Operationalize Product E2E accounting, tracing, and scheduling (#17009)

## Thinking Path

> - Paperclip manages agents and the work they perform.
> - Product E2E tests exercise real agents, tools, setup and cleanup.
> - Repeated runs need retained costs and traces, including failed
attempts.
> - A passing retry must not hide earlier spending or feedback.
> - Recurring work also needs admission limits, private reports and
failure detection.
> - This change supplies those controls while keeping paid activation
behind existing gates.

## Linked Issues or Issue Description

Refs #16996 and #17158. This is the consolidated landing of the reviewed
eval operations stack: #17019, #17024, #17025, #17027, #17030, #17033,
#17035, #17038, #17043, #17044, #17048, #17050, #17051, #17092, #17096,
#17100, #17107, #17109, #17112, #17115, #17117, #17121, #17123, #17127,
#17130, #17133, #17134, #17137, #17140, #17143, #17154. The repository
permits squash merges only. A local rehearsal showed that squashing each
slice into master causes repeated conflicts in dependent slices. This PR
preserves their commits and lands their combined implementation in one
reviewed integration. Superseded slices will close after this merge.

## What Changed

- Retain every attempt's cost receipt, including setup, failures,
interruptions and retries. Separate reported amounts, estimates, missing
costs and reserved capacity in reports and dashboards.
- Add bounded request admission, exact model pricecards, gateway error
accounting, cache policy and reconciliation evidence. Refuse unsupported
routes and requests that cannot fit the allowance.
- Integrate Braintrust gateway traces and OTLP correlation, with secret
filtering and experiment imports. Record phase timing, including setup,
feedback capture and cleanup.
- Collect complaint and suggestion evidence after each attempt,
including recovery after failures. Retain explicit review dispositions
independently from the product grade.
- Add gated daily and weekly selections, measured forecasts,
setup/readiness checks, wall-time limits and retained monitor
notifications. Include declared non-model overhead in admission while
reporting the existing subscription separately.
- Keep recurring history private, bound uploads and retention, and use
isolated archive environments. Keep public publication an explicit
operation. Report and publication jobs install only the committed
lockfile, with scripts disabled and isolated stores; stale pins fail
closed.
- Integrate current master, preserve its Product E2E journey billing and
privacy checks, and test that shared setup receipts do not double-count
estimated agent usage. Preserve upstream fixture repairs.

## Verification

- Complete integration baseline
`0649a5ce7544ab20825c2183d2f421157db49f24` includes master
`a3e1d915a7110a4e115b46396a3f79e6dfb4d05e` and every original stack head
as ancestors.
- On that integration baseline, `pnpm test:e2e:runner:unit`: 4,012
Vitest tests passed, two skipped, across 193 files; all 137 Node
source-contract tests passed.
- Focused billing and Product E2E journey contract checks: 24 tests
passed. They cover estimates, unknown receipts, single-owner setup
costs, browser-only execution and private publication guards.
- Monitor and workflow wiring: all 96 Node tests passed. `node
scripts/check-token-gates.mjs`: all gates clean.
- `pnpm test:e2e:runner:typecheck` passes after the standard Runner
TypeScript build refreshed local declarations. The first attempt
rejected the new master `runner_prepared_launch` union member because
this checkout retained an older generated declaration; the source union
already contained that member.
- Current head `492b0708a1c531a023d9ac10f0f3dc6383cc1754` removes
dependency re-resolution from archive-authorized reporting jobs after
the security scan flagged it. All 15 workflow-security tests pass after
updating the old two-install assertion.
- Hosted [CI run
39965460180](https://github.com/paperclipai/paperclip/actions/runs/39965460180)
passes on the current repaired head, including typecheck, build, general
tests, Runner checks, browser shards and canary dry run. Greptile is 5/5
on this exact head with no unresolved threads. The security scan passes
after the fixed lockfile-resolution thread was resolved.
- Paperclip Review returned a terminal neutral check but an incomplete
0-file assessment on the repaired head: its platform blocked both diff
responses as prompt-injection content. This is not a successful code
review. No bypass or fabricated pass was attempted; current-head
Greptile, security and hosted CI are independent gates.
- No paid test, reservation release or recurring-run activation
accompanies this landing. Live route qualification and invoice
reconciliation remain separate evidence.

<details>
<summary>Retained earlier validation failures</summary>

Earlier broad local runs had two 15-second test timeouts (CLI poll
cadence and Retry validation), one embedded-database setup timeout, and
later PostgreSQL semaphore exhaustion. The exact timed-out tests passed
separately without larger timeouts; the broad-run causes were not
established. Those local failures remain distinct from subsequent hosted
CI results. The independent #17158 fix records its Muse fixture
collision, its UUID correction and hosted verification. Local Muse
execution was also blocked by macOS embedded-PostgreSQL startup. No
historical failure is treated as a successful paid qualification.

</details>

## Risks

- Admission is a local control, not a provider invoice cap. Missing
provider receipts or resource charges retain unknown amounts and holds;
estimates do not become billed dollars.
- The bounded path admits only documented local suites and provider
routes. Ordinary legacy or separate Runner protocol campaigns have
different controls. Merging this code does not qualify additional
routes.
- Recurrence still needs the existing enable gates and current
qualification/allowance evidence. Archive permissions and resources must
match the documented private-environment contract.
- Legacy reports may lack complete attempt or phase evidence. Reports
preserve that limitation and do not infer zero usage from missing data.

