PRIVATE_KEY: ${{ secrets.FIREBASE_PRIVATE_KEY }}
+          FIREBASE_DATA_ACTION: ${{ inputs.firebase_data_action }}
+          FIREBASE_DATA_CONFIRMATION: ${{ inputs.confirmation }}
+        run: |
+          configured=0
+          [ -n "$CLOUDFLARE_API_TOKEN" ] && configured=$((configured + 1))
+          [ -n "$FIREBASE_DATABASE_URL" ] && configured=$((configured + 1))
+          [ -n "$FIREBASE_CLIENT_EMAIL" ] && configured=$((configured + 1))
+          [ -n "$FIREBASE_PRIVATE_KEY" ] && configured=$((configured + 1))
+          if [ "$configured" -ne 4 ]; then
+            echo "Cloudflare and Firebase migration secrets must all be configured."
+            exit 1
+          fi
+
+          case "$FIREBASE_DATA_ACTION" in
+            dry-run)
+              npm run migrate:firebase-data
+              ;;
+            apply)
+              if [ "$FIREBASE_DATA_CONFIRMATION" != "APPLY_FIREBASE_CRASH_DATA" ]; then
+                echo "Apply requires the exact confirmation APPLY_FIREBASE_CRASH_DATA."
+                exit 1
+              fi
+              npm run migrate:firebase-data -- --apply
+              npm run migrate:firebase-data -- --verify-only
+              ;;
+            verify-only)
+              npm run migrate:firebase-data -- --verify-only
+              ;;
+            *)
+              echo "Unsupported Firebase crash data action."
+              exit 1
+              ;;
+          esac

.github/workflows/issue-version-label.yml

@@ -2,7 +2,7 @@ name: Label issue version
 
 # Issue forms can't let a reporter set a label directly (that needs triage rights),
 # so the bug/feature forms carry a "Version line" dropdown and this workflow reads
-# the submitted value and applies the matching v1/v2 label on their behalf.
+# the submitted value and applies the matching v2/v3 label on their behalf.
 on:
   issues:
     types: [opened, edited]
@@ -25,7 +25,8 @@ jobs:
             const sectionOf = (name) =>
               body.split(/^###\s+/m).find((s) => new RegExp(`^${name}`, 'i').test(s)) || '';
 
-            const m = sectionOf('Version line').match(/\bv([12])\b/i);
+            const lines = ['v1', 'v2', 'v3'];
+            const m = sectionOf('Version line').match(/\bv([23])\b/i);
             if (!m) {
               core.info('No version line found; nothing to label.');
               return;
@@ -33,31 +34,35 @@ jobs:
             let choice = 'v' + m[1];
 
             // The dropdown is a choice, and v2 sits first, so it gets picked by
-            // reporters who are actually on 0.x. `Exact version` is pasted from
-            // `reasonix --version`, so when it parses it is the better evidence:
-            // 0.x is the TypeScript line, 1.x the Go rewrite. Anything that does
-            // not parse (a commit sha, "main-v2") leaves the dropdown to decide.
+            // reporters who are actually on the other line. `Exact version` is
+            // pasted from `reasonix --version`, so when it parses it is the
+            // better evidence: 1.x Go rewrite (v2), 2.x Studio (v3, studio
+            // branch). 0.x is no longer a filing line. Anything that does not
+            // parse (a commit sha, "main-v2", "studio") leaves the dropdown
+            // to decide.
             const exact = sectionOf('Exact version').match(/\b(\d+)\.(\d+)\.(\d+)/);
             if (exact) {
-              const fromVersion = Number(exact[1]) === 0 ? 'v1' : 'v2';
-              if (fromVersion !== choice) {
+              const major = Number(exact[1]);
+              const fromVersion = major === 1 ? 'v2' : major === 2 ? 'v3' : null;
+              if (fromVersion && fromVersion !== choice) {
                 core.info(`Version line says ${choice} but ${exact[0]} says ${fromVersion}; trusting the version.`);
                 choice = fromVersion;
               }
             }
-            const other = choice === 'v2' ? 'v1' : 'v2';
             await github.rest.issues.addLabels({
               ...context.repo,
               issue_number: context.issue.number,
               labels: [choice],
             });
-            // Keep v1/v2 mutually exclusive in case an edit flipped the choice.
-            try {
-              await github.rest.issues.removeLabel({
-                ...context.repo,
-                issue_number: context.issue.number,
-                name: other,
-              });
-            } catch (e) {
-              core.info(`No ${other} label to remove.`);
+            // Keep version-line labels mutually exclusive if an edit flipped the choice.
+            for (const other of lines.filter((l) => l !== choice)) {
+              try {
+                await github.rest.issues.removeLabel({
+                  ...context.repo,
+                  issue_number: context.issue.number,
+                  name: other,
+                });
+              } catch (e) {
+                core.info(`No ${other} label to remove.`);
+              }
             }

.github/workflows/pr-version-label.yml

@@ -2,7 +2,7 @@ name: Label PR version
 
 # Contributors (especially from forks) can't set labels themselves — that needs
 # triage rights. A PR's version line is fully determined by its base branch, so
-# this reads base.ref and applies v1/v2 on their behalf. pull_request_target runs
+# this reads base.ref and applies v1/v2/v3 on their behalf. pull_request_target runs
 # in the base repo's context so it has write access even for fork PRs; it only
 # reads trusted metadata (the base ref) and never checks out or runs PR code.
 on:
@@ -23,27 +23,28 @@ jobs:
       - uses: actions/github-script@v9
         with:
           script: |
+            const lineByBase = { v1: 'v1', 'main-v2': 'v2', studio: 'v3' };
+            const lines = Object.values(lineByBase);
             const base = context.payload.pull_request.base.ref;
-            const label = base === 'v1' ? 'v1'
-                        : base === 'main-v2' ? 'v2'
-                        : null;
+            const label = lineByBase[base] || null;
             if (!label) {
               core.info(`Base branch '${base}' isn't a release line; skipping.`);
               return;
             }
-            const other = label === 'v2' ? 'v1' : 'v2';
             await github.rest.issues.addLabels({
               ...context.repo,
               issue_number: context.payload.pull_request.number,
               labels: [label],
             });
-            // Drop the other line's label if the base was changed after opening.
-            try {
-              await github.rest.issues.removeLabel({
-                ...context.repo,
-                issue_number: context.payload.pull_request.number,
-                name: other,
-              });
-            } catch (e) {
-              core.info(`No ${other} label to remove.`);
+            // Drop other line labels if the base was changed after opening.
+            for (const other of lines.filter((l) => l !== label)) {
+              try {
+                await github.rest.issues.removeLabel({
+                  ...context.repo,
+                  issue_number: context.payload.pull_request.number,
+                  name: other,
+                });
+              } catch (e) {
+                core.info(`No ${other} label to remove.`);
+              }
             }

.github/workflows/release-desktop.yml

@@ -310,7 +310,7 @@ jobs:
 
       - uses: actions/setup-node@v7
         with:
-          node-version: "22"
+          node-version: "24"
       - uses: pnpm/[email protected]
         with:
           version: 10
@@ -371,7 +371,7 @@ jobs:
           rm -f "$RUNNER_TEMP/cert.p12"
 
       - name: Install Wails CLI
-        run: go install github.com/wailsapp/wails/v2/cmd/wails@v2.12.0
+        run: go install "github.com/wailsapp/wails/v2/cmd/wails@$(cat "$GITHUB_WORKSPACE/.wails-version")"
 
       # Official Windows releases must fail closed. Forks can still exercise
       # unsigned packaging without repository secrets, but esengine releases
@@ -395,6 +395,32 @@ jobs:
           APPLE_API_ISSUER_ID: ${{ secrets.APPLE_API_ISSUER_ID }}
         run: scripts/desktop-build.sh "${{ matrix.platform }}" "${{ needs.resolve.outputs.version }}" "${{ needs.resolve.outputs.channel }}"
 
+      # Candidate code is immutable, but release validation belongs to the
+      # protected workflow control plane. Reuse this sparse checkout later for
+      # Authenticode verification rather than trusting a candidate-owned test.
+      - name: Checkout protected release verifier
+        if: runner.os == 'Windows' && (matrix.platform == 'windows/amd64' || env.HAS_SIGNPATH == 'true')
+        uses: actions/checkout@v7
+        with:
+          ref: ${{ github.workflow_sha }}
+          path: release-control
+          sparse-checkout: |
+            scripts/test-webview2-native-smoke.ps1
+            scripts/verify-windows-authenticode.ps1
+          sparse-checkout-cone-mode: false
+          persist-credentials: false
+
+      # Exercise the exact production Wails binary built for Stable on
+      # Microsoft's real WebView2 runtime before signing or publication.
+      - name: Smoke-test Wails/WebView2 native startup
+        if: matrix.platform == 'windows/amd64'
+        shell: pwsh
+        run: |
+          ./release-control/scripts/test-webview2-native-smoke.ps1 `
+            -ExecutablePath "desktop/build/bin/reasonix-desktop.exe" `
+            -TimeoutSeconds 60 `
+            -HealthySeconds 5
+
       # Sign every executable that users actually run before rebuilding the
       # portable archive and NSIS installer. Signing only the finished NSIS
       # container leaves reasonix-desktop.exe and its sidecars unsigned after
@@ -504,20 +530,6 @@ jobs:
         if: runner.os == 'Windows' && env.HAS_SIGNPATH == 'true'
         run: cp signed-installer/*installer*.exe dist/
 
-      # Recovery builds intentionally check out the immutable product SHA,
-      # which can predate a verifier repair. Fetch only the verifier from the
-      # protected workflow commit so recovery can validate old immutable
-      # artifacts without rebuilding them from a moving product branch.
-      - name: Checkout protected release verifier
-        if: runner.os == 'Windows' && env.HAS_SIGNPATH == 'true'
-        uses: actions/checkout@v7
-        with:
-          ref: ${{ github.sha }}
-          path: release-control
-          sparse-checkout: scripts/verify-windows-authenticode.ps1
-          sparse-checkout-cone-mode: false
-          persist-credentials: false
-
       - name: Verify Windows Authenticode release contract
         if: runner.os == 'Windows' && env.HAS_SIGNPATH == 'true'
         shell: pwsh
@@ -594,7 +606,7 @@ jobs:
 
       - uses: actions/setup-node@v7
         with:
-          node-version: "22"
+          node-version: "24"
 
       - uses: actions/download-artifact@v8
         with:

.github/workflows/release-notes.yml

@@ -4,9 +4,12 @@ on:
   pull_request:
     paths:
       - "release-notes/**"
+      - "scripts/generate-release-notes.mjs"
       - "scripts/release-notes*.mjs"
       - "site/src/pages/changelog/**"
       - "site/src/components/ChangelogPage.astro"
+      - "site/src/data/releases.ts"
+      - "site/src/styles/changelog.css"
       - "desktop/frontend/src/App.tsx"
       - "desktop/frontend/src/components/SettingsPanel.tsx"
       - "desktop/frontend/src/components/UpdateBanner.tsx"

.github/workflows/transcript-native-smoke.yml

@@ -0,0 +1,72 @@
+name: Transcript Native Smoke
+
+on:
+  pull_request:
+    branches: [main-v2]
+    paths:
+      - ".github/workflows/transcript-native-smoke.yml"
+      - "desktop/cmd/transcript-native-smoke/**"
+      - "desktop/frontend/src/components/Transcript*.tsx"
+      - "desktop/frontend/src/lib/transcript*.ts"
+      - "desktop/frontend/src/lib/useTranscript*.ts"
+      - "desktop/frontend/src/styles.css"
+      - "desktop/transcript_native_smoke_contract.js"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: transcript-native-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  macos-wkwebview:
+    runs-on: macos-latest
+    timeout-minutes: 15
+    defaults:
+      run:
+        working-directory: desktop
+    steps:
+      - uses: actions/checkout@v7
+
+      - uses: actions/setup-go@v7
+        with:
+          go-version-file: desktop/go.mod
+          cache: true
+          cache-dependency-path: desktop/go.sum
+
+      - uses: pnpm/[email protected]
+        with:
+          version: 10
+          run_install: false
+
+      - uses: actions/setup-node@v7
+        with:
+          node-version: "24"
+          cache: pnpm
+          cache-dependency-path: desktop/frontend/pnpm-lock.yaml
+
+      - name: Build focused transcript fixture
+        run: |
+          echo "$(go env GOPATH)/bin" >> "$GITHUB_PATH"
+          go install "github.com/wailsapp/wails/v2/cmd/wails@$(cat "$GITHUB_WORKSPACE/.wails-version")"
+          wails generate module
+          pnpm --dir frontend install --frozen-lockfile
+          pnpm --dir frontend exec vite build
+
+      - name: Test sustained WKWebView transcript reading
+        timeout-minutes: 5
+        env:
+          REASONIX_NATIVE_SMOKE_ISOLATED_CI: "1"
+        run: |
+          pnpm --dir frontend exec vite preview --host 127.0.0.1 --port 4173 --strictPort >"$RUNNER_TEMP/reasonix-transcript-preview.log" 2>&1 &
+          preview_pid=$!
+          trap 'kill "$preview_pid" 2>/dev/null || true' EXIT
+          for _ in $(seq 1 100); do
+            curl -fsS http://127.0.0.1:4173/ >/dev/null && break
+            sleep 0.1
+          done
+          go run -tags reasonix_transcript_smoke ./cmd/transcript-native-smoke \
+            -url 'http://127.0.0.1:4173/?mock=bench&bench=1' \
+            -script transcript_native_smoke_contract.js

.gitignore

@@ -5,6 +5,8 @@
 /npm/.stage/
 /reasonix
 /reasonix.exe
+/e2ebench
+/e2ebench.exe
 
 # Website (Astro) build output
 /site/dist/
@@ -34,6 +36,8 @@ mem.prof
 .env
 .env.local
 *.local
+**/.firebase-crash-migration-state.json
+**/.firebase-crash-migration-state.json.tmp-*
 /reasonix.toml
 /desktop/.env
 /desktop/reasonix.toml

.golangci.yml

@@ -58,6 +58,14 @@ linters:
         linters:
           - staticcheck
         text: SA5011
+      # SA4023 is trivially true on GOOS=windows: dialAgent's Windows stub
+      # (agent_windows.go) always returns a non-nil error until named-pipe
+      # transport lands. Suppress only this call site; the comparison stays
+      # meaningful on Unix where dialAgent can succeed.
+      - path: internal/remote/auth\.go
+        linters:
+          - staticcheck
+        text: SA4023
 
 issues:
   max-issues-per-linter: 0

.wails-version

@@ -0,0 +1 @@
+v2.13.0

CHANGELOG.md

@@ -6,10 +6,143 @@ branch.
 
 ## Unreleased
 
+### Added
+
+- **MCP 2026-07-28 protocol:** multi-round-trip form/URL elicitation across
+  Desktop, CLI TUI, and serve; headless entries stay on the core surface and
+  cancel unanswered requests instead of guessing.
+- **MCP Apps 2026-01-26 (Desktop):** inline app surfaces in tool cards behind
+  a per-server double-iframe sandbox, app-tool visibility metadata, bounded
+  aggregate local presentations, tab-bound AppBridge routing and teardown,
+  immutable digest-bound resource snapshots, and confirmed external links;
+  local rich results, instance-gated app tool calls, and the four-layer
+  capability matrix in MCP status.
+- **Profile-scoped MCP schema caches:** capability-declaring hosts keep their
+  own `v3` cache files so catalogs negotiated under different client
+  capabilities never cross-read.
+
+### Changed
+
+- **Fact-driven execution:** Ordinary requests always enter the executor.
+  There is no automatic simple / light / full task mode and no per-turn
+  `TaskPolicy` classification. The planner runs only for an explicit Plan,
+  an approval boundary, or Goal start. The host builds verification
+  obligations from concrete tool effects and receipts. Plan, Goal,
+  permission, and sandbox stay independent. Tool schemas and the executor
+  system prefix stay byte-stable. Historical `<execution-policy>` tags remain
+  readable on old sessions and are stripped from new provider context.
+  Old `--preset`/`--profile` compatibility no-ops are unchanged.
+
+- **Remote connect wizard host picker:** Step 1's host field now opens the
+  saved SSH connections through an explicit chevron dropdown on the input's
+  right edge instead of the old focus-triggered popup. The dropdown lists
+  every saved connection unfiltered, appends non-standard ports to each row,
+  leads with a "saved SSH connections" caption, and closes on pick, arrow
+  toggle, Escape (before the Escape that exits the wizard), or an outside
+  pointer press. The arrow is hidden while no hosts are saved and disabled
+  while a connection is busy.
+
 ### Fixed
 
+- **serve Host-header allowlist:** `reasonix serve` now rejects requests whose
+  `Host` is neither loopback nor the actual listen address (HTTP 421), closing
+  the DNS-rebinding bypass of the JSON content-type CSRF guard — a rebind page
+  becomes same-origin with the loopback listener and could previously drive
+  `/bypass`, `/submit`, and read `/history`. `behind_proxy` deployments and
+  wildcard/non-loopback binds are exempt. The non-loopback plaintext-HTTP
+  startup warning now also fires — loudest — for the unauthenticated `auth =
+  none` case that used to stay silent.
+
+- **Preview read confinement:** `write_file` / `edit_file` / `multi_edit`
+  previews now apply the same `confinePreview` boundary as `delete_range` /
+  `delete_symbol`. A model-supplied absolute path outside the workspace roots
+  previously read the file (rendering its contents into the approval card and
+  session log) even though Execute would refuse the write.
+
+- **Clean-filter hardening on internal diffs:** gitcmd diff invocations now
+  neutralize every `filter.<driver>` defined in the repository's local
+  `.git/config` (`clean=` emptied, `required` forced off), so viewing a changed
+  file's diff can no longer execute a repository-configured clean filter via
+  `.gitattributes`. Emptied filters are identity pass-throughs: the diff still
+  renders the real working-tree change.
+
+- **install_source proxy SSRF parity:** the install_source SSRF dial guard now
+  also validates the request destination (IP literals) at the RoundTripper
+  boundary, so a configured HTTP/HTTPS proxy can no longer forward a blocked
+  target (cloud metadata, RFC1918, link-local, CGNAT) that the dial-time check
+  never sees — matching web_fetch's proxy-path behavior.
+
+- **awk approval classification:** the bash indirect-execution classifier now
+  treats `awk`/`gawk`/`mawk`/`nawk` with an inline program (anything not read
+  via `-f`/`--file`) like `python -c`: it always requires human approval and
+  can never be covered by a remembered reusable prefix rule. `awk
+  'BEGIN{system("…")}'` previously fell through to the reusable class.
+
+- **cargo check/doc read-only correction:** the legacy read-only command table
+  no longer lists `cargo check` / `cargo doc` as permission readers — cargo
+  executes the crate's `build.rs` for both. The effect classifier already
+  billed them as code-executing writers; the stale table entry (and its test)
+  now agree. Only `cargo search` remains read-only.
+
+- **Compact MCP discovery:** `use_capability(action=list)` now returns one
+  compact summary per configured MCP server instead of expanding every cached
+  tool description, including tools from disabled servers. Inspecting one
+  enabled `mcp-server:<name>` still returns its live or cached directory
+  without starting it, while direct known-ID calls, routing, authorization,
+  and the fixed provider-visible tool schema remain unchanged.
+
+- **Project MCP session reliability:** The MCP client now uses the official Go
+  SDK for stdio, legacy SSE, and Streamable HTTP while retaining Reasonix's
+  existing configuration, OAuth, process isolation, and schema-cache contracts.
+  Streamable HTTP opens its long-lived GET/SSE listener immediately after
+  initialization, so JetBrains project-level `.mcp.json` servers no longer lose
+  their pending session before the first tool call. Lost sessions converge on
+  one bounded rebuild and one replay, read-only surfaces consume every cursor
+  page, prompts/resources share the tool session, and shutdown terminates HTTP
+  sessions and local processes. MCP calls also accept a single JSON-object
+  string in `use_capability.arguments`, while rejecting arrays, scalars, invalid
+  JSON, and nested encoded strings. `/mcp` and Desktop expose redacted protocol,
+  listening, reconnect, and error-category diagnostics without session IDs.
+
+- **v1.24.2 session snapshot & recovery root fix:** Keep PR #7982's WAL/CAS/lease
+  safety foundation, but replace process-level "I hold a lease" ownership with a
+  generation-bound `SessionWriteAuthority`. Same-revision tool-preview/load
+  reshapes no longer false-diverge; recovery files are bounded to one path per
+  writer/lineage; empty checkpoints heal from their own WAL; projection lineage
+  rebinds across upgrade/model switch and inherits across recovery forks without
+  changing provider-visible prompt bytes. Catalog upgrades to disposable
+  `session-catalog/v3.sqlite` with recovery lineage roles
+  (`normal|covered_copy|adopted|diverged`); covered idle copies move to the
+  recoverable `.trash` using a 15-minute idle threshold applied on two early
+  sweeps (at startup and ~20 minutes later), then a 24-hour threshold on the
+  6-hour background ticker; independent diverged branches stay and are listed
+  for user choice. v1/v2 catalogs are
+  left byte-unchanged for coexistence/downgrade.
+  **v1.24.1** only hid/reclaimed already-created covered copies and fixed Windows
+  flash-window startup; **v1.24.2** stops the misclassification source and repairs
+  existing user directories without rewriting authoritative JSONL/WAL/sidecar data.
+
+- Goal now runs continuously by default: the former 16-round per-Run boundary,
+  10/20/40 cross-Run quotas, default wall-clock budget, and numeric
+  no-progress/Todo-stall pauses no longer stop valid work. Progress guards still
+  detect repeated host outcomes and zero-evidence work, but redirect the model
+  to re-plan instead of producing `goal_run_budget` or `goal_stuck`. Explicit
+  `[agent].goal_token_budget`, `--max-steps`, positive time/cost budgets, manual
+  pause/stop, genuine user/external blockers, and evaluator fail-closed behavior
+  remain available. The Goal token budget defaults to `0` (off); resuming its
+  `budget_spend` pause grants a fresh slice without clearing cumulative usage.
+  Goal status reports turns, provider requests, tokens, the optional configured
+  token threshold, and cumulative active work time. Bot `max_steps` also
+  defaults to `0` (continuous), while positive user configuration is enforced.
+
+- Removed numeric Goal pauses in existing sidecars automatically normalize to
+  `running` without sending a model request. Active Goal sidecars write
+  `turnsLimit: -1` as a downgrade-safe unlimited sentinel while public runtime
+  APIs retain deprecated limit fields as `0`. The migration preserves unknown
+  fields, todos, checkpoints, usage, evidence, and historical metadata.
+
 - Goal is now the sole long-task runtime. Historical AutoResearch sidecars
-  migrate transactionally into research-budget Goals. Invalid archives block
+  migrate transactionally into Goals with research compatibility metadata. Invalid archives block
   fail closed and remain read-only, retaining the task id and compatibility mode
   for a restart or `/goal resume` retry; successful Goal-only sidecars omit the
   old task id and write an explicit downgrade fence so previous readers cannot

CONTRIBUTING.md

@@ -8,6 +8,8 @@ everything you need to get started.
 - **Go 1.25+** — the project targets the latest stable Go release
 - **Git** — for version control
 - **Node.js** (optional) — only if you work on the desktop app (`desktop/`)
+- **Wails CLI** (desktop only) — run `make wails-install` so the CLI matches
+  `desktop/go.mod`
 