## Model Used

OpenAI GPT-6 through Codex, with reasoning, repository tools and code
execution. The exact deployment variant and context-window size are not
exposed by this session.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass (targeted checks;
full-suite host limitation disclosed above)
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>

.github/infra/runner-e2e-private-history.yml

@@ -0,0 +1,117 @@
+AWSTemplateFormatVersion: '2010-09-09'
+Description: Private bounded Paperclip eval evidence and reports; no CDN reader
+Parameters:
+  BucketName:
+    Type: String
+  GitHubRepository:
+    Type: String
+    Default: paperclipai/paperclip
+  GitHubOidcProviderArn:
+    Type: String
+Resources:
+  PrivateHistoryBucket:
+    Type: AWS::S3::Bucket
+    DeletionPolicy: Retain
+    UpdateReplacePolicy: Retain
+    Properties:
+      BucketName: !Ref BucketName
+      PublicAccessBlockConfiguration:
+        BlockPublicAcls: true
+        IgnorePublicAcls: true
+        BlockPublicPolicy: true
+        RestrictPublicBuckets: true
+      OwnershipControls:
+        Rules:
+          - ObjectOwnership: BucketOwnerEnforced
+      VersioningConfiguration:
+        Status: Enabled
+      BucketEncryption:
+        ServerSideEncryptionConfiguration:
+          - ServerSideEncryptionByDefault:
+              SSEAlgorithm: AES256
+      LifecycleConfiguration:
+        Rules:
+          - Id: BoundedEvalRetentionV1
+            Status: Enabled
+            Prefix: runner-e2e-private/bounded-v1/
+            ExpirationInDays: 30
+            NoncurrentVersionExpiration:
+              NoncurrentDays: 1
+            AbortIncompleteMultipartUpload:
+              DaysAfterInitiation: 1
+          - Id: BoundedEvalDeleteMarkersV1
+            Status: Enabled
+            Prefix: runner-e2e-private/bounded-v1/
+            ExpiredObjectDeleteMarker: true
+  PrivateHistoryBucketPolicy:
+    Type: AWS::S3::BucketPolicy
+    Properties:
+      Bucket: !Ref PrivateHistoryBucket
+      PolicyDocument:
+        Version: '2012-10-17'
+        Statement:
+          - Sid: DenyInsecureTransport
+            Effect: Deny
+            Principal: '*'
+            Action: s3:*
+            Resource:
+              - !GetAtt PrivateHistoryBucket.Arn
+              - !Sub '${PrivateHistoryBucket.Arn}/*'
+            Condition:
+              Bool:
+                aws:SecureTransport: 'false'
+          - Sid: DenyUnconditionalWrites
+            Effect: Deny
+            Principal: '*'
+            Action: s3:PutObject
+            Resource: !Sub '${PrivateHistoryBucket.Arn}/runner-e2e-private/bounded-v1/*'
+            Condition:
+              'Null':
+                s3:if-none-match: 'true'
+  PrivateHistoryRole:
+    Type: AWS::IAM::Role
+    Properties:
+      RoleName: paperclip-runner-e2e-private-history-github
+      MaxSessionDuration: 3600
+      AssumeRolePolicyDocument:
+        Version: '2012-10-17'
+        Statement:
+          - Effect: Allow
+            Principal:
+              Federated: !Ref GitHubOidcProviderArn
+            Action: sts:AssumeRoleWithWebIdentity
+            Condition:
+              StringEquals:
+                token.actions.githubusercontent.com:aud: sts.amazonaws.com
+                token.actions.githubusercontent.com:sub:
+                  - !Sub 'repo:${GitHubRepository}:environment:runner-e2e-private-paid'
+                  - !Sub 'repo:${GitHubRepository}:environment:runner-e2e-private-history'
+      Policies:
+        - PolicyName: private-eval-artifacts
+          PolicyDocument:
+            Version: '2012-10-17'
+            Statement:
+              - Sid: VerifyPrivateRetention
+                Effect: Allow
+                Action:
+                  - s3:GetBucketVersioning
+                  - s3:GetLifecycleConfiguration
+                  - s3:GetBucketObjectLockConfiguration
+                  - s3:GetReplicationConfiguration
+                  - s3:GetBucketPublicAccessBlock
+                  - s3:GetBucketOwnershipControls
+                  - s3:GetBucketPolicy
+                Resource: !GetAtt PrivateHistoryBucket.Arn
+              - Sid: RetainAndReadPrivateArtifacts
+                Effect: Allow
+                Action:
+                  - s3:GetObject
+                  - s3:PutObject
+                Resource: !Sub '${PrivateHistoryBucket.Arn}/runner-e2e-private/bounded-v1/*'
+Outputs:
+  Bucket:
+    Value: !Ref PrivateHistoryBucket
+  RoleArn:
+    Value: !GetAtt PrivateHistoryRole.Arn
+  Region:
+    Value: !Ref AWS::Region

.github/workflows/pr-trusted.yml

@@ -119,7 +119,7 @@ jobs:
         run: node "$CI_NODE_TEST" ./scripts/__tests__/e2e-shard.test.mjs
 
       - name: Test release verify workflow wiring
-        run: node "$CI_NODE_TEST" ./scripts/__tests__/release-verify-workflow.test.mjs ./scripts/__tests__/prepare-runner-release-image.test.mjs ./scripts/cloud-source-verification.test.mjs ./scripts/standard-image-contract.test.mjs
+        run: node "$CI_NODE_TEST" ./scripts/__tests__/release-verify-workflow.test.mjs ./scripts/__tests__/eval-schedule-monitor.test.mjs ./scripts/__tests__/prepare-runner-release-image.test.mjs ./scripts/cloud-source-verification.test.mjs ./scripts/standard-image-contract.test.mjs
 
       - name: Test standalone package build concurrency
         run: node "$CI_NODE_TEST" ./scripts/__tests__/build-standalone-concurrency.test.mjs

.github/workflows/runner-full-stack-e2e.yml

@@ -1,10 +1,17 @@
 name: Runner Full-Stack E2E
+run-name: Runner Full-Stack E2E / ${{ github.event.schedule || inputs.cadence || 'manual' }}
 
 on:
   schedule:
-    - cron: "47 8 * * 0"
+    - cron: "47 8 * * *"
+    - cron: "47 9 * * 0"
   workflow_dispatch:
     inputs:
+      cadence:
+        description: "Bounded daily ($20) or weekly ($100) selection; manual keeps explicit selectors"
+        type: choice
+        options: [manual, daily, weekly]
+        default: manual
       target_branch:
         description: "Branch in paperclipai/paperclip to test; the trusted workflow still runs from master"
         type: string
@@ -55,7 +62,7 @@ concurrency:
 jobs:
   authorize:
     name: Authorize paid campaign
-    if: github.event_name != 'schedule' || vars.RUNNER_FULL_STACK_E2E_NIGHTLY_ENABLED == 'true'
+    if: github.event_name != 'schedule' || (vars.RUNNER_FULL_STACK_E2E_NIGHTLY_ENABLED == 'true' && vars.RUNNER_FULL_STACK_E2E_OPERATIONS_ENABLED == 'true')
     runs-on: ubuntu-latest
     timeout-minutes: 5
     permissions:
@@ -115,14 +122,25 @@ jobs:
           GH_TOKEN: ${{ github.token }}
           REPOSITORY: ${{ github.repository }}
           TARGET_BRANCH: ${{ inputs.target_branch || github.event.repository.default_branch }}
+          DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
+          EVENT_NAME: ${{ github.event_name }}
+          EVAL_CADENCE: ${{ inputs.cadence || 'manual' }}
         run: |
           set -euo pipefail
           if [ -z "$TARGET_BRANCH" ] || [[ "$TARGET_BRANCH" == refs/* ]]; then
             echo "target_branch must name a branch in this repository without a refs/ prefix." >&2
             exit 1
           fi
-          encoded_branch="$(jq -rn --arg branch "$TARGET_BRANCH" '$branch | @uri')"
-          target_sha="$(gh api -X GET "repos/$REPOSITORY/branches/$encoded_branch" --jq .commit.sha)"
+          if [ "$EVENT_NAME" = schedule ] || [ "$EVAL_CADENCE" != manual ]; then
+            if [ "$TARGET_BRANCH" != "$DEFAULT_BRANCH" ]; then
+              echo "Bounded campaigns require the workflow's default-branch commit." >&2
+              exit 1
+            fi
+            target_sha="$GITHUB_SHA"
+          else
+            encoded_branch="$(jq -rn --arg branch "$TARGET_BRANCH" '$branch | @uri')"
+            target_sha="$(gh api -X GET "repos/$REPOSITORY/branches/$encoded_branch" --jq .commit.sha)"
+          fi
           if ! [[ "$target_sha" =~ ^[0-9a-f]{40}$ ]]; then
             echo "The requested repository branch did not resolve to a commit." >&2
             exit 1
@@ -135,12 +153,23 @@ jobs:
         id: runner
         env:
           AWS_PAID_RUNNER_ENABLED: ${{ vars.RUNNER_E2E_AWS_ENABLED }}
+          EVENT_NAME: ${{ github.event_name }}
+          EVAL_CADENCE: ${{ inputs.cadence || 'manual' }}
+          REPOSITORY_PRIVATE: ${{ github.event.repository.private }}
         run: |
           set -euo pipefail
           github_runner='ubuntu-latest'
           aws_runner='runs-on/fleet=paperclip-public-pr-x64/env=public-ci'
+          bounded=false
+          if [ "$EVENT_NAME" = schedule ] || [ "$EVAL_CADENCE" != manual ]; then
+            if [ "$REPOSITORY_PRIVATE" != false ]; then
+              echo 'Bounded campaigns require a public repository and standard GitHub-hosted compute.' >&2
+              exit 1
+            fi
+            bounded=true
+          fi
 
-          if [ "$AWS_PAID_RUNNER_ENABLED" = true ]; then
+          if [ "$AWS_PAID_RUNNER_ENABLED" = true ] && [ "$bounded" = false ]; then
             {
               echo "runner=$aws_runner"
               echo "max_parallel_default=100"
@@ -155,7 +184,7 @@ jobs:
               echo "max_parallel_limit=57"
               echo "playwright_channel="
             } >> "$GITHUB_OUTPUT"
-            echo '::notice title=Paid runner routing::RUNNER_E2E_AWS_ENABLED is not true; using the proven GitHub-hosted runner'
+            echo '::notice title=Paid runner routing::Using a standard GitHub-hosted runner'
           fi
 
   target_lock:
@@ -200,6 +229,10 @@ jobs:
           fi
           echo "sha256=$(sha256sum pnpm-lock.yaml | cut -d ' ' -f 1)" >> "$GITHUB_OUTPUT"
 