 ## Getting started
 
@@ -124,6 +126,10 @@ go test ./internal/agent/ -v            # verbose, one package
 go test ./internal/tool/builtin/ -run TestGrep  # one test
 ```
 
+Desktop transcript scroll changes follow the discipline in
+`desktop/AGENTS.md` (single scroll writer, deterministic race tests via
+`pnpm test:transcript` in `desktop/frontend/`).
+
 ### Code style
 
 - `gofmt` is enforced by CI — format before committing

Makefile

@@ -8,8 +8,9 @@ LDFLAGS := -s -w \
 GOEXE := $(shell go env GOEXE)
 # One pin for the Makefile and the CI lint job; see .github/workflows/ci.yml.
 GOLANGCI_VERSION := $(shell cat .golangci-version)
+WAILS_VERSION := $(shell tr -d '[:space:]' < .wails-version)
 
-.PHONY: build vet fmt lint lint-go lint-install lint-cross lint-update test desktop-test desktop-test-short desktop-test-times sdk-test sdk-test-race hooks cross clean
+.PHONY: build vet fmt lint lint-go lint-install lint-cross lint-update wails-install test desktop-test desktop-test-short desktop-test-times sdk-test sdk-test-race hooks cross clean
 
 build:
 	CGO_ENABLED=0 go build -ldflags "$(LDFLAGS)" -o bin/reasonix$(GOEXE) ./cmd/reasonix
@@ -26,6 +27,8 @@ fmt:
 # particular never surface in `go vet`.
 lint: lint-go
 	go run ./tools/repolint
+	bash scripts/check-wails-pin.sh
+	bash scripts/check-wails-pin.test.sh
 
 lint-go:
 	@command -v golangci-lint >/dev/null || { echo "golangci-lint not installed; run: make lint-install"; exit 1; }
@@ -41,6 +44,10 @@ lint-install:
 lint-update:
 	go run ./tools/repolint -update
 
+wails-install:
+	bash scripts/check-wails-pin.sh
+	go install "github.com/wailsapp/wails/v2/cmd/wails@$(WAILS_VERSION)"
+
 # Linting one GOOS leaves every //go:build windows and darwin file unchecked.
 lint-cross:
 	@for t in "linux ." "darwin ." "windows ." "linux desktop" "windows desktop"; do \

README.md

@@ -115,13 +115,39 @@ approvals, model selection, and workspace sessions.
 
 ### Path D: Build from source
 
+Clone the repository first:
+
 ```sh
 git clone https://github.com/esengine/DeepSeek-Reasonix.git
 cd DeepSeek-Reasonix
+```
+
+#### CLI
+
+The CLI build requires **Go 1.25+**. The module pins a `toolchain` directive;
+keep `GOTOOLCHAIN=auto` so Go downloads the pinned toolchain, or install it.
+
+```sh
 make build      # -> bin/reasonix(.exe)
 make cross      # -> dist/ (darwin|linux|windows × amd64|arm64)
 ```
 
+#### Desktop
+
+The desktop build additionally requires:
+
+- **Node 24+ and pnpm 10** (`npm install -g pnpm@10`) for the frontend
+- **Wails CLI** matching the shared `.wails-version` pin
+
+```sh
+make wails-install
+cd desktop
+wails build
+```
+
+See the [desktop build guide](desktop/README.md#prerequisites) for platform
+webview dependencies and Linux build tags.
+
 ## Quick start
 
 ### CLI / TUI

README.zh-CN.md

@@ -106,13 +106,39 @@ Windows 安装器通过 [SignPath.io](https://signpath.io/) 完成代码签名
 
 ### 路径 D：从源码构建
 
+先克隆仓库：
+
 ```sh
 git clone https://github.com/esengine/DeepSeek-Reasonix.git
 cd DeepSeek-Reasonix
+```
+
+#### CLI
+
+CLI 构建需要 **Go 1.25+**。模块固定了 `toolchain` 指令；
+保持 `GOTOOLCHAIN=auto` 让 Go 自动下载固定的工具链，或自行安装。
+
+```sh
 make build      # -> bin/reasonix(.exe)
 make cross      # -> dist/（darwin|linux|windows × amd64|arm64）
 ```
 
+#### 桌面端
+
+桌面端构建额外需要：
+
+- **Node 24+ 和 pnpm 10**（`npm install -g pnpm@10`）用于前端
+- **Wails CLI**，与共享的 `.wails-version` 固定版本一致
+
+```sh
+make wails-install
+cd desktop
+wails build
+```
+
+平台相关的 WebView 依赖和 Linux 构建标签见
+[桌面端构建指南](desktop/README.md#prerequisites)。
+
 ## 快速开始
 
 ### CLI / TUI

REASONIX.md

@@ -15,6 +15,11 @@ agent. It is the Reasonix analog of Claude Code's CLAUDE.md.
   the frontends `cli`, `serve`, `acp`, `bot`, `botruntime`, `boot` and the hosts
   `cmd/`, `desktop/` may import `control`; nothing below a frontend may import
   one. The declared sets live in `tools/repolint/layers.go`.
+- Subagent delegation keeps five concepts apart: a profile says how a worker
+  thinks, `TaskSpec` what this call wants, `CapabilityGrant` what it may touch,
+  `ContextRequest` what it starts from, `SchedulerPolicy` when it runs. Put a
+  field in whichever member decides its value — profiles carry ceilings, never
+  per-call values. `internal/agent/profile_boundary_test.go` enforces it.
 - Cache-first: the system-prompt prefix (base prompt + tools + memory) must stay
   byte-stable across turns so DeepSeek's automatic prefix cache stays warm. Never
   mutate it mid-session — ride the turn tail instead (see `control.Compose`).
@@ -22,6 +27,12 @@ agent. It is the Reasonix analog of Claude Code's CLAUDE.md.
   (`internal/boot/effect_test.go` pattern): assert what actually reaches the
   provider request, frontend sink, or trajectory through the real `boot.Build`
   assembly. Component correctness is not system effectiveness.
+- A mutex- or atomic-guarded struct is ratcheted on its **scalar** field count
+  (`struct-state`), not its total: independent flags multiply into states no
+  type records as legal. Fixing a boundary case by adding one more `bool` is
+  the move this blocks — group by lifetime into a named sub-state instead
+  (`agent.perTurnState` is the pattern), which costs one field and removes the
+  whole product.
 
 ## Comments
 
@@ -29,7 +40,7 @@ Default is none — the code is the truth. Write one only when the **why** is
 non-obvious: a hidden constraint, a workaround anchored to something verifiable,
 an invariant the type system cannot express, or an external-protocol quirk.
 
-- Declaration doc: ≤5 lines. Package comment: ≤8 lines, or ≤40 in a `doc.go`.
+- Declaration doc: ≤15 lines. Package comment: ≤8 lines, or ≤40 in a `doc.go`.
 - Every other comment: ≤3 lines. Struct-field and trailing `//`: 1 line.
 - Never: restatements of the code, phase/stage narrative, incident or
   conversation history, section banners, commented-out code, `@param` lists.

benchmarks/README.md

@@ -106,6 +106,61 @@ Each task under `e2e/tasks/<id>/` contains:
 | `verify.sh` | The grader: exits 0 iff the agent's artifacts are correct. |
 | `workdir/` | Optional seed workspace, copied into the temp run dir before the agent starts. |
 
+## Anchor resistance
+
+Multi-agent systems isolate conversations. They rarely isolate conclusions: a
+sub-agent asked to "independently check this" usually arrives already holding
+its parent's answer. Before adding an interface to prevent that, measure
+whether it costs anything here — a handed-down conclusion that the agent
+routinely overturns is not a problem worth building against.
+
+The `-anchor` arms make that measurable on the `failing-test-diagnosis` tasks,
+which have one knowable cause each. Each carries two authored hypotheses: the
+real cause (`seed_correct`) and a plausible one that is not (`seed_wrong`).
+The arm prefixes the prompt with its seed, so the agent meets the conclusion
+before it has read anything.
+
+```bash
+go run ./cmd/e2ebench -task diagnose-float-total,diagnose-floor-division,diagnose-missing-file,diagnose-tie-order,diagnose-utf8-bom,diagnose-version-sort -json blind.json
+go run ./cmd/e2ebench -anchor correct -task ...same... -json correct.json
+go run ./cmd/e2ebench -anchor wrong   -task ...same... -json wrong.json
+```
+
+Anchor resistance is the wrong arm's solve rate over the blind arm's on the
+same tasks. A wrong arm that collapses says a handed-down conclusion survives
+contact with the evidence, and that blind delegation is worth its cost; a wrong
+arm that barely moves says the opposite. Nothing here is a single composite
+"independence score" — the arms are reported separately because they answer
+different questions.
+
+Two limits are worth stating rather than discovering later. The seed goes to
+the top-level agent, so it prices agent-level anchoring; it reaches a
+sub-agent only if the parent delegates and repeats it, which the **evidence
+origin** line under Delegation is what measures. And the seeded arms score a
+smaller corpus than the blind one — every skipped task is named in the report,
+because a seeded arm quietly scoring fewer tasks is not the same experiment.
+
+### Evidence origin
+
+The Delegation section reports how much of what the children looked at they
+had to find themselves, and what the parent's own delegation text pointed at.
+Both come from host receipts and the parent-authored task text before host
+framing, never from anything an agent claims.
+
+Two kinds of pointing are counted apart, because they are not the same act:
+
+| | What it is | Blind delegation |
+| --- | --- | --- |
+| **scope hint** (`pkg/`) | Narrowing the search — the unavoidable cost of handing work off at all | expected, and recorded |
+| **named file** (`pkg/romeo.py`) | Saying where the answer is | the number that should be zero |
+
+Discovery is judged against named files only: a child sent to a directory
+still had to work out which file in it mattered, so a scope hint never erases
+its credit. Both stay absolute counts — a rate would hide how large the
+hand-over was — while the discovery share is a ratio of summed paths across
+children, not a mean of per-child rates, so a child that opened one file
+cannot outweigh one that swept forty.
+
 ## Neutral metering
 
 A harness comparison has an accounting problem before it has a measurement
@@ -146,9 +201,74 @@ metered this way precisely because it *does* self-report: if the proxy and
 `.run-metrics.json` disagree about the same run, one of them is wrong and no
 cross-harness number is ready to publish.
 
-`-faults` injects provider failures at fixed request indices through the same
-proxy, which is what LongRun needs: deterministic 429/500 at the same point of
-a run, replayable across harnesses.
+## Fault recovery
+
+`-faults` injects provider failures through the same proxy — deterministic, and
+replayable across harnesses. Two forms:
+
+- `3:429` — a targeted failure at an exact request.
+- `every:5:500` — a cadence. **A mixed-length suite needs this**: a task that
+  only ever makes four requests would never reach a fixed index and would join
+  the unfaulted group without anyone noticing.
+
+An absolute index wins over the cadence, so a targeted failure stays where it
+was asked for.
+
+```sh
+go run ./cmd/e2ebench -meter ~/.reasonix/config.toml -faults every:5:500 -trajectories t/
+```
+
+The readout separates two things that are easy to conflate:
+
+```text
+**Fault recovery** (31 runs failed on purpose, 47 injections): **retried** 94% (29) ·
+**still solved** 61% (19/31) · in-run control 78% (14/18 never hit a fault)
+```
+
+- **retried** — the meter saw another request after the failure. A harness that
+  dies on the first 429 never reaches this, and *was never really tested*.
+- **still solved** — the task landed anyway. A harness can retry forever and
+  still not finish; that is not recovery.
+- **in-run control** — with a cadence, short tasks never hit a fault, so the
+  same run carries its own unfaulted baseline. The cost of failure is measured
+  against the same suite and model rather than a separate arm run at another
+  time under other conditions.
+
+## Segmented runs
+
+A twelve-hour session is not interesting because it is twelve hours long. It is
+interesting because of the states it passes through: a session reloaded from
+disk, a prefix rebuilt, a compaction crossing a turn boundary, a user arriving
+mid-task with a new instruction. `-segments N` reaches those states directly
+instead of waiting hours for them.
+
+```sh
+go run ./cmd/e2ebench -segments 3 -steer "also handle empty input@2" -trajectories t/
+```
+
+Leg 1 starts the session with the task. Later legs resume it with `--continue`,
+which is unambiguous because each task already runs in its own home and
+therefore its own session directory. A resumed leg is deliberately **not** given
+the task again — its prompt is a bare continuation, because a leg that restates
+the work would hide exactly the degradation this is meant to expose. A `-steer`
+entry replaces one leg's continuation with a user turn.
+
+Two properties are load-bearing:
+
+- **The step budget is divided, never multiplied.** A segmented arm gets the
+  same `max_steps` as the control arm, split across legs with the remainder on
+  the last. Otherwise the arm would win by being allowed to work longer.
+- **Each leg writes its own metrics file.** They share a work dir, so a single
+  `.run-metrics.json` would leave the last leg's numbers standing in for the
+  whole run and the earlier legs' tokens would simply vanish. `Segments` in the
+  JSON records how many legs a run had.
+
+A leg that fails ends the run: resuming a session the child never finished
+writing would measure crash recovery, which is a different experiment.
+
+Only the last leg's trajectory digest is read, so time attribution and cognition
+lines describe that leg rather than the whole run. Merging per-leg trajectories
+is not done yet; `Segments` is what tells you the digest is partial.
 
 ## task.toml schema
 
@@ -162,6 +282,8 @@ decoder. The task ID is the directory name; tasks run in sorted ID order.
 | `max_steps` | int | yes | Agent tool-call cap; passed through as `--max-steps` to `reasonix run`. |
 | `no_solution` | bool | no | Ground truth: no reachable solution exists. The task leaves every accuracy denominator, its `verify.sh` grades the inverse contract, and it is scored on honesty instead. See [Completion Integrity](#completion-integrity). |
 | `timeout_sec` | int | no | Per-task wall-clock timeout in seconds; defaults to `240` when omitted or `0`. |
+| `seed_correct` | string | no | The task's real cause, phrased as a conclusion handed down before the run. Used by `-anchor correct`. See [Anchor resistance](#anchor-resistance). |
+| `seed_wrong` | string | no | A plausible cause that is **not** the real one. Used by `-anchor wrong`. Author both seeds or neither: a task seeded on one side only would be scored in one arm and skipped in the other. |
 
 Example (`tasks/fizzbuzz/task.toml`):
 
@@ -237,10 +359,13 @@ own outcome).
 | `-json` | *(none)* | Write the JSON report here (optional). |
 | `-trajectories` | *(none)* | Suite mode: write one `<task-id>.trajectory.jsonl` per task into this directory (the agent's full event stream with timestamps — see `reasonix run --trajectory`). The report gains a time-attribution line (tools vs. model) and each JSON result a `trajectory` digest. |
 | `-force-planner` | `false` | Suite mode: prefix each prompt with a plan-first directive so the two-model turn engages regardless of the planner gate. Use for the "with planner" arm of an A/B; results carry `plan_forced` so arms are only comparable with equal forcing. |
+| `-anchor` | `blind` | Suite mode: which hypothesis the agent holds before it looks at anything — `blind` (none, the control) \| `correct` \| `wrong`. The seeded arms prefix each prompt with the task's authored seed and **skip** tasks that have none, so an unseeded control run never lands in a seeded denominator. Results carry `anchor`. See [Anchor resistance](#anchor-resistance). |
 | `-cache` | `cold` | Suite mode: `cold` runs each task as a fresh session (the fair cross-agent comparison arm); `warm` primes the provider prefix cache with a one-step run in the same workdir first, measuring the long-lived-session steady state. Never mix arms in one report — compare them with `-mode compare cold.json warm.json`. |
 | `-budget` | `800000` | Abort once total tokens cross this (`0` = no cap). Remaining tasks are reported as skipped. |
 | `-meter` | *(off)* | Suite mode: route the benchmarked provider through the neutral measuring proxy, using this `config.toml` as the source. Spend is then counted at the request boundary instead of trusted from the harness. See [Neutral metering](#neutral-metering). |
-| `-faults` | *(none)* | Suite mode: inject provider failures at fixed request indices, e.g. `3:429,7:500`. Requires `-meter` — the proxy is the only place a fault can be injected. |
+| `-faults` | *(none)* | Suite mode: inject provider failures through the meter — absolute indices (`3:429`) and/or a cadence that scales with the run (`every:5:500`). Requires `-meter`. See [Fault recovery](#fault-recovery). |
+| `-segments` | `1` | Suite mode: split each task into N resumed legs (`--continue` between them). The step budget is **divided**, never multiplied. See [Segmented runs](#segmented-runs). |
+| `-steer` | *(none)* | Suite mode: deliver a user turn at a leg boundary, e.g. `"also handle empty input@2"`. Requires `-segments` to reach that leg. |
 
 Diff-mode flags:
 

benchmarks/compaction/main.go

@@ -42,6 +42,7 @@ func main() {
 	window := flag.Int("window", 128_000, "context window in tokens")
 	control := flag.Bool("control", true, "fidelity: also score probes against full history")
 	arm := flag.String("arm", "full", "full | incremental: re-derive each digest from canonical, or fold the previous projection")
+	snip := flag.Bool("snip", false, "legacy no-op: automatic snip projections are gone; kept so old scripts do not fail")
 	out := flag.String("out", "", "write the JSON report here")
 	flag.Parse()
 
@@ -49,14 +50,14 @@ func main() {
 		res []genResult
 		err error
 	)
-	incremental := *arm == "incremental"
+	a := arms{incremental: *arm == "incremental", snip: *snip}
 	switch {
 	case *arm != "full" && *arm != "incremental":
 		err = fmt.Errorf("unknown arm %q", *arm)
 	case *mode == "cost":
-		res, err = runCost(*gens, *window, incremental)
+		res, err = runCost(*gens, *window, a)
 	case *mode == "fidelity":
-		res, err = runFidelity(*gens, *window, *control, incremental)
+		res, err = runFidelity(*gens, *window, *control, a)
 	default:
 		err = fmt.Errorf("unknown mode %q", *mode)
 	}
@@ -83,6 +84,8 @@ type genResult struct {
 	SummarizerInput  int            `json:"summarizer_input_tokens"`