+      - name: Bound scheduled lockfile upload
+        if: github.event_name == 'schedule' || (inputs.cadence != '' && inputs.cadence != 'manual')
+        run: node tests/runner-e2e/artifact-budget.mjs check lock pnpm-lock.yaml
+
       - name: Upload resolved target lockfile
         id: upload
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
@@ -212,13 +245,15 @@ jobs:
   catalog:
     name: Validate catalog and select cells
     needs: [authorize, target_lock]
-    if: github.event_name != 'schedule' || vars.RUNNER_FULL_STACK_E2E_NIGHTLY_ENABLED == 'true'
+    if: github.event_name != 'schedule' || (vars.RUNNER_FULL_STACK_E2E_NIGHTLY_ENABLED == 'true' && vars.RUNNER_FULL_STACK_E2E_OPERATIONS_ENABLED == 'true')
     runs-on: ubuntu-latest
     timeout-minutes: 10
     permissions:
       contents: read
     outputs:
       matrix: ${{ steps.catalog.outputs.matrix }}
+      operations_cadence: ${{ steps.catalog.outputs.operations_cadence }}
+      operating_overhead: ${{ steps.catalog.outputs.operating_overhead }}
       needs_daytona: ${{ steps.catalog.outputs.needs_daytona }}
       needs_runner_typescript: ${{ steps.catalog.outputs.needs_runner_typescript }}
       needs_native_binaries: ${{ steps.catalog.outputs.needs_native_binaries }}
@@ -281,6 +316,13 @@ jobs:
         id: catalog
         env:
           EVENT_NAME: ${{ github.event_name }}
+          EVAL_EVENT: ${{ github.event_name }}
+          EVAL_SCHEDULE: ${{ github.event.schedule }}
+          EVAL_CADENCE: ${{ inputs.cadence || 'manual' }}
+          EVAL_OPERATIONS_ENABLED: ${{ vars.RUNNER_FULL_STACK_E2E_OPERATIONS_ENABLED }}
+          EVAL_OPERATING_OVERHEAD_JSON: ${{ vars.RUNNER_E2E_OPERATING_OVERHEAD_JSON }}
+          EVAL_TEST_RUNNER: ${{ needs.authorize.outputs.test_runner }}
+          TARGET_SHA: ${{ needs.authorize.outputs.target_sha }}
           SELECT_ALL: ${{ inputs.all }}
           SELECT_SUITE: ${{ inputs.suite }}
           SELECT_GROUP: ${{ inputs.group }}
@@ -293,6 +335,31 @@ jobs:
           REQUESTED_MAX_PARALLEL: ${{ inputs.max_parallel }}
         run: |
           set -euo pipefail
+          if [ "$EVAL_EVENT" = schedule ] || [ "$EVAL_CADENCE" != manual ]; then
+            test "$TARGET_SHA" = "$GITHUB_SHA"
+            test -z "${SELECT_SUITE:-}${SELECT_GROUP:-}${SELECT_PROFILE:-}${SELECT_ENVIRONMENT:-}${SELECT_CASE:-}${SELECT_ID:-}"
+            catalog_json="$(node cli/node_modules/tsx/dist/cli.mjs tests/runner-e2e/scheduled-operations.ts matrix)"
+            cadence="$EVAL_CADENCE"
+            if [ "$EVAL_EVENT" = schedule ]; then
+              case "$EVAL_SCHEDULE" in
+                '47 8 * * *') cadence=daily ;;
+                '47 9 * * 0') cadence=weekly ;;
+                *) exit 1 ;;
+              esac
+            fi
+            {
+              echo "operations_cadence=$cadence"
+              echo "operating_overhead=$(jq -c '.overhead' <<< "$catalog_json")"
+              echo "matrix=$(jq -c '{include: .include}' <<< "$catalog_json")"
+              echo "execution_ids=$(jq -c '.executionIds' <<< "$catalog_json")"
+              echo "needs_daytona=false"
+              echo "needs_runner_typescript=true"
+              echo "needs_native_binaries=true"
+              echo "needs_remote_provider_pack=false"
+              echo "max_parallel=1"
+            } >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
           args=(--matrix-json)
           add_values() {
             local flag="$1"
@@ -509,7 +576,7 @@ jobs:
   build_runner_artifacts:
     name: Build reusable runner campaign artifacts
     needs: [authorize, target_lock, catalog]
-    if: github.event_name != 'schedule' || vars.RUNNER_FULL_STACK_E2E_NIGHTLY_ENABLED == 'true'
+    if: github.event_name != 'schedule' || (vars.RUNNER_FULL_STACK_E2E_NIGHTLY_ENABLED == 'true' && vars.RUNNER_FULL_STACK_E2E_OPERATIONS_ENABLED == 'true')
     # Compile native binaries on the same reviewed image used to execute them,
     # avoiding libc/architecture drift between GitHub-hosted and AWS lanes.
     runs-on: ${{ needs.authorize.outputs.test_runner }}
@@ -618,6 +685,10 @@ jobs:
           TARGET_SHA: ${{ needs.authorize.outputs.target_sha }}
         run: echo "name=runner-e2e-build-${TARGET_SHA}-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}" >> "$GITHUB_OUTPUT"
 
+      - name: Bound scheduled build upload
+        if: needs.catalog.outputs.operations_cadence != ''
+        run: node tests/runner-e2e/artifact-budget.mjs check build runner-e2e-build-bundle.tar.gz runner-e2e-build-bundle.tar.gz.sha256
+
       - name: Upload immutable shared campaign outputs
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         with:
@@ -633,7 +704,7 @@ jobs:
     name: Build reusable remote provider pack
     needs:
       [authorize, target_lock, catalog, daytona_image, build_runner_artifacts]
-    if: github.event_name != 'schedule' || vars.RUNNER_FULL_STACK_E2E_NIGHTLY_ENABLED == 'true'
+    if: github.event_name != 'schedule' || (vars.RUNNER_FULL_STACK_E2E_NIGHTLY_ENABLED == 'true' && vars.RUNNER_FULL_STACK_E2E_OPERATIONS_ENABLED == 'true')
     runs-on: ubuntu-latest
     timeout-minutes: 15
     permissions:
@@ -769,6 +840,7 @@ jobs:
 
   test:
     name: ${{ matrix.executionId }}
+    if: needs.catalog.outputs.operations_cadence == ''
     needs:
       [
         authorize,
@@ -790,7 +862,7 @@ jobs:
       fail-fast: false
       max-parallel: ${{ fromJSON(needs.catalog.outputs.max_parallel) }}
       matrix: ${{ fromJSON(needs.catalog.outputs.matrix) }}
-    steps:
+    steps: &paid_test_steps
       - name: Reauthorize paid execution before provider access
         env:
           GH_TOKEN: ${{ github.token }}
@@ -962,8 +1034,8 @@ jobs:
           }
           NODE
 