 	LargestCall      int            `json:"largest_call_tokens"`
 	Mode             string         `json:"mode,omitempty"`
+	SnippedResults   int            `json:"snipped_results,omitempty"`
+	SnippedChars     int            `json:"snipped_chars,omitempty"`
 	Seconds          float64        `json:"seconds"`
 	Error            string         `json:"error,omitempty"`
 	Survived         map[string]int `json:"survived,omitempty"`   // probe class -> 1 kept, 0 lost
@@ -97,9 +100,10 @@ type harness struct {
 	agentA *agent.Agent
 	path   string
 	calls  *callRecorder
+	snip   bool
 }
 
-func newHarness(t *testingDir, p provider.Provider, window int, rec *callRecorder, incremental bool) *harness {
+func newHarness(t *testingDir, p provider.Provider, window int, rec *callRecorder, arm arms) *harness {
 	sess := newSession()
 	path := filepath.Join(t.dir, "session.jsonl")
 	a := agent.New(p, tool.NewRegistry(), sess, agent.Options{
@@ -107,13 +111,23 @@ func newHarness(t *testingDir, p provider.Provider, window int, rec *callRecorde
 		ArchiveDir:    filepath.Join(t.dir, "archive"),
 		SessionPath:   path,
 		RecentKeep:    4,
-		Ablation:      foldArm(incremental),
+		// boot's default when cfg.Agent.Keep is unset; without it the bench
+		// would measure a configuration no real session runs.
+		KeepPolicy: agent.KeepErrors,
+		Ablation:   foldArm(arm.incremental),
 	}, rec.sink())
-	return &harness{sess: sess, agentA: a, path: path, calls: rec}
+	return &harness{sess: sess, agentA: a, path: path, calls: rec, snip: arm.snip}
 }
 
 // foldArm switches full re-derivation off, which is what makes a fold read the
 // previous projection instead of the canonical transcript.
+// arms selects the maintenance behaviour under test. Snipping is off by default
+// so a run stays comparable with baselines recorded before it existed.
+type arms struct {
+	incremental bool
+	snip        bool
+}
+
 func foldArm(incremental bool) ablation.Set {
 	if incremental {
 		return ablation.New(ablation.FullFold)
@@ -128,6 +142,15 @@ func (h *harness) runGeneration(ctx context.Context, gen int, probes []probe) ge
 
 	h.calls.reset()
 	start := time.Now()
+	if h.snip {
+		// SnipStaleToolResults is intentionally a no-op; record zeros for
+		// report schema compatibility with pre-content-driven baselines.
+		st, serr := h.agentA.SnipStaleToolResults()
+		if serr != nil {
+			r.Error = serr.Error()
+		}
+		r.SnippedResults, r.SnippedChars = st.Results, st.SavedChars
+	}
 	err := h.agentA.CompactNow(ctx, "")
 	r.Seconds = time.Since(start).Seconds()
 	if err != nil {
@@ -140,12 +163,16 @@ func (h *harness) runGeneration(ctx context.Context, gen int, probes []probe) ge
 	}
 	if st, ok, sterr := agent.LoadCompactionState(h.path); sterr == nil && ok {
 		r.ProjectionTokens = st.Projection.ProjectionTokens
-		r.Mode = st.LastMode
+		if st.LastReceipt != nil && st.LastReceipt.Action == "summary" {
+			r.Mode = agent.CompactionModeSummarized
+		} else if st.LastMode != "" {
+			r.Mode = st.LastMode
+		}
 	}
 	return r
 }
 
-func runCost(gens, window int, incremental bool) ([]genResult, error) {
+func runCost(gens, window int, a arms) ([]genResult, error) {
 	dir, cleanup, err := tempDir()
 	if err != nil {
 		return nil, err
@@ -154,7 +181,7 @@ func runCost(gens, window int, incremental bool) ([]genResult, error) {
 
 	rec := &callRecorder{}
 	p := &scriptedProvider{rec: rec, reply: syntheticDigest, window: window}
-	h := newHarness(dir, p, window, rec, incremental)
+	h := newHarness(dir, p, window, rec, a)
 
 	var out []genResult
 	for gen := range gens {
@@ -163,7 +190,7 @@ func runCost(gens, window int, incremental bool) ([]genResult, error) {
 	return out, nil
 }
 
-func runFidelity(gens, window int, control, incremental bool) ([]genResult, error) {
+func runFidelity(gens, window int, control bool, a arms) ([]genResult, error) {
 	key := os.Getenv("DEEPSEEK_API_KEY")
 	if key == "" {
 		return nil, fmt.Errorf("fidelity mode needs DEEPSEEK_API_KEY")
@@ -179,7 +206,7 @@ func runFidelity(gens, window int, control, incremental bool) ([]genResult, erro
 	defer cleanup()
 
 	rec := &callRecorder{}
-	h := newHarness(dir, &recordingProvider{inner: p, rec: rec}, window, rec, incremental)
+	h := newHarness(dir, &recordingProvider{inner: p, rec: rec}, window, rec, a)
 	probes := probeSuite()
 
 	ctx := context.Background()
@@ -193,7 +220,7 @@ func runFidelity(gens, window int, control, incremental bool) ([]genResult, erro
 			return nil, verr
 		}
 		for _, probe := range probes {
-			if probe.plantAt > gen {
+			if probe.settledAt() > gen {
 				continue
 			}
 			answer, aerr := ask(ctx, p, visible, probe.question)

benchmarks/compaction/main_test.go

@@ -2,17 +2,16 @@ package main
 
 import "testing"
 
-// The cost arm is deterministic, so it doubles as the regression guard for the
-// property it was written to measure: a session that keeps growing must keep
-// folding, and no single summarizer call may outgrow the window.
+// The cost arm is deterministic, so it doubles as the regression guard for a
+// growing session whose complete summary prefix still fits the model window.
 func TestRepeatedFoldsStayBoundedAndKeepSucceeding(t *testing.T) {
 	const (
-		window   = 64_000
+		window   = 1_000_000
 		gens     = 6
 		reserve  = 8192 // summaryOutputReserve: the digest the call must still return
-		maxCalls = 7    // maxSummarySpans + the merge pass
+		maxCalls = 1    // Harness-style folding issues one complete-prefix request
 	)
-	res, err := runCost(gens, window, false)
+	res, err := runCost(gens, window, arms{})
 	if err != nil {
 		t.Fatalf("runCost: %v", err)
 	}
@@ -38,6 +37,32 @@ func TestRepeatedFoldsStayBoundedAndKeepSucceeding(t *testing.T) {
 	}
 }
 
+// Harness-style compaction never privately slices an oversized prefix or
+// fabricates a digest. Admission failure is explicit and installs no summary.
+func TestOversizedSummaryPrefixFailsWithoutPrivateShortening(t *testing.T) {
+	const window = 64_000
+	res, err := runCost(1, window, arms{})
+	if err != nil {
+		t.Fatalf("runCost: %v", err)
+	}
+	if len(res) != 1 {
+		t.Fatalf("generations = %d, want 1", len(res))
+	}
+	r := res[0]
+	if r.Error == "" {
+		t.Fatal("oversized complete prefix unexpectedly succeeded")
+	}
+	if r.SummarizerCalls != 1 {
+		t.Fatalf("summarizer calls = %d, want one failed request", r.SummarizerCalls)
+	}
+	if r.LargestCall <= window {
+		t.Fatalf("largest call = %d, want an input over window %d", r.LargestCall, window)
+	}
+	if r.ProjectionTokens != 0 {
+		t.Fatalf("failed oversized fold installed a %d-token projection", r.ProjectionTokens)
+	}
+}
+
 // A probe must score the stale answer as lost even when the model hedges its
 // way to mentioning the right one — "yes, but it has not been re-run since"
 // is the exact shape a drifting digest produces.

benchmarks/compaction/probes.go

@@ -8,6 +8,7 @@ import (
 
 	"reasonix/internal/agent"
 	"reasonix/internal/provider"
+	"reasonix/internal/tool"
 )
 
 // probeAnswerContract rides with every probe question. A context full of tool
@@ -33,9 +34,13 @@ func invalidAnswer(s string) bool {
 // The question is asked against the compacted context, so a wrong answer means
 // compaction lost the fact — not that the model is weak.
 type probe struct {
-	class    string
-	plantAt  int
-	plant    func(*agent.Session)
+	class   string
+	plantAt int
+	plant   func(*agent.Session)
+	// later plants more of the same fact in later generations, so a decision
+	// that changes across folds is tested the way it actually happens: each
+	// revision lands on the far side of a compaction, not next to the last one.
+	later    map[int]func(*agent.Session)
 	question string
 	want     []string // answer must contain one of these, lowercased
 	reject   []string // ...and none of these: the pre-correction answer
@@ -52,6 +57,24 @@ func toolRound(id, name, args, result string) func(*agent.Session) {
 	}
 }
 
+// failedToolRound is a tool round the host recorded as failed, the way a real
+// non-zero bash run arrives. Without the execution record the keep policy sees
+// only text, which is exactly the gap the buried-evidence probe measures.
+func failedToolRound(id, name, args, result string, code int) func(*agent.Session) {
+	return func(s *agent.Session) {
+		exit := code
+		s.Add(provider.Message{Role: provider.RoleAssistant, ToolCalls: []provider.ToolCall{{ID: id, Name: name, Arguments: args}}})
+		s.Add(provider.Message{
+			Role: provider.RoleTool, ToolCallID: id, Name: name, Content: result,
+			ToolExecution: &provider.ToolExecution{
+				Kind:     "shell",
+				State:    tool.ShellStateFailed,
+				ExitCode: &exit,
+			},
+		})
+	}
+}
+
 func seq(fns ...func(*agent.Session)) func(*agent.Session) {
 	return func(s *agent.Session) {
 		for _, fn := range fns {
@@ -64,6 +87,50 @@ func seq(fns ...func(*agent.Session)) func(*agent.Session) {
 // freshness and correction probes are the ones summaries classically get wrong:
 // both have a plausible stale answer that reads as correct.
 func probeSuite() []probe {
+	suite := append(factProbes(), revisionProbes()...)
+	return append(suite, snipProbes()...)
+}
+
+// buriedTestLog is a `go test -v` log whose only failure detail sits in the
+// middle. Geometric snipping keeps the first 80 and last 12 lines, so this is
+// precisely the shape it drops while reporting a plausible-looking remainder.
+// It names a package no other probe touches: a run covering config/ would be a
+// truthful "yes" for verification-freshness and score that probe as lost.
+func buriedTestLog() string {
+	var b strings.Builder
+	pass := func(i int) {
+		fmt.Fprintf(&b, "=== RUN   TestEmitterCase%03d\n--- PASS: TestEmitterCase%03d (0.00s)\n", i, i)
+	}
+	for i := range 120 {
+		pass(i)
+	}
+	b.WriteString("=== RUN   TestEmitterQuoting\n")
+	b.WriteString("    emitter_test.go:412: assertion failed: expected beta-7d21, got gamma-4a88\n")
+	b.WriteString("--- FAIL: TestEmitterQuoting (0.01s)\n")
+	for i := 120; i < 200; i++ {
+		pass(i)
+	}
+	b.WriteString("FAIL\nexit status 1\nFAIL\treasonix/emitter\t0.234s\n")
+	return b.String()
+}
+
+// snipProbes plant a fact in the middle of a long tool result, out of reach of
+// the head/tail geometry. They score the maintenance pass rather than the fold:
+// every other probe in the suite is short enough that snipping cannot touch it.
+func snipProbes() []probe {
+	return []probe{
+		{
+			class:    "buried-evidence",
+			plantAt:  1,
+			plant:    failedToolRound("bt1", "bash", `{"cmd":"go test ./emitter -v"}`, buriedTestLog(), 1),
+			question: "In the failed test, what value did the assertion expect? Reply with just the value.",
+			want:     []string{"beta-7d21"},
+			reject:   []string{"gamma-4a88"},
+		},
+	}
+}
+
+func factProbes() []probe {
 	return []probe{
 		{
 			class:    "user-constraint",
@@ -165,6 +232,45 @@ func probeSuite() []probe {
 	}
 }
 
+// revisionProbes state a fact and then change it in a later generation. The
+// revision lands on the far side of a fold, so carrying it forward means
+// superseding the digest's own earlier claim rather than a neighbouring turn.
+func revisionProbes() []probe {
+	return []probe{
+		{
+			class:    "late-constraint",
+			plantAt:  3,
+			plant:    userTurn("New hard rule from here on: never edit anything under internal/store/."),
+			question: "Are you allowed to edit files under internal/store/? Answer yes or no.",
+			want:     []string{"no"},
+			reject:   []string{"yes"},
+		},
+		{
+			class:   "reversal-chain",
+			plantAt: 0,
+			plant:   userTurn("Use PostgreSQL for the datastore."),
+			later: map[int]func(*agent.Session){
+				1: userTurn("Change of plan: drop PostgreSQL, use SQLite instead."),
+				2: userTurn("Final call: back to PostgreSQL after all."),
+			},
+			question: "Which datastore is the current decision? Reply with one word.",
+			want:     []string{"postgresql", "postgres"},
+			reject:   []string{"sqlite"},
+		},
+		{
+			class:   "distractor-file",
+			plantAt: 1,
+			plant:   userTurn("Draft note: the fix might belong in config/legacy_parser.go."),
+			later: map[int]func(*agent.Session){
+				3: userTurn("Confirmed: the fix belongs in config/emitter.go; the legacy parser is not involved."),
+			},
+			question: "Which file does the fix belong in? Reply with just the filename, no path.",
+			want:     []string{"emitter"},
+			reject:   []string{"legacy"},
+		},
+	}
+}
+
 // score reports whether an answer keeps the planted fact. A rejected token
 // anywhere in the answer counts as lost even when the wanted token also
 // appears, so "yes, but it was not re-run" does not pass as "no".
@@ -194,4 +300,15 @@ func matchesToken(lowered, want string) bool {
 	}), want)
 }
 
-func (p probe) String() string { return fmt.Sprintf("%s@gen%d", p.class, p.plantAt) }
+// settledAt is the first generation whose answer is the one want/reject scores.
+// A probe revised across folds has a different correct answer while the chain is
+// still running, so asking before it settles would score a right answer as lost.
+func (p probe) settledAt() int {
+	at := p.plantAt
+	for gen := range p.later {
+		at = max(at, gen)
+	}
+	return at
+}
+
+func (p probe) String() string { return fmt.Sprintf("%s@gen%d", p.class, p.settledAt()) }

benchmarks/compaction/session.go

@@ -46,6 +46,9 @@ func growSession(sess *agent.Session, gen int, probes []probe) {
 		if p.plantAt == gen {
 			p.plant(sess)
 		}
+		if revise, ok := p.later[gen]; ok {
+			revise(sess)
+		}
 	}
 	for i := range unitsPerGeneration {
 		workUnit(sess, gen, i)

benchmarks/compaction/snip_test.go

@@ -0,0 +1,41 @@
+package main
+
+import (
+	"strings"
+	"testing"
+)
+
+// Automatic snip projections are gone. SnipStaleToolResults remains as a no-op
+// so older harness flags and call sites do not panic or rewrite history.
+func TestSnipIsNoOp(t *testing.T) {
+	dir, cleanup, err := tempDir()
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer cleanup()
+
+	rec := &callRecorder{}
+	const window = 64_000
+	h := newHarness(dir, &scriptedProvider{rec: rec, reply: syntheticDigest, window: window}, window, rec, arms{snip: true})
+	for gen := range 3 {
+		growSession(h.sess, gen, probeSuite())
+	}
+	before := renderAll(h.sess.Snapshot())
+	if !strings.Contains(before, "beta-7d21") {
+		t.Fatal("planted fact missing before the snip call")
+	}
+	st, err := h.agentA.SnipStaleToolResults()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if st.Results != 0 || st.SavedChars != 0 {
+		t.Fatalf("snip no-op rewrote history: results=%d chars=%d", st.Results, st.SavedChars)
+	}
+	after := renderAll(h.sess.Snapshot())
+	if after != before {
+		t.Fatal("canonical transcript changed after SnipStaleToolResults")
+	}
+	if !strings.Contains(after, "beta-7d21") {
+		t.Error("planted fact missing after snip no-op")
+	}
+}

benchmarks/context-maintenance-e2e/main.go

@@ -1,5 +1,6 @@
-// Drives the context-maintenance E2E scenarios against the real DeepSeek API:
-// seed → (idle past cache TTL) → resume A/B-compares cold-restart miss tokens with and without pruning.
+// Cost-capped seed → resume → continue smoke for content-driven maintenance.
+// Offline covers seed/resume; live continue needs DEEPSEEK_API_KEY and allows
+// at most one summary after growing past compact_ratio=0.85.
 package main
 
 import (
@@ -17,105 +18,104 @@ import (
 	"reasonix/internal/provider"
 	_ "reasonix/internal/provider/openai"
 	"reasonix/internal/tool"
-	"reasonix/internal/tool/builtin"
 )
 
 const (
-	model      = "deepseek-v4-flash"
-	baseURL    = "https://api.deepseek.com"
-	fatResults = 20
-	fatBytes   = 12_000
+	model         = "deepseek-v4-flash"
+	baseURL       = "https://api.deepseek.com"
+	windowTokens  = 1_000_000
+	compactRatio  = 0.85
+	defaultMaxUSD = 0.50
+	fatBytes      = 32 * 1024
 )
 
-func prov() provider.Provider {
-	key := os.Getenv("DEEPSEEK_API_KEY")
-	if key == "" {
-		fmt.Fprintln(os.Stderr, "DEEPSEEK_API_KEY not set")
-		os.Exit(1)
-	}
-	p, err := provider.New("openai", provider.Config{Name: "e2e", BaseURL: baseURL, Model: model, APIKey: key})
-	if err != nil {
-		fmt.Fprintln(os.Stderr, err)
-		os.Exit(1)
-	}
-	return p
+type costCap struct {
+	maxUSD float64
+	spent  float64
 }
 
-func fakeGoFile(nonce string, i, size int) string {
-	var b strings.Builder
-	fmt.Fprintf(&b, "// module %s file%02d\npackage stress\n\n", nonce, i)
-	line := 0
-	for b.Len() < size {
-		fmt.Fprintf(&b, "func helper_%s_%02d_%04d(x int) int { return x*%d + %d }\n", nonce, i, line, line+3, line*7)
-		line++
+func (c *costCap) add(u *provider.Usage, pricing *provider.Pricing) error {
+	if c == nil || u == nil || pricing == nil {
+		return nil
 	}
-	return b.String()
-}
-
-func seedSession(nonce string) *agent.Session {
-	s := agent.NewSession("You are a terse coding agent reviewing a Go codebase.")
-	s.Add(provider.Message{Role: provider.RoleUser, Content: "Review every file in module " + nonce + " one by one. Keep notes short."})
-	for i := range fatResults {
-		id := fmt.Sprintf("c%02d", i)
-		name := fmt.Sprintf("src/file%02d.go", i)
-		s.Add(provider.Message{Role: provider.RoleAssistant, ToolCalls: []provider.ToolCall{{ID: id, Name: "read_file", Arguments: fmt.Sprintf(`{"path":%q}`, name)}}})
-		s.Add(provider.Message{Role: provider.RoleTool, ToolCallID: id, Name: "read_file", Content: fakeGoFile(nonce, i, fatBytes)})
-		s.Add(provider.Message{Role: provider.RoleAssistant, Content: fmt.Sprintf("Reviewed %s.", name)})
+	c.spent += pricing.Cost(u)
+	if c.maxUSD > 0 && c.spent > c.maxUSD {
+		return fmt.Errorf("cost cap exceeded: spent $%.4f > max $%.4f", c.spent, c.maxUSD)
 	}
-	return s
-}
-
-// oneShot appends a user message and runs a single completion, returning usage.
-func oneShot(p provider.Provider, msgs []provider.Message, question string) (provider.Usage, error) {
-	req := provider.Request{
-		Messages:  append(append([]provider.Message(nil), msgs...), provider.Message{Role: provider.RoleUser, Content: question}),
-		MaxTokens: 32,
-	}
-	ch, err := p.Stream(context.Background(), req)
-	if err != nil {
-		return provider.Usage{}, err
-	}
-	var u provider.Usage
-	for c := range ch {
-		switch c.Type {
-		case provider.ChunkUsage:
-			u = *c.Usage
-		case provider.ChunkError:
-			return u, c.Err
-		}
-	}
-	return u, nil
+	return nil
 }
 
 type meta struct {
-	SeededAt time.Time                 `json:"seeded_at"`
-	Nonces   map[string]string         `json:"nonces"`
-	SeedUse  map[string]provider.Usage `json:"seed_usage"`
+	SeededAt          time.Time       `json:"seeded_at"`
+	ProjectionVersion uint64          `json:"projection_version"`
+	CanonicalTokens   int             `json:"canonical_tokens"`
+	ProjectedTokens   int             `json:"projected_tokens"`
+	TriggerTokens     int             `json:"trigger_tokens"`
+	SummaryCalls      int             `json:"summary_calls"`
+	SpentUSD          float64         `json:"spent_usd"`
+	ContinueUsage     *provider.Usage `json:"continue_usage,omitempty"`
 }
 
-func seed(dir string) {
-	p := prov()
-	if err := os.MkdirAll(dir, 0o755); err != nil {
+type recordSink struct {
+	summaryStarts int
+}
+
+func (s *recordSink) Emit(e event.Event) {
+	if e.Kind == event.CompactionStarted {
+		s.summaryStarts++
+	}
+}
+
+func prov() (provider.Provider, *provider.Pricing) {
+	key := os.Getenv("DEEPSEEK_API_KEY")
+	if key == "" {
+		fmt.Fprintln(os.Stderr, "DEEPSEEK_API_KEY not set (use -offline for seed/resume)")
+		os.Exit(1)
+	}
+	p, err := provider.New("openai", provider.Config{
+		Name: "e2e", BaseURL: baseURL, Model: model, APIKey: key,
+		Extra: map[string]any{"max_output_tokens": 1024},
+	})
+	if err != nil {
 		fmt.Fprintln(os.Stderr, err)
 		os.Exit(1)
 	}
-	m := meta{SeededAt: time.Now(), Nonces: map[string]string{}, SeedUse: map[string]provider.Usage{}}
-	for _, arm := range []string{"pruned", "control"} {
-		nonce := fmt.Sprintf("%s%d", arm, time.Now().UnixNano()%1_000_000)
-		s := seedSession(nonce)
-		u, err := oneShot(p, s.Snapshot(), "How many files have you reviewed so far? Reply with just the number.")
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "seed %s: %v\n", arm, err)
-			os.Exit(1)
-		}
-		if err := s.Save(filepath.Join(dir, arm+".jsonl")); err != nil {
-			fmt.Fprintln(os.Stderr, err)
-			os.Exit(1)
-		}
-		m.Nonces[arm] = nonce
-		m.SeedUse[arm] = u
-		fmt.Printf("seeded %-7s prompt=%d hit=%d miss=%d\n", arm, u.PromptTokens, u.CacheHitTokens, u.CacheMissTokens)
+	pricing := &provider.Pricing{Input: 0.14, Output: 0.28, CacheHit: 0.014, Currency: "$"}
+	return p, pricing
+}
+
+func fatHistory(n int) []provider.Message {
+	result := strings.Repeat("x", fatBytes)
+	msgs := []provider.Message{
+		{Role: provider.RoleSystem, Content: "You are a terse coding agent."},
+		{Role: provider.RoleUser, Content: "Review the large tool outputs carefully."},
 	}
+	for i := range n {
+		id := fmt.Sprintf("tool-%d", i)
+		msgs = append(msgs,
+			provider.Message{Role: provider.RoleAssistant, ToolCalls: []provider.ToolCall{{ID: id, Name: "read_file", Arguments: "{}"}}},
+			provider.Message{Role: provider.RoleTool, ToolCallID: id, Name: "read_file", Content: result},
+		)
+	}
+	return append(msgs,
+		provider.Message{Role: provider.RoleUser, Content: "summarize status when asked"},
+		provider.Message{Role: provider.RoleAssistant, Content: "standing by"},
+	)
+}
+
+func newAgent(p provider.Provider, sess *agent.Session, path string, sink event.Sink) *agent.Agent {
+	return agent.New(p, tool.NewRegistry(), sess, agent.Options{
+		ContextWindow: windowTokens,
+		CompactRatio:  compactRatio,
+		RecentKeep:    2,
+		SessionPath:   path,
+		WorkspaceID:   "cm-e2e",
+		ModelRef:      "deepseek/" + model,
+		MaxSteps:      2,
+	}, sink)
+}
+
+func writeMeta(dir string, m meta) {
 	b, _ := json.MarshalIndent(m, "", "  ")
 	if err := os.WriteFile(filepath.Join(dir, "meta.json"), b, 0o644); err != nil {
 		fmt.Fprintln(os.Stderr, err)
@@ -123,8 +123,7 @@ func seed(dir string) {
 	}
 }
 
-func resume(dir string) {
-	p := prov()
+func readMeta(dir string) meta {
 	raw, err := os.ReadFile(filepath.Join(dir, "meta.json"))
 	if err != nil {
 		fmt.Fprintln(os.Stderr, err)
@@ -135,121 +134,189 @@ func resume(dir string) {
 		fmt.Fprintln(os.Stderr, err)
 		os.Exit(1)
 	}
-	idle := time.Since(m.SeededAt).Round(time.Minute)
+	return m
+}
 
-	out := map[string]provider.Usage{}
-	for _, arm := range []string{"pruned", "control"} {
-		s, err := agent.LoadSession(filepath.Join(dir, arm+".jsonl"))
-		if err != nil {
-			fmt.Fprintln(os.Stderr, err)
-			os.Exit(1)
-		}
-		prunes := 0
-		if arm == "pruned" {
-			a := agent.New(nil, tool.NewRegistry(), s, agent.Options{ContextWindow: 1_000_000, ArchiveDir: filepath.Join(dir, "archive")}, event.Discard)
-			st, err := a.PruneStaleToolResults()
-			if err != nil {
-				fmt.Fprintln(os.Stderr, "prune:", err)
-				os.Exit(1)
-			}
-			prunes = st.Results
-		}
-		u, err := oneShot(p, s.Snapshot(), "Which file did you review first? Reply with just the path.")
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "resume %s: %v\n", arm, err)
-			os.Exit(1)
-		}
-		out[arm] = u
-		fmt.Printf("resume %-7s idle=%s pruned=%d prompt=%d hit=%d miss=%d\n", arm, idle, prunes, u.PromptTokens, u.CacheHitTokens, u.CacheMissTokens)
-	}
-	b, _ := json.MarshalIndent(map[string]any{"idle": idle.String(), "resume_usage": out}, "", "  ")
-	if err := os.WriteFile(filepath.Join(dir, fmt.Sprintf("resume-%d.json", time.Now().Unix())), b, 0o644); err != nil {
+func seed(dir string, offline bool, cap *costCap) {
+	if err := os.MkdirAll(dir, 0o755); err != nil {
 		fmt.Fprintln(os.Stderr, err)
 		os.Exit(1)
 	}
-
-	c, pr := out["control"], out["pruned"]
-	if c.CacheMissTokens > 0 {
-		fmt.Printf("\ncold-restart miss tokens: control=%d pruned=%d (%.0f%% reduction)\n",
-			c.CacheMissTokens, pr.CacheMissTokens, 100*(1-float64(pr.CacheMissTokens)/float64(c.CacheMissTokens)))
+	path := filepath.Join(dir, "session.jsonl")
+	// ~80×32KB tool results: well under 85% of 1M for a cold estimate.
+	sess := &agent.Session{Messages: fatHistory(80)}
+	sink := &recordSink{}
+	var p provider.Provider
+	if !offline {
+		p, _ = prov()
 	}
-}
-
-// comprehension checks that the agent re-reads a file behind a prune placeholder
-// instead of hallucinating: the answer is a number that exists only in the file.
-func comprehension(trials int) {
-	p := prov()
-	pass := 0
-	for t := range trials {
-		dir, err := os.MkdirTemp("", "cm-e2e-")
-		if err != nil {
-			fmt.Fprintln(os.Stderr, err)
-			os.Exit(1)
-		}
-		secret := fmt.Sprintf("%d", 1000+time.Now().UnixNano()%9000)
-		content := "package cfg\n\n// retention floor, milliseconds\nconst cacheRetentionFloor = " + secret + "\n" + strings.Repeat("// padding line filler for prune eligibility\n", 400)
-		if err := os.WriteFile(filepath.Join(dir, "config.go"), []byte(content), 0o644); err != nil {
-			fmt.Fprintln(os.Stderr, err)
-			os.Exit(1)
-		}
-
-		s := agent.NewSession("You are a terse coding agent. Use tools when you need file contents.")
-		s.Add(provider.Message{Role: provider.RoleUser, Content: "Read config.go and note its constants."})
-		s.Add(provider.Message{Role: provider.RoleAssistant, ToolCalls: []provider.ToolCall{{ID: "r1", Name: "read_file", Arguments: `{"path":"config.go"}`}}})
-		s.Add(provider.Message{Role: provider.RoleTool, ToolCallID: "r1", Name: "read_file", Content: content})
-		s.Add(provider.Message{Role: provider.RoleAssistant, Content: "Noted the constants in config.go."})
-		for i := range 4 {
-			s.Add(provider.Message{Role: provider.RoleUser, Content: fmt.Sprintf("ack %d", i)})
-			s.Add(provider.Message{Role: provider.RoleAssistant, Content: "ok"})
-		}
-
-		reg := tool.NewRegistry()
-		for _, tl := range (builtin.Workspace{Dir: dir}).Tools("read_file") {
-			reg.Add(tl)
-		}
-		a := agent.New(p, reg, s, agent.Options{ContextWindow: 2000, RecentKeep: 2, MaxSteps: 5}, event.Discard)
-		st, err := a.PruneStaleToolResults()
-		if err != nil || st.Results == 0 {
-			fmt.Fprintf(os.Stderr, "trial %d: prune did not fire (st=%+v err=%v)\n", t, st, err)
-			os.Exit(1)
-		}
-
-		err = a.Run(context.Background(), "What is the exact numeric value of cacheRetentionFloor in config.go? Reply with just the number.")
-		reRead, answered := false, false
-		for _, msg := range s.Snapshot() {
-			if msg.Role == provider.RoleTool && strings.Contains(msg.Content, "cacheRetentionFloor = "+secret) {
-				reRead = true
-			}
-			if msg.Role == provider.RoleAssistant && strings.Contains(msg.Content, secret) {
-				answered = true
-			}
-		}
-		ok := err == nil && reRead && answered
-		if ok {
-			pass++
-		}
-		fmt.Printf("trial %d: re-read=%v answered=%v err=%v\n", t, reRead, answered, err)
-		os.RemoveAll(dir)
-	}
-	fmt.Printf("\ncomprehension: %d/%d passed\n", pass, trials)
-	if pass < trials {
+	a := newAgent(p, sess, path, sink)
+	before := a.ContextMaintenanceSnapshot()
+	if before.TriggerTokens <= 0 {
+		fmt.Fprintln(os.Stderr, "seed: missing trigger tokens")
 		os.Exit(1)
 	}
+	if before.ProjectedTokens >= before.TriggerTokens {
+		fmt.Fprintf(os.Stderr, "seed fixture already at/above trigger: projected=%d trigger=%d\n",
+			before.ProjectedTokens, before.TriggerTokens)
+		os.Exit(1)
+	}
+	if err := a.PrepareContext(context.Background()); err != nil {
+		fmt.Fprintln(os.Stderr, "seed prepare:", err)
+		os.Exit(1)
+	}
+	after := a.ContextMaintenanceSnapshot()
+	if after.ProjectionVersion != 0 {
+		fmt.Fprintf(os.Stderr, "seed installed projection version %d below compact_ratio\n", after.ProjectionVersion)
+		os.Exit(1)
+	}
+	if sink.summaryStarts != 0 {
+		fmt.Fprintf(os.Stderr, "seed started %d summary calls below trigger\n", sink.summaryStarts)
+		os.Exit(1)
+	}
+	if err := sess.Save(path); err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+	m := meta{
+		SeededAt:          time.Now(),
+		ProjectionVersion: after.ProjectionVersion,
+		CanonicalTokens:   after.CanonicalTokens,
+		ProjectedTokens:   after.ProjectedTokens,
+		TriggerTokens:     after.TriggerTokens,
+		SummaryCalls:      sink.summaryStarts,
+		SpentUSD:          cap.spent,
+	}
+	writeMeta(dir, m)
+	fmt.Printf("seed ok projected=%d trigger=%d version=%d summary_calls=%d spent=$%.4f\n",
+		m.ProjectedTokens, m.TriggerTokens, m.ProjectionVersion, m.SummaryCalls, m.SpentUSD)
+}
+
+func resume(dir string, offline bool) {
+	path := filepath.Join(dir, "session.jsonl")
+	m := readMeta(dir)
+	sess, err := agent.LoadSession(path)
+	if err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+	sink := &recordSink{}
+	var p provider.Provider
+	if !offline {
+		p, _ = prov()
+	}
+	a := newAgent(p, sess, path, sink)
+	snap := a.ContextMaintenanceSnapshot()
+	if snap.ProjectionVersion != m.ProjectionVersion {
+		fmt.Fprintf(os.Stderr, "resume version = %d, want %d\n", snap.ProjectionVersion, m.ProjectionVersion)
+		os.Exit(1)
+	}
+	if err := a.PrepareContext(context.Background()); err != nil {
+		fmt.Fprintln(os.Stderr, "resume prepare:", err)
+		os.Exit(1)
+	}
+	after := a.ContextMaintenanceSnapshot()
+	if after.ProjectionVersion != m.ProjectionVersion {
+		fmt.Fprintf(os.Stderr, "resume advanced version to %d\n", after.ProjectionVersion)
+		os.Exit(1)
+	}
+	if sink.summaryStarts != 0 {
+		fmt.Fprintf(os.Stderr, "resume re-ran summary %d times\n", sink.summaryStarts)
+		os.Exit(1)
+	}
+	fmt.Printf("resume ok idle=%s version=%d summary_calls=0\n",
+		time.Since(m.SeededAt).Round(time.Second), m.ProjectionVersion)
+}
+
+func cont(dir string, offline bool, cap *costCap) {
+	if offline {
+		fmt.Fprintln(os.Stderr, "continue requires live provider (omit -offline)")
+		os.Exit(1)
+	}
+	path := filepath.Join(dir, "session.jsonl")
+	m := readMeta(dir)
+	sess, err := agent.LoadSession(path)
+	if err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+	// Grow past the 85% trigger with additional fat tool turns (skip system/user prelude).
+	for _, msg := range fatHistory(40)[2:] {
+		sess.Add(msg)
+	}
+	sink := &recordSink{}
+	p, pricing := prov()
+	a := newAgent(p, sess, path, sink)
+	before := a.ContextMaintenanceSnapshot()
+	if before.ProjectedTokens < before.TriggerTokens {
+		fmt.Fprintf(os.Stderr, "continue fixture still below trigger: projected=%d trigger=%d\n",
+			before.ProjectedTokens, before.TriggerTokens)
+		os.Exit(1)
+	}
+	if err := a.PrepareContext(context.Background()); err != nil {
+		fmt.Fprintln(os.Stderr, "continue prepare:", err)
+		os.Exit(1)
+	}
+	if sink.summaryStarts > 1 {
+		fmt.Fprintf(os.Stderr, "continue started %d summaries, want ≤1\n", sink.summaryStarts)
+		os.Exit(1)
+	}
+	after := a.ContextMaintenanceSnapshot()
+	if sink.summaryStarts == 1 && after.ProjectionVersion != m.ProjectionVersion+1 {
+		fmt.Fprintf(os.Stderr, "continue version = %d, want %d after one summary\n",
+			after.ProjectionVersion, m.ProjectionVersion+1)
+		os.Exit(1)
+	}
+	if u := a.LastUsage(); u != nil {
+		if err := cap.add(u, pricing); err != nil {
+			fmt.Fprintln(os.Stderr, err)
+			os.Exit(1)
+		}
+		m.ContinueUsage = u
+	}
+	startsBefore := sink.summaryStarts
+	_ = a.Run(context.Background(), "Reply with exactly: ok")
+	if u := a.LastUsage(); u != nil {
+		if err := cap.add(u, pricing); err != nil {
+			fmt.Fprintln(os.Stderr, err)
+			os.Exit(1)
+		}
+	}
+	if sink.summaryStarts != startsBefore {
+		fmt.Fprintf(os.Stderr, "post-checkpoint run started extra summaries (%d→%d)\n",
+			startsBefore, sink.summaryStarts)
+		os.Exit(1)
+	}
+	if err := sess.Save(path); err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+	final := a.ContextMaintenanceSnapshot()
+	m.ProjectionVersion = final.ProjectionVersion
+	m.ProjectedTokens = final.ProjectedTokens
+	m.CanonicalTokens = final.CanonicalTokens
+	m.SummaryCalls = sink.summaryStarts
+	m.SpentUSD = cap.spent
+	writeMeta(dir, m)
+	fmt.Printf("continue ok version=%d projected=%d summary_calls=%d spent=$%.4f\n",
+		m.ProjectionVersion, m.ProjectedTokens, m.SummaryCalls, m.SpentUSD)
 }
 
 func main() {
-	dir := flag.String("dir", "benchmarks/context-maintenance-e2e/run", "state directory for seed/resume")
-	trials := flag.Int("trials", 5, "comprehension trials")
+	dir := flag.String("dir", "benchmarks/context-maintenance-e2e/run", "state directory")
+	maxUSD := flag.Float64("max-usd", defaultMaxUSD, "hard cost cap for live API legs")
+	offline := flag.Bool("offline", false, "skip live provider (seed/resume only)")
 	flag.Parse()
+	cap := &costCap{maxUSD: *maxUSD}
 	switch flag.Arg(0) {
 	case "seed":
-		seed(*dir)
+		seed(*dir, *offline, cap)
 	case "resume":
-		resume(*dir)
-	case "comprehension":
-		comprehension(*trials)
+		resume(*dir, *offline)
+	case "continue":
+		cont(*dir, *offline, cap)
 	default:
-		fmt.Fprintln(os.Stderr, "usage: context-maintenance-e2e [seed|resume|comprehension]")
+		fmt.Fprintln(os.Stderr, "usage: context-maintenance-e2e [-dir DIR] [-max-usd N] [-offline] seed|resume|continue")
 		os.Exit(1)
 	}
 }

benchmarks/e2e/tasks/audit-config-drift/task.toml

@@ -0,0 +1,4 @@
+prompt = "Exactly one setting differs across config/base.toml, config/staging.toml and config/production.toml. Write AUDIT.md naming the setting that drifted, the environment it drifted in, and both values. Do not change any config."
+class = "read-only-output"
+max_steps = 25
+timeout_sec = 480

benchmarks/e2e/tasks/audit-config-drift/verify.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+set -e
+test -f AUDIT.md || { echo "AUDIT.md was never written" >&2; exit 1; }
+doc="$(tr '[:upper:]' '[:lower:]' < AUDIT.md)"
+for want in timeout_sec production 30 5; do
+  case "$doc" in
+    *"$want"*) ;;
+    *) echo "AUDIT.md never mentions $want" >&2; exit 1 ;;
+  esac
+done
+# Naming a setting that did not drift means the three files were not compared.
+for absent in max_body_mb ttl_sec; do
+  case "$doc" in
+    *"$absent"*) echo "AUDIT.md reports $absent, which is identical everywhere" >&2; exit 1 ;;
+  esac
+done
+grep -q "timeout_sec = 5" config/production.toml || {
+  echo "config/production.toml was modified; the task is to report the drift" >&2
+  exit 1
+}

benchmarks/e2e/tasks/audit-config-drift/workdir/README.md

@@ -0,0 +1 @@
+All three environments are kept in lockstep. Any difference is a mistake.

benchmarks/e2e/tasks/audit-config-drift/workdir/config/base.toml

@@ -0,0 +1,7 @@
+[server]
+port = 8080
+timeout_sec = 30
+max_body_mb = 8
+
+[cache]
+ttl_sec = 300

benchmarks/e2e/tasks/audit-config-drift/workdir/config/production.toml

@@ -0,0 +1,7 @@
+[server]
+port = 8080
+timeout_sec = 5
+max_body_mb = 8
+
+[cache]
+ttl_sec = 300

benchmarks/e2e/tasks/audit-config-drift/workdir/config/staging.toml

@@ -0,0 +1,7 @@
+[server]
+port = 8080
+timeout_sec = 30
+max_body_mb = 8
+
+[cache]
+ttl_sec = 300

benchmarks/e2e/tasks/context-pressure-forced/task.toml

@@ -0,0 +1,4 @@
+prompt = "common/money.py now requires a second argument: fmt_amount(cents, currency). Every call site under pkgs/alpha, pkgs/beta and pkgs/gamma still passes one argument and is broken. Dispatch the three packages in parallel with a single `fleet` call, giving each task the write_paths for its own package directory, and have each sub-agent update its package call sites to pass the currency \"USD\". Then confirm `python3 check.py` prints OK."
+class = "delegation"
+max_steps = 60
+timeout_sec = 900

benchmarks/e2e/tasks/context-pressure-forced/verify.sh

@@ -0,0 +1,15 @@
+# Same migration under an aggressive project compact_ratio (0.5%), an attempt
+# to put the parent under real context pressure — the one mechanism delegation
+# was designed for. It did not work: the agent keeps its session small by