-      - name: Install pinned legacy Claude CLI
-        if: matrix.profileId == 'legacy-claude'
+      - name: Install pinned Claude CLI for setup verification
+        if: matrix.profileId == 'legacy-claude' || matrix.profileId == 'runner-acpx-claude'
         run: |
           npm install --global --omit=dev --ignore-scripts @anthropic-ai/claude-code@2.1.277
           launcher="$(npm root --global)/@anthropic-ai/claude-code/cli-wrapper.cjs"
@@ -1012,7 +1084,7 @@ jobs:
       # This definition executes only from the authorized default-branch workflow.
       # Provision host policy before credentials reach target-controlled tests.
       - name: Provision Codex sandbox on the disposable trusted runner
-        if: matrix.environmentId == 'local' && (matrix.profileId == 'runner-codex' || matrix.profileId == 'runner-codex-mini' || matrix.profileId == 'runner-acpx-codex' || matrix.profileId == 'runner-codex-subscription')
+        if: matrix.environmentId == 'local' && (needs.catalog.outputs.operations_cadence == 'weekly' || matrix.profileId == 'runner-codex' || matrix.profileId == 'runner-codex-mini' || matrix.profileId == 'runner-acpx-codex' || matrix.profileId == 'runner-codex-subscription')
         run: |
           node --input-type=module <<'NODE'
           import { execFileSync } from "node:child_process";
@@ -1052,7 +1124,60 @@ jobs:
           timeout 120s docker pull "$oracle_image"
           timeout 30s docker image inspect "$oracle_image" --format '{{.Id}}'
 
+      - name: Obtain scoped private history credentials
+        id: private_history_credentials
+        if: needs.catalog.outputs.operations_cadence != ''
+        uses: aws-actions/configure-aws-credentials@e1253824e5c10ff9df46874f81ed3ec929e19cfd # v6
+        with:
+          role-to-assume: ${{ vars.RUNNER_E2E_PRIVATE_HISTORY_AWS_ROLE_ARN }}
+          aws-region: ${{ vars.RUNNER_E2E_PRIVATE_HISTORY_AWS_REGION }}
+          output-env-credentials: false
+          output-credentials: true
+          disable-retry: true
+          action-timeout-s: 60
+
+      - name: Verify private evidence retention before paid execution
+        if: needs.catalog.outputs.operations_cadence != ''
+        env:
+          AWS_ACCESS_KEY_ID: ${{ steps.private_history_credentials.outputs.aws-access-key-id }}
+          AWS_SECRET_ACCESS_KEY: ${{ steps.private_history_credentials.outputs.aws-secret-access-key }}
+          AWS_SESSION_TOKEN: ${{ steps.private_history_credentials.outputs.aws-session-token }}
+          AWS_DEFAULT_REGION: ${{ vars.RUNNER_E2E_PRIVATE_HISTORY_AWS_REGION }}
+          RUNNER_E2E_PRIVATE_HISTORY_S3_BUCKET: ${{ vars.RUNNER_E2E_PRIVATE_HISTORY_S3_BUCKET }}
+        run: node cli/node_modules/tsx/dist/cli.mjs tests/runner-e2e/private-history.ts verify evidence "$GITHUB_RUN_ID" bounded-runner-e2e-evidence
+
+      - name: Prepare bounded campaign before credentials
+        if: needs.catalog.outputs.operations_cadence != ''
+        env:
+          EVAL_EVENT: ${{ github.event_name }}
+          EVAL_SCHEDULE: ${{ github.event.schedule }}
+          EVAL_CADENCE: ${{ needs.catalog.outputs.operations_cadence }}
+          EVAL_OPERATIONS_ENABLED: ${{ vars.RUNNER_FULL_STACK_E2E_OPERATIONS_ENABLED }}
+          EVAL_OPERATING_OVERHEAD_JSON: ${{ needs.catalog.outputs.operating_overhead }}
+          EVAL_TEST_RUNNER: ${{ needs.authorize.outputs.test_runner }}
+          PAPERCLIP_E2E_BRAINTRUST_PROJECT_ID: ${{ vars.RUNNER_E2E_BRAINTRUST_PROJECT_ID }}
+        run: node cli/node_modules/tsx/dist/cli.mjs tests/runner-e2e/scheduled-operations.ts prepare
+
+      - name: Run bounded campaign and retain feedback review
+        if: needs.catalog.outputs.operations_cadence != ''
+        env:
+          BRAINTRUST_API_KEY: ${{ secrets.BRAINTRUST_API_KEY }}
+          PAPERCLIP_E2E_BRAINTRUST_PROJECT_ID: ${{ vars.RUNNER_E2E_BRAINTRUST_PROJECT_ID }}
+          PAPERCLIP_RUNNER_E2E_SOURCE_SHA: ${{ needs.authorize.outputs.target_sha }}
+          PAPERCLIP_RUNNER_E2E_SOURCE_REF: ${{ needs.authorize.outputs.target_ref }}
+          PAPERCLIP_PLAYWRIGHT_CHANNEL: ${{ needs.authorize.outputs.playwright_channel }}
+        run: |
+          set +e
+          args=(--max-parallel 1 --max-automatic-retries 0)
+          while IFS= read -r id; do args+=(--id "$id"); done < <(jq -r '.executionIds[]' "$PAPERCLIP_E2E_OPERATIONS_MANIFEST")
+          pnpm test:e2e:runner -- "${args[@]}"
+          run_status=$?
+          node cli/node_modules/tsx/dist/cli.mjs tests/runner-e2e/scheduled-finalization.ts
+          finalization_status=$?
+          test "$run_status" = 0 && test "$finalization_status" = 0
+
       - name: Run paid cell
+        if: needs.catalog.outputs.operations_cadence == ''
         env:
           OPENAI_API_KEY: ${{ matrix.credentialName == 'OPENAI_API_KEY' && secrets.OPENAI_API_KEY || '' }}
           ANTHROPIC_API_KEY: ${{ matrix.credentialName == 'ANTHROPIC_API_KEY' && secrets.ANTHROPIC_API_KEY || '' }}
@@ -1063,13 +1188,19 @@ jobs:
           PAPERCLIP_E2E_DAYTONA_IMAGE: ${{ needs.daytona_image.outputs.image }}
           PAPERCLIP_RUNNER_REMOTE_PROVIDER_PACK_PATH: ${{ github.workspace }}/packages/paperclip-runner/provider-pack
           PAPERCLIP_E2E_CAMPAIGN_ID: gha-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.executionId }}
+          PAPERCLIP_E2E_ACCOUNTING_CAMPAIGN_ID: gha-${{ github.run_id }}-${{ github.run_attempt }}
           PAPERCLIP_RUNNER_E2E_SOURCE_SHA: ${{ needs.authorize.outputs.target_sha }}
           PAPERCLIP_RUNNER_E2E_SOURCE_REF: ${{ needs.authorize.outputs.target_ref }}
           PAPERCLIP_PLAYWRIGHT_CHANNEL: ${{ needs.authorize.outputs.playwright_channel }}
         run: pnpm test:e2e:runner -- --id "${{ matrix.executionId }}"
 