+# writing a script instead of reading, so compaction never engaged and the
+# arms measured the same thing the other shapes did. Kept as an honest record
+# of the attempt, and as a config variant that still exercises the workspace
+# reasonix.toml merge path.
+# Forced-delegation twin: identical workdir and checks, only the prompt differs.
+set -e
+# 36 files across three non-overlapping packages, each needing a real read
+# before any edit. This is the branch size where delegation could pay: the
+# neutral prompt never mentions sub-agents, so an arm that does the work
+# itself is only penalised by the clock.
+python3 check.py
+test -z "$(grep -rn 'fmt_amount([a-z_]*)' pkgs/ || true)"

benchmarks/e2e/tasks/context-pressure-forced/workdir/check.py

@@ -0,0 +1,27 @@
+import importlib, pathlib, sys
+sys.path[:0] = ["common", "."]
+bad = []
+for pkg in ("alpha", "beta", "gamma"):
+    for p in sorted(pathlib.Path("pkgs", pkg).glob("*.py")):
+        if p.stem == "__init__":
+            continue
+        src = p.read_text()
+        if "fmt_amount(" not in src:
+            continue
+        m = importlib.import_module(f"pkgs.{pkg}.{p.stem}")
+        for name in dir(m):
+            fn = getattr(m, name)
+            # Only functions this module defines: fmt_amount is imported into
+            # the namespace and is not one of the call sites under test.
+            if not callable(fn) or name.startswith("_") or getattr(fn, "__module__", "") != m.__name__:
+                continue
+            try:
+                got = fn([{"cents": 1234}])
+            except TypeError as exc:
+                bad.append(f"{pkg}/{p.stem}.{name}: {exc}")
+                continue
+            if got and got[0] not in ("1234", "12.34 USD"):
+                bad.append(f"{pkg}/{p.stem}.{name}: {got[0]}")
+if bad:
+    print("FAIL:"); [print(" ", b) for b in bad[:10]]; sys.exit(1)
+print("OK")

benchmarks/e2e/tasks/context-pressure-forced/workdir/common/money.py

@@ -0,0 +1,3 @@
+def fmt_amount(cents, currency):
+    """Format cents as a currency string, e.g. 1234 -> '12.34 USD'."""
+    return "%d.%02d %s" % (cents // 100, cents % 100, currency)

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/alpha/batch_2.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def collect_batch_0(rows):
+    """Collect batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_batch_1(rows):
+    """Summarise batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_batch_2(rows):
+    """Validate batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_batch_3(rows):
+    """Expand batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_batch_4(rows):
+    """Merge batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_batch_5(rows):
+    """Filter batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_batch_6(rows):
+    """Rank batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_batch_7(rows):
+    """Tally batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_batch_8(rows):
+    """Audit batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/alpha/credit_9.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def tally_credit_0(rows):
+    """Tally credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_credit_1(rows):
+    """Audit credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_credit_2(rows):
+    """Emit credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_credit_3(rows):
+    """Load credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_credit_4(rows):
+    """Render credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_credit_5(rows):
+    """Collect credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_credit_6(rows):
+    """Summarise credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_credit_7(rows):
+    """Validate credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_credit_8(rows):
+    """Expand credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/alpha/invoice_0.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def load_invoice_0(rows):
+    """Load invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_invoice_1(rows):
+    """Render invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_invoice_2(rows):
+    """Collect invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_invoice_3(rows):
+    """Summarise invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_invoice_4(rows):
+    """Validate invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_invoice_5(rows):
+    """Expand invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_invoice_6(rows):
+    """Merge invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_invoice_7(rows):
+    """Filter invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_invoice_8(rows):
+    """Rank invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/alpha/ledger_1.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def render_ledger_0(rows):
+    """Render ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_ledger_1(rows):
+    """Collect ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_ledger_2(rows):
+    """Summarise ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_ledger_3(rows):
+    """Validate ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_ledger_4(rows):
+    """Expand ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_ledger_5(rows):
+    """Merge ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_ledger_6(rows):
+    """Filter ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_ledger_7(rows):
+    """Rank ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_ledger_8(rows):
+    """Tally ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/alpha/payout_5.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def expand_payout_0(rows):
+    """Expand payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_payout_1(rows):
+    """Merge payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_payout_2(rows):
+    """Filter payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_payout_3(rows):
+    """Rank payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_payout_4(rows):
+    """Tally payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_payout_5(rows):
+    """Audit payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_payout_6(rows):
+    """Emit payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_payout_7(rows):
+    """Load payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_payout_8(rows):
+    """Render payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/alpha/quota_8.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def rank_quota_0(rows):
+    """Rank quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_quota_1(rows):
+    """Tally quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_quota_2(rows):
+    """Audit quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_quota_3(rows):
+    """Emit quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_quota_4(rows):
+    """Load quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_quota_5(rows):
+    """Render quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_quota_6(rows):
+    """Collect quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_quota_7(rows):
+    """Summarise quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_quota_8(rows):
+    """Validate quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/alpha/rebate_4.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def validate_rebate_0(rows):
+    """Validate rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_rebate_1(rows):
+    """Expand rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_rebate_2(rows):
+    """Merge rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_rebate_3(rows):
+    """Filter rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_rebate_4(rows):
+    """Rank rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_rebate_5(rows):
+    """Tally rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_rebate_6(rows):
+    """Audit rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_rebate_7(rows):
+    """Emit rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_rebate_8(rows):
+    """Load rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/alpha/refund_7.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def filter_refund_0(rows):
+    """Filter refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_refund_1(rows):
+    """Rank refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_refund_2(rows):
+    """Tally refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_refund_3(rows):
+    """Audit refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_refund_4(rows):
+    """Emit refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_refund_5(rows):
+    """Load refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_refund_6(rows):
+    """Render refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_refund_7(rows):
+    """Collect refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_refund_8(rows):
+    """Summarise refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/alpha/shipment_6.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def merge_shipment_0(rows):
+    """Merge shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_shipment_1(rows):
+    """Filter shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_shipment_2(rows):
+    """Rank shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_shipment_3(rows):
+    """Tally shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_shipment_4(rows):
+    """Audit shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_shipment_5(rows):
+    """Emit shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_shipment_6(rows):
+    """Load shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_shipment_7(rows):
+    """Render shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_shipment_8(rows):
+    """Collect shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/alpha/tariff_10.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def audit_tariff_0(rows):
+    """Audit tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_tariff_1(rows):
+    """Emit tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_tariff_2(rows):
+    """Load tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_tariff_3(rows):
+    """Render tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_tariff_4(rows):
+    """Collect tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_tariff_5(rows):
+    """Summarise tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_tariff_6(rows):
+    """Validate tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_tariff_7(rows):
+    """Expand tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_tariff_8(rows):
+    """Merge tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/alpha/tenant_3.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def summarise_tenant_0(rows):
+    """Summarise tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_tenant_1(rows):
+    """Validate tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_tenant_2(rows):
+    """Expand tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_tenant_3(rows):
+    """Merge tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_tenant_4(rows):
+    """Filter tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_tenant_5(rows):
+    """Rank tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_tenant_6(rows):
+    """Tally tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_tenant_7(rows):
+    """Audit tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_tenant_8(rows):
+    """Emit tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/alpha/voucher_11.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def emit_voucher_0(rows):
+    """Emit voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_voucher_1(rows):
+    """Load voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_voucher_2(rows):
+    """Render voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_voucher_3(rows):
+    """Collect voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_voucher_4(rows):
+    """Summarise voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_voucher_5(rows):
+    """Validate voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_voucher_6(rows):
+    """Expand voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_voucher_7(rows):
+    """Merge voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_voucher_8(rows):
+    """Filter voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/beta/batch_2.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def collect_batch_0(rows):
+    """Collect batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_batch_1(rows):
+    """Summarise batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_batch_2(rows):
+    """Validate batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_batch_3(rows):
+    """Expand batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_batch_4(rows):
+    """Merge batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_batch_5(rows):
+    """Filter batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_batch_6(rows):
+    """Rank batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_batch_7(rows):
+    """Tally batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_batch_8(rows):
+    """Audit batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/beta/credit_9.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def tally_credit_0(rows):
+    """Tally credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_credit_1(rows):
+    """Audit credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_credit_2(rows):
+    """Emit credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_credit_3(rows):
+    """Load credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_credit_4(rows):
+    """Render credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_credit_5(rows):
+    """Collect credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_credit_6(rows):
+    """Summarise credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_credit_7(rows):
+    """Validate credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_credit_8(rows):
+    """Expand credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/beta/invoice_0.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def load_invoice_0(rows):
+    """Load invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_invoice_1(rows):
+    """Render invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_invoice_2(rows):
+    """Collect invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_invoice_3(rows):
+    """Summarise invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_invoice_4(rows):
+    """Validate invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_invoice_5(rows):
+    """Expand invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_invoice_6(rows):
+    """Merge invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_invoice_7(rows):
+    """Filter invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_invoice_8(rows):
+    """Rank invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/beta/ledger_1.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def render_ledger_0(rows):
+    """Render ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_ledger_1(rows):
+    """Collect ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_ledger_2(rows):
+    """Summarise ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_ledger_3(rows):
+    """Validate ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_ledger_4(rows):
+    """Expand ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_ledger_5(rows):
+    """Merge ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_ledger_6(rows):
+    """Filter ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_ledger_7(rows):
+    """Rank ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_ledger_8(rows):
+    """Tally ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/beta/payout_5.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def expand_payout_0(rows):
+    """Expand payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_payout_1(rows):
+    """Merge payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_payout_2(rows):
+    """Filter payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_payout_3(rows):
+    """Rank payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_payout_4(rows):
+    """Tally payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_payout_5(rows):
+    """Audit payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_payout_6(rows):
+    """Emit payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_payout_7(rows):
+    """Load payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_payout_8(rows):
+    """Render payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/beta/quota_8.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def rank_quota_0(rows):
+    """Rank quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_quota_1(rows):
+    """Tally quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_quota_2(rows):
+    """Audit quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_quota_3(rows):
+    """Emit quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_quota_4(rows):
+    """Load quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_quota_5(rows):
+    """Render quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_quota_6(rows):
+    """Collect quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_quota_7(rows):
+    """Summarise quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_quota_8(rows):
+    """Validate quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/beta/rebate_4.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def validate_rebate_0(rows):