+      - name: Stage bounded campaign evidence
+        id: stage_evidence
+        if: always() && needs.catalog.outputs.operations_cadence != ''
+        run: node tests/runner-e2e/artifact-budget.mjs stage evidence tests/runner-e2e/results bounded-runner-e2e-evidence
+
       - name: Upload access-controlled packaged cell evidence
-        if: always()
+        if: always() && needs.catalog.outputs.operations_cadence == ''
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         with:
           name: runner-e2e-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.executionId }}
@@ -1077,10 +1208,41 @@ jobs:
           retention-days: 30
           if-no-files-found: error
 
+      - name: Retain bounded campaign evidence in private AWS storage
+        if: always() && needs.catalog.outputs.operations_cadence != '' && steps.private_history_credentials.outcome == 'success'
+        env:
+          AWS_ACCESS_KEY_ID: ${{ steps.private_history_credentials.outputs.aws-access-key-id }}
+          AWS_SECRET_ACCESS_KEY: ${{ steps.private_history_credentials.outputs.aws-secret-access-key }}
+          AWS_SESSION_TOKEN: ${{ steps.private_history_credentials.outputs.aws-session-token }}
+          AWS_DEFAULT_REGION: ${{ vars.RUNNER_E2E_PRIVATE_HISTORY_AWS_REGION }}
+          RUNNER_E2E_PRIVATE_HISTORY_S3_BUCKET: ${{ vars.RUNNER_E2E_PRIVATE_HISTORY_S3_BUCKET }}
+        run: node cli/node_modules/tsx/dist/cli.mjs tests/runner-e2e/private-history.ts upload evidence "$GITHUB_RUN_ID" bounded-runner-e2e-evidence
+
+      - name: Enforce complete bounded evidence retention
+        if: always() && needs.catalog.outputs.operations_cadence != '' && steps.stage_evidence.outputs.complete != 'true'
+        run: exit 1
+
+  test_recurring:
+    name: ${{ matrix.executionId }}
+    if: needs.catalog.outputs.operations_cadence != '' && needs.authorize.outputs.target_sha == github.sha && github.ref == format('refs/heads/{0}', github.event.repository.default_branch)
+    needs: [authorize, target_lock, catalog, daytona_image, build_runner_artifacts, build_remote_provider_pack]
+    runs-on: ${{ needs.authorize.outputs.test_runner }}
+    timeout-minutes: ${{ matrix.timeoutMinutes }}
+    permissions:
+      contents: read
+      id-token: write
+    environment:
+      name: runner-e2e-private-paid
+    strategy:
+      fail-fast: false
+      max-parallel: ${{ fromJSON(needs.catalog.outputs.max_parallel) }}
+      matrix: ${{ fromJSON(needs.catalog.outputs.matrix) }}
+    steps: *paid_test_steps
+
   report:
     name: Merge and enforce campaign result
-    if: always() && !cancelled() && needs.catalog.result == 'success'
-    needs: [authorize, catalog, daytona_image, test]
+    if: always() && !cancelled() && needs.catalog.result == 'success' && github.ref == format('refs/heads/{0}', github.event.repository.default_branch)
+    needs: [authorize, catalog, daytona_image, test, test_recurring]
     outputs:
       history_source_ready: ${{ steps.history_source_ready.outputs.ready }}
     runs-on: ubuntu-latest
@@ -1088,6 +1250,9 @@ jobs:
     permissions:
       actions: read
       contents: read
+      id-token: write
+    environment:
+      name: runner-e2e-private-history
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
         with:
@@ -1107,15 +1272,8 @@ jobs:
         with:
           version: 9.15.4
 
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
-        with:
-          node-version: 24
-          cache: pnpm
-
-      # Resolve from this trusted checkout only. Never use the target branch's
-      # lockfile or install scripts in the publication job.
-      - run: pnpm install --lockfile-only --ignore-scripts --no-frozen-lockfile
-      - run: pnpm install --frozen-lockfile
+      - name: Install pinned reporting dependencies
+        run: pnpm install --frozen-lockfile --ignore-scripts --store-dir "${{ runner.temp }}/eval-report-store"
 
       - name: Resolve workflow job attempts
         env:
@@ -1138,6 +1296,7 @@ jobs:
 
       - name: Download cell evidence
         id: download_evidence
+        if: needs.catalog.outputs.operations_cadence == ''
         continue-on-error: true
         uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
         with:
@@ -1146,15 +1305,37 @@ jobs:
           merge-multiple: false
 
       - name: Retry cell evidence download after transport failure
-        if: steps.download_evidence.outcome == 'failure'
+        if: needs.catalog.outputs.operations_cadence == '' && steps.download_evidence.outcome == 'failure'
         uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
         with:
           pattern: runner-e2e-${{ github.run_id }}-*-*
           path: downloaded-runner-e2e
           merge-multiple: false
 
+      - name: Obtain scoped private history credentials
+        id: private_history_credentials
+        if: needs.catalog.outputs.operations_cadence != ''
+        uses: aws-actions/configure-aws-credentials@e1253824e5c10ff9df46874f81ed3ec929e19cfd # v6
+        with:
+          role-to-assume: ${{ vars.RUNNER_E2E_PRIVATE_HISTORY_AWS_ROLE_ARN }}
+          aws-region: ${{ vars.RUNNER_E2E_PRIVATE_HISTORY_AWS_REGION }}
+          output-env-credentials: false
+          output-credentials: true
+          disable-retry: true
+          action-timeout-s: 60
+
+      - name: Download private bounded campaign evidence
+        if: needs.catalog.outputs.operations_cadence != ''
+        env:
+          AWS_ACCESS_KEY_ID: ${{ steps.private_history_credentials.outputs.aws-access-key-id }}
+          AWS_SECRET_ACCESS_KEY: ${{ steps.private_history_credentials.outputs.aws-secret-access-key }}
+          AWS_SESSION_TOKEN: ${{ steps.private_history_credentials.outputs.aws-session-token }}
+          AWS_DEFAULT_REGION: ${{ vars.RUNNER_E2E_PRIVATE_HISTORY_AWS_REGION }}
+          RUNNER_E2E_PRIVATE_HISTORY_S3_BUCKET: ${{ vars.RUNNER_E2E_PRIVATE_HISTORY_S3_BUCKET }}
+        run: node cli/node_modules/tsx/dist/cli.mjs tests/runner-e2e/private-history.ts download evidence "$GITHUB_RUN_ID" "downloaded-runner-e2e/runner-e2e-$GITHUB_RUN_ID-1-scheduled-campaign"
+
       - name: Select latest workflow attempt per cell
-        if: always()
+        if: always() && needs.catalog.outputs.operations_cadence == ''
         env:
           PAPERCLIP_RUNNER_E2E_ARTIFACT_ROOT: ${{ github.workspace }}/downloaded-runner-e2e
           PAPERCLIP_RUNNER_E2E_SELECTED_ROOT: ${{ github.workspace }}/selected-runner-e2e
@@ -1164,6 +1345,25 @@ jobs:
           PAPERCLIP_RUNNER_E2E_SOURCE_REF: ${{ needs.authorize.outputs.target_ref }}
         run: node cli/node_modules/tsx/dist/cli.mjs tests/runner-e2e/select-rerun-artifacts.ts
 
+      - name: Preserve bounded campaign evidence and journal
+        if: always() && needs.catalog.outputs.operations_cadence != ''
+        env:
+          RUN_ID: ${{ github.run_id }}
+        run: |
+          set -euo pipefail
+          artifact="downloaded-runner-e2e/runner-e2e-$RUN_ID-1-scheduled-campaign"
+          directory="$GITHUB_WORKSPACE/selected-runner-e2e/runner-e2e-$RUN_ID-1-scheduled-campaign/scheduled"
+          echo "PAPERCLIP_E2E_OPERATIONS_LEDGER=$directory/ledger.jsonl" >> "$GITHUB_ENV"
+          test -d "$artifact"
+          mkdir -p selected-runner-e2e
+          cp -R "$artifact" selected-runner-e2e/
+          if [ -f "$directory/feedback-review.json" ]; then
+            echo "PAPERCLIP_E2E_FEEDBACK_REVIEW=$directory/feedback-review.json" >> "$GITHUB_ENV"
+          fi
+          if [ -f "$directory/experiment-receipt.json" ]; then
+            echo "PAPERCLIP_E2E_BRAINTRUST_EXPERIMENT=$directory/experiment-receipt.json" >> "$GITHUB_ENV"
+          fi
+
       - name: Collect blob reports
         run: |
           set -euo pipefail
@@ -1188,21 +1388,34 @@ jobs:
           PAPERCLIP_RUNNER_E2E_REPORT_ROOT: ${{ github.workspace }}/selected-runner-e2e
           PAPERCLIP_RUNNER_E2E_REPORT_OUT: ${{ github.workspace }}/runner-e2e-merged-report/normalized
           PAPERCLIP_RUNNER_E2E_EXPECTED_IDS: ${{ needs.catalog.outputs.execution_ids }}
-          PAPERCLIP_E2E_CAMPAIGN_ID: gha-${{ github.run_id }}-${{ github.run_attempt }}
+          PAPERCLIP_E2E_CAMPAIGN_ID: ${{ needs.catalog.outputs.operations_cadence != '' && format('gha-{0}-1-scheduled-campaign', github.run_id) || format('gha-{0}-{1}', github.run_id, github.run_attempt) }}
           PAPERCLIP_RUNNER_E2E_SOURCE_SHA: ${{ needs.authorize.outputs.target_sha }}
           PAPERCLIP_RUNNER_E2E_SOURCE_REF: ${{ needs.authorize.outputs.target_ref }}
-          PAPERCLIP_RUNNER_E2E_HISTORY_PUBLIC_BASE_URL: ${{ vars.RUNNER_E2E_HISTORY_PUBLIC_BASE_URL }}
+          PAPERCLIP_RUNNER_E2E_HISTORY_PUBLIC_BASE_URL: ${{ needs.catalog.outputs.operations_cadence == '' && vars.RUNNER_E2E_HISTORY_PUBLIC_BASE_URL || '' }}
           PAPERCLIP_RUNNER_E2E_HISTORY_PREFIX: ${{ vars.RUNNER_E2E_HISTORY_PREFIX || 'runner-e2e' }}
+          EVAL_OPERATIONS_CADENCE: ${{ needs.catalog.outputs.operations_cadence }}
         run: |
           set +e
-          pnpm test:e2e:runner:report
+          if [ -n "$EVAL_OPERATIONS_CADENCE" ]; then
+            mkdir -p runner-e2e-merged-report
+            pnpm test:e2e:runner:report > runner-e2e-merged-report/report.log 2>&1
+          else
+            pnpm test:e2e:runner:report
+          fi
           report_status=$?
           set -e
-          cat runner-e2e-merged-report/normalized/summary.md >> "$GITHUB_STEP_SUMMARY"
+          if [ -z "$EVAL_OPERATIONS_CADENCE" ]; then
+            cat runner-e2e-merged-report/normalized/summary.md >> "$GITHUB_STEP_SUMMARY"
+          fi
           exit "$report_status"
 