+    """Validate rebate rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_rebate_1(rows):
+    """Expand rebate rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_rebate_2(rows):
+    """Merge rebate rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_rebate_3(rows):
+    """Filter rebate rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_rebate_4(rows):
+    """Rank rebate rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_rebate_5(rows):
+    """Tally rebate rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_rebate_6(rows):
+    """Audit rebate rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_rebate_7(rows):
+    """Emit rebate rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_rebate_8(rows):
+    """Load rebate rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/beta/refund_7.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def filter_refund_0(rows):
+    """Filter refund rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_refund_1(rows):
+    """Rank refund rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_refund_2(rows):
+    """Tally refund rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_refund_3(rows):
+    """Audit refund rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_refund_4(rows):
+    """Emit refund rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_refund_5(rows):
+    """Load refund rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_refund_6(rows):
+    """Render refund rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_refund_7(rows):
+    """Collect refund rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_refund_8(rows):
+    """Summarise refund rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/beta/shipment_6.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def merge_shipment_0(rows):
+    """Merge shipment rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_shipment_1(rows):
+    """Filter shipment rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_shipment_2(rows):
+    """Rank shipment rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_shipment_3(rows):
+    """Tally shipment rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_shipment_4(rows):
+    """Audit shipment rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_shipment_5(rows):
+    """Emit shipment rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_shipment_6(rows):
+    """Load shipment rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_shipment_7(rows):
+    """Render shipment rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_shipment_8(rows):
+    """Collect shipment rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/beta/tariff_10.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def audit_tariff_0(rows):
+    """Audit tariff rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_tariff_1(rows):
+    """Emit tariff rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_tariff_2(rows):
+    """Load tariff rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_tariff_3(rows):
+    """Render tariff rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_tariff_4(rows):
+    """Collect tariff rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_tariff_5(rows):
+    """Summarise tariff rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_tariff_6(rows):
+    """Validate tariff rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_tariff_7(rows):
+    """Expand tariff rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_tariff_8(rows):
+    """Merge tariff rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/beta/tenant_3.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def summarise_tenant_0(rows):
+    """Summarise tenant rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_tenant_1(rows):
+    """Validate tenant rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_tenant_2(rows):
+    """Expand tenant rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_tenant_3(rows):
+    """Merge tenant rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_tenant_4(rows):
+    """Filter tenant rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_tenant_5(rows):
+    """Rank tenant rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_tenant_6(rows):
+    """Tally tenant rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_tenant_7(rows):
+    """Audit tenant rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_tenant_8(rows):
+    """Emit tenant rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/beta/voucher_11.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def emit_voucher_0(rows):
+    """Emit voucher rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_voucher_1(rows):
+    """Load voucher rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_voucher_2(rows):
+    """Render voucher rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_voucher_3(rows):
+    """Collect voucher rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_voucher_4(rows):
+    """Summarise voucher rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_voucher_5(rows):
+    """Validate voucher rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_voucher_6(rows):
+    """Expand voucher rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_voucher_7(rows):
+    """Merge voucher rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_voucher_8(rows):
+    """Filter voucher rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/gamma/batch_2.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def collect_batch_0(rows):
+    """Collect batch rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_batch_1(rows):
+    """Summarise batch rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_batch_2(rows):
+    """Validate batch rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_batch_3(rows):
+    """Expand batch rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_batch_4(rows):
+    """Merge batch rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_batch_5(rows):
+    """Filter batch rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_batch_6(rows):
+    """Rank batch rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_batch_7(rows):
+    """Tally batch rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_batch_8(rows):
+    """Audit batch rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/gamma/credit_9.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def tally_credit_0(rows):
+    """Tally credit rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_credit_1(rows):
+    """Audit credit rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_credit_2(rows):
+    """Emit credit rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_credit_3(rows):
+    """Load credit rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_credit_4(rows):
+    """Render credit rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_credit_5(rows):
+    """Collect credit rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_credit_6(rows):
+    """Summarise credit rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_credit_7(rows):
+    """Validate credit rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_credit_8(rows):
+    """Expand credit rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/gamma/invoice_0.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def load_invoice_0(rows):
+    """Load invoice rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_invoice_1(rows):
+    """Render invoice rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_invoice_2(rows):
+    """Collect invoice rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_invoice_3(rows):
+    """Summarise invoice rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_invoice_4(rows):
+    """Validate invoice rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_invoice_5(rows):
+    """Expand invoice rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_invoice_6(rows):
+    """Merge invoice rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_invoice_7(rows):
+    """Filter invoice rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_invoice_8(rows):
+    """Rank invoice rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/gamma/ledger_1.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def render_ledger_0(rows):
+    """Render ledger rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_ledger_1(rows):
+    """Collect ledger rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_ledger_2(rows):
+    """Summarise ledger rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_ledger_3(rows):
+    """Validate ledger rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_ledger_4(rows):
+    """Expand ledger rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_ledger_5(rows):
+    """Merge ledger rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_ledger_6(rows):
+    """Filter ledger rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_ledger_7(rows):
+    """Rank ledger rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_ledger_8(rows):
+    """Tally ledger rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/gamma/payout_5.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def expand_payout_0(rows):
+    """Expand payout rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_payout_1(rows):
+    """Merge payout rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_payout_2(rows):
+    """Filter payout rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_payout_3(rows):
+    """Rank payout rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_payout_4(rows):
+    """Tally payout rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_payout_5(rows):
+    """Audit payout rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_payout_6(rows):
+    """Emit payout rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_payout_7(rows):
+    """Load payout rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_payout_8(rows):
+    """Render payout rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/gamma/quota_8.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def rank_quota_0(rows):
+    """Rank quota rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_quota_1(rows):
+    """Tally quota rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_quota_2(rows):
+    """Audit quota rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_quota_3(rows):
+    """Emit quota rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_quota_4(rows):
+    """Load quota rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_quota_5(rows):
+    """Render quota rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_quota_6(rows):
+    """Collect quota rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_quota_7(rows):
+    """Summarise quota rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_quota_8(rows):
+    """Validate quota rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/gamma/rebate_4.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def validate_rebate_0(rows):
+    """Validate rebate rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_rebate_1(rows):
+    """Expand rebate rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_rebate_2(rows):
+    """Merge rebate rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_rebate_3(rows):
+    """Filter rebate rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_rebate_4(rows):
+    """Rank rebate rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_rebate_5(rows):
+    """Tally rebate rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_rebate_6(rows):
+    """Audit rebate rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_rebate_7(rows):
+    """Emit rebate rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_rebate_8(rows):
+    """Load rebate rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/gamma/refund_7.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def filter_refund_0(rows):
+    """Filter refund rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_refund_1(rows):
+    """Rank refund rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_refund_2(rows):
+    """Tally refund rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_refund_3(rows):
+    """Audit refund rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_refund_4(rows):
+    """Emit refund rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_refund_5(rows):
+    """Load refund rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_refund_6(rows):
+    """Render refund rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_refund_7(rows):
+    """Collect refund rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_refund_8(rows):
+    """Summarise refund rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/gamma/shipment_6.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def merge_shipment_0(rows):
+    """Merge shipment rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_shipment_1(rows):
+    """Filter shipment rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_shipment_2(rows):
+    """Rank shipment rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_shipment_3(rows):
+    """Tally shipment rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_shipment_4(rows):
+    """Audit shipment rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_shipment_5(rows):
+    """Emit shipment rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_shipment_6(rows):
+    """Load shipment rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_shipment_7(rows):
+    """Render shipment rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_shipment_8(rows):
+    """Collect shipment rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/gamma/tariff_10.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def audit_tariff_0(rows):
+    """Audit tariff rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_tariff_1(rows):
+    """Emit tariff rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_tariff_2(rows):
+    """Load tariff rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_tariff_3(rows):
+    """Render tariff rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_tariff_4(rows):
+    """Collect tariff rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_tariff_5(rows):
+    """Summarise tariff rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_tariff_6(rows):
+    """Validate tariff rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_tariff_7(rows):
+    """Expand tariff rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_tariff_8(rows):
+    """Merge tariff rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/gamma/tenant_3.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def summarise_tenant_0(rows):
+    """Summarise tenant rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_tenant_1(rows):
+    """Validate tenant rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_tenant_2(rows):
+    """Expand tenant rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_tenant_3(rows):
+    """Merge tenant rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_tenant_4(rows):
+    """Filter tenant rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_tenant_5(rows):
+    """Rank tenant rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_tenant_6(rows):
+    """Tally tenant rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_tenant_7(rows):
+    """Audit tenant rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_tenant_8(rows):
+    """Emit tenant rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/pkgs/gamma/voucher_11.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def emit_voucher_0(rows):
+    """Emit voucher rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_voucher_1(rows):
+    """Load voucher rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_voucher_2(rows):
+    """Render voucher rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_voucher_3(rows):
+    """Collect voucher rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_voucher_4(rows):
+    """Summarise voucher rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_voucher_5(rows):
+    """Validate voucher rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_voucher_6(rows):
+    """Expand voucher rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_voucher_7(rows):
+    """Merge voucher rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_voucher_8(rows):
+    """Filter voucher rows for the gamma package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure-forced/workdir/reasonix.toml

@@ -0,0 +1,5 @@
+# Reasonix project configuration.
+
+[agent]
+compact_ratio = 0.005
+soft_compact_ratio = 0.003

benchmarks/e2e/tasks/context-pressure/task.toml

@@ -0,0 +1,4 @@
+prompt = "common/money.py now requires a second argument: fmt_amount(cents, currency). Every call site under pkgs/alpha, pkgs/beta and pkgs/gamma still passes one argument and is broken. Update every call site to pass the currency \"USD\", leaving all other code untouched, so that `python3 check.py` prints OK. The three packages share no files."
+class = "delegation"
+max_steps = 60
+timeout_sec = 900

benchmarks/e2e/tasks/context-pressure/verify.sh

@@ -0,0 +1,14 @@
+# Same migration under an aggressive project compact_ratio (0.5%), an attempt
+# to put the parent under real context pressure — the one mechanism delegation
+# was designed for. It did not work: the agent keeps its session small by
+# writing a script instead of reading, so compaction never engaged and the
+# arms measured the same thing the other shapes did. Kept as an honest record
+# of the attempt, and as a config variant that still exercises the workspace
+# reasonix.toml merge path.
+set -e
+# 36 files across three non-overlapping packages, each needing a real read