+      - name: Stage bounded merged report
+        id: stage_report
+        if: always() && needs.catalog.outputs.operations_cadence != ''
+        run: node tests/runner-e2e/artifact-budget.mjs stage report runner-e2e-merged-report bounded-runner-e2e-report
+
       - name: Upload access-controlled merged report
-        if: always()
+        if: always() && needs.catalog.outputs.operations_cadence == ''
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         with:
           name: runner-e2e-report-${{ github.run_id }}-${{ github.run_attempt }}
@@ -1210,6 +1423,33 @@ jobs:
           retention-days: 30
           if-no-files-found: error
 
+      - name: Retain bounded report in private AWS storage
+        id: private_report
+        if: always() && needs.catalog.outputs.operations_cadence != '' && steps.private_history_credentials.outcome == 'success'
+        env:
+          AWS_ACCESS_KEY_ID: ${{ steps.private_history_credentials.outputs.aws-access-key-id }}
+          AWS_SECRET_ACCESS_KEY: ${{ steps.private_history_credentials.outputs.aws-secret-access-key }}
+          AWS_SESSION_TOKEN: ${{ steps.private_history_credentials.outputs.aws-session-token }}
+          AWS_DEFAULT_REGION: ${{ vars.RUNNER_E2E_PRIVATE_HISTORY_AWS_REGION }}
+          RUNNER_E2E_PRIVATE_HISTORY_S3_BUCKET: ${{ vars.RUNNER_E2E_PRIVATE_HISTORY_S3_BUCKET }}
+        run: |
+          node cli/node_modules/tsx/dist/cli.mjs tests/runner-e2e/private-history.ts upload report "$GITHUB_RUN_ID" bounded-runner-e2e-report
+          echo '{"version":1,"privateReportRetained":true}' > private-report-status.json
+          echo 'The recurring campaign report is retained in private AWS storage. See the eval operations runbook for authenticated retrieval.' >> "$GITHUB_STEP_SUMMARY"
+
+      - name: Retain report availability for the schedule monitor
+        if: always() && needs.catalog.outputs.operations_cadence != '' && steps.private_report.outcome == 'success'
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: runner-e2e-report-${{ github.run_id }}-${{ github.run_attempt }}
+          path: private-report-status.json
+          retention-days: 30
+          if-no-files-found: error
+
+      - name: Enforce complete bounded report retention
+        if: always() && needs.catalog.outputs.operations_cadence != '' && steps.stage_report.outputs.complete != 'true'
+        run: exit 1
+
       - name: Verify normalized history source report
         id: history_source_ready
         if: always()
@@ -1225,7 +1465,7 @@ jobs:
   publish_history:
     name: Publish S3 history and Pages bundle with declared screenshots
     needs: [authorize, catalog, report]
-    if: always() && needs.catalog.result == 'success' && needs.report.outputs.history_source_ready == 'true'
+    if: always() && needs.catalog.result == 'success' && needs.catalog.outputs.operations_cadence == '' && needs.report.outputs.history_source_ready == 'true'
     runs-on: ubuntu-latest
     timeout-minutes: 15
     outputs:
@@ -1257,12 +1497,10 @@ jobs:
         with:
           version: 9.15.4
 
-      # Resolve the trusted publication checkout's lockfile without lifecycle
-      # scripts, then install the exact result. This matches the report job's
-      # frozen-install preparation while keeping target-controlled code out of
-      # the AWS credentialed publisher.
-      - run: pnpm install --lockfile-only --ignore-scripts --no-frozen-lockfile
-      - run: pnpm install --frozen-lockfile
+      # Use a job-local store and disable lifecycle scripts throughout install.
+      # OIDC is available to every step, even before the AWS credential exchange.
+      - name: Install pinned publication dependencies
+        run: pnpm install --frozen-lockfile --ignore-scripts --store-dir "${{ runner.temp }}/eval-publisher-store"
 
       - name: Install publisher-only Chromium
         run: pnpm exec playwright install --with-deps --only-shell chromium