+# before any edit. This is the branch size where delegation could pay: the
+# neutral prompt never mentions sub-agents, so an arm that does the work
+# itself is only penalised by the clock.
+python3 check.py
+test -z "$(grep -rn 'fmt_amount([a-z_]*)' pkgs/ || true)"

benchmarks/e2e/tasks/context-pressure/workdir/check.py

@@ -0,0 +1,27 @@
+import importlib, pathlib, sys
+sys.path[:0] = ["common", "."]
+bad = []
+for pkg in ("alpha", "beta", "gamma"):
+    for p in sorted(pathlib.Path("pkgs", pkg).glob("*.py")):
+        if p.stem == "__init__":
+            continue
+        src = p.read_text()
+        if "fmt_amount(" not in src:
+            continue
+        m = importlib.import_module(f"pkgs.{pkg}.{p.stem}")
+        for name in dir(m):
+            fn = getattr(m, name)
+            # Only functions this module defines: fmt_amount is imported into
+            # the namespace and is not one of the call sites under test.
+            if not callable(fn) or name.startswith("_") or getattr(fn, "__module__", "") != m.__name__:
+                continue
+            try:
+                got = fn([{"cents": 1234}])
+            except TypeError as exc:
+                bad.append(f"{pkg}/{p.stem}.{name}: {exc}")
+                continue
+            if got and got[0] not in ("1234", "12.34 USD"):
+                bad.append(f"{pkg}/{p.stem}.{name}: {got[0]}")
+if bad:
+    print("FAIL:"); [print(" ", b) for b in bad[:10]]; sys.exit(1)
+print("OK")

benchmarks/e2e/tasks/context-pressure/workdir/common/money.py

@@ -0,0 +1,3 @@
+def fmt_amount(cents, currency):
+    """Format cents as a currency string, e.g. 1234 -> '12.34 USD'."""
+    return "%d.%02d %s" % (cents // 100, cents % 100, currency)

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/alpha/batch_2.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def collect_batch_0(rows):
+    """Collect batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_batch_1(rows):
+    """Summarise batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_batch_2(rows):
+    """Validate batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_batch_3(rows):
+    """Expand batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_batch_4(rows):
+    """Merge batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_batch_5(rows):
+    """Filter batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_batch_6(rows):
+    """Rank batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_batch_7(rows):
+    """Tally batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_batch_8(rows):
+    """Audit batch rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/alpha/credit_9.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def tally_credit_0(rows):
+    """Tally credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_credit_1(rows):
+    """Audit credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_credit_2(rows):
+    """Emit credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_credit_3(rows):
+    """Load credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_credit_4(rows):
+    """Render credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_credit_5(rows):
+    """Collect credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_credit_6(rows):
+    """Summarise credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_credit_7(rows):
+    """Validate credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_credit_8(rows):
+    """Expand credit rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/alpha/invoice_0.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def load_invoice_0(rows):
+    """Load invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_invoice_1(rows):
+    """Render invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_invoice_2(rows):
+    """Collect invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_invoice_3(rows):
+    """Summarise invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_invoice_4(rows):
+    """Validate invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_invoice_5(rows):
+    """Expand invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_invoice_6(rows):
+    """Merge invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_invoice_7(rows):
+    """Filter invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_invoice_8(rows):
+    """Rank invoice rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/alpha/ledger_1.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def render_ledger_0(rows):
+    """Render ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_ledger_1(rows):
+    """Collect ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_ledger_2(rows):
+    """Summarise ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_ledger_3(rows):
+    """Validate ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_ledger_4(rows):
+    """Expand ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_ledger_5(rows):
+    """Merge ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_ledger_6(rows):
+    """Filter ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_ledger_7(rows):
+    """Rank ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_ledger_8(rows):
+    """Tally ledger rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/alpha/payout_5.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def expand_payout_0(rows):
+    """Expand payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_payout_1(rows):
+    """Merge payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_payout_2(rows):
+    """Filter payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_payout_3(rows):
+    """Rank payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_payout_4(rows):
+    """Tally payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_payout_5(rows):
+    """Audit payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_payout_6(rows):
+    """Emit payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_payout_7(rows):
+    """Load payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_payout_8(rows):
+    """Render payout rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/alpha/quota_8.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def rank_quota_0(rows):
+    """Rank quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_quota_1(rows):
+    """Tally quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_quota_2(rows):
+    """Audit quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_quota_3(rows):
+    """Emit quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_quota_4(rows):
+    """Load quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_quota_5(rows):
+    """Render quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_quota_6(rows):
+    """Collect quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_quota_7(rows):
+    """Summarise quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_quota_8(rows):
+    """Validate quota rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/alpha/rebate_4.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def validate_rebate_0(rows):
+    """Validate rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_rebate_1(rows):
+    """Expand rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_rebate_2(rows):
+    """Merge rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_rebate_3(rows):
+    """Filter rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_rebate_4(rows):
+    """Rank rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_rebate_5(rows):
+    """Tally rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_rebate_6(rows):
+    """Audit rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_rebate_7(rows):
+    """Emit rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_rebate_8(rows):
+    """Load rebate rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/alpha/refund_7.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def filter_refund_0(rows):
+    """Filter refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_refund_1(rows):
+    """Rank refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_refund_2(rows):
+    """Tally refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_refund_3(rows):
+    """Audit refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_refund_4(rows):
+    """Emit refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_refund_5(rows):
+    """Load refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_refund_6(rows):
+    """Render refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_refund_7(rows):
+    """Collect refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_refund_8(rows):
+    """Summarise refund rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/alpha/shipment_6.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def merge_shipment_0(rows):
+    """Merge shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_shipment_1(rows):
+    """Filter shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_shipment_2(rows):
+    """Rank shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_shipment_3(rows):
+    """Tally shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_shipment_4(rows):
+    """Audit shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_shipment_5(rows):
+    """Emit shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_shipment_6(rows):
+    """Load shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_shipment_7(rows):
+    """Render shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_shipment_8(rows):
+    """Collect shipment rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/alpha/tariff_10.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def audit_tariff_0(rows):
+    """Audit tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_tariff_1(rows):
+    """Emit tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_tariff_2(rows):
+    """Load tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_tariff_3(rows):
+    """Render tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_tariff_4(rows):
+    """Collect tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_tariff_5(rows):
+    """Summarise tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_tariff_6(rows):
+    """Validate tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_tariff_7(rows):
+    """Expand tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_tariff_8(rows):
+    """Merge tariff rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/alpha/tenant_3.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def summarise_tenant_0(rows):
+    """Summarise tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_tenant_1(rows):
+    """Validate tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_tenant_2(rows):
+    """Expand tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_tenant_3(rows):
+    """Merge tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_tenant_4(rows):
+    """Filter tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_tenant_5(rows):
+    """Rank tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_tenant_6(rows):
+    """Tally tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_tenant_7(rows):
+    """Audit tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_tenant_8(rows):
+    """Emit tenant rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/alpha/voucher_11.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def emit_voucher_0(rows):
+    """Emit voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_voucher_1(rows):
+    """Load voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_voucher_2(rows):
+    """Render voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_voucher_3(rows):
+    """Collect voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_voucher_4(rows):
+    """Summarise voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_voucher_5(rows):
+    """Validate voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_voucher_6(rows):
+    """Expand voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_voucher_7(rows):
+    """Merge voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_voucher_8(rows):
+    """Filter voucher rows for the alpha package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/beta/batch_2.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def collect_batch_0(rows):
+    """Collect batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_batch_1(rows):
+    """Summarise batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_batch_2(rows):
+    """Validate batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_batch_3(rows):
+    """Expand batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_batch_4(rows):
+    """Merge batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_batch_5(rows):
+    """Filter batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_batch_6(rows):
+    """Rank batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_batch_7(rows):
+    """Tally batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_batch_8(rows):
+    """Audit batch rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/beta/credit_9.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def tally_credit_0(rows):
+    """Tally credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_credit_1(rows):
+    """Audit credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_credit_2(rows):
+    """Emit credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_credit_3(rows):
+    """Load credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_credit_4(rows):
+    """Render credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_credit_5(rows):
+    """Collect credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_credit_6(rows):
+    """Summarise credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_credit_7(rows):
+    """Validate credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_credit_8(rows):
+    """Expand credit rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/beta/invoice_0.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def load_invoice_0(rows):
+    """Load invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_invoice_1(rows):
+    """Render invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_invoice_2(rows):
+    """Collect invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_invoice_3(rows):
+    """Summarise invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_invoice_4(rows):
+    """Validate invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_invoice_5(rows):
+    """Expand invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_invoice_6(rows):
+    """Merge invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_invoice_7(rows):
+    """Filter invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_invoice_8(rows):
+    """Rank invoice rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/beta/ledger_1.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def render_ledger_0(rows):
+    """Render ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_ledger_1(rows):
+    """Collect ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_ledger_2(rows):
+    """Summarise ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_ledger_3(rows):
+    """Validate ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def expand_ledger_4(rows):
+    """Expand ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_ledger_5(rows):
+    """Merge ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_ledger_6(rows):
+    """Filter ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_ledger_7(rows):
+    """Rank ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_ledger_8(rows):
+    """Tally ledger rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/beta/payout_5.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def expand_payout_0(rows):
+    """Expand payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def merge_payout_1(rows):
+    """Merge payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def filter_payout_2(rows):
+    """Filter payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def rank_payout_3(rows):
+    """Rank payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_payout_4(rows):
+    """Tally payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_payout_5(rows):
+    """Audit payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_payout_6(rows):
+    """Emit payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_payout_7(rows):
+    """Load payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_payout_8(rows):
+    """Render payout rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out

benchmarks/e2e/tasks/context-pressure/workdir/pkgs/beta/quota_8.py

@@ -0,0 +1,76 @@
+import sys
+sys.path.insert(0, "common")
+from money import fmt_amount
+
+
+def rank_quota_0(rows):
+    """Rank quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def tally_quota_1(rows):
+    """Tally quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def audit_quota_2(rows):
+    """Audit quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def emit_quota_3(rows):
+    """Emit quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def load_quota_4(rows):
+    """Load quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def render_quota_5(rows):
+    """Render quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def collect_quota_6(rows):
+    """Collect quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out
+
+def summarise_quota_7(rows):
+    """Summarise quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(fmt_amount(value))
+    return out
+
+def validate_quota_8(rows):
+    """Validate quota rows for the beta package."""
+    out = []
+    for row in rows:
+        value = int(row.get("cents", 0))
+        out.append(str(value))
+    return out