## Current remote coverage: final 34-cell drain snapshot

OpenCode/OpenRouter model `deepseek/deepseek-v4.1-flash-1017`; historical Codex results are separate. This is a partial snapshot from [run 40584967834](https://github.com/paperclipai/paperclip/actions/runs/40584967834), not a completed 244-case campaign.

**57 measured scenarios: 6 passed / 51 failed / 187 unrun. 62 attempts: 6 passed / 56 failed.** Initial outcomes remain immutable; latest allowed outcomes determine these exclusive categories.

| Current status | Scenarios |
|---|---:|
| Live passes | 6 |
| Live failures pending reviewed disposition or final correction | 47 |
| Permanently failed after the one correction | 4 |
| Implemented but not yet run | 119 |
| Future: unmerged invitation core prerequisite | 20 |
| Future: explicit external prerequisite missing | 42 |
| Future: incomplete journey or missing public product path | 6 |
| **Total** | **244** |

The 34 completed cells in this run contain three genuine passes and 31 overall failures; all cleanup results passed. At the verified 21:58:36 UTC drain there were zero active cells and 120 unadmitted cells. The run was intentionally stopped because of the shared named-key credential-custody finding, not a fleet queue. Manager-authorized normal cancellation was accepted once at 21:58:53 UTC; the workflow was confirmed completed/cancelled at 21:58:58 UTC. Those 120 consume no ordinal: 119 initial attempts and the comment-reference final correction remain unused. Pending and queued jobs are not measurements. **All new paid starts are held because the shared OpenCode credential-custody risk is not scoped to one case.**

### Six actual current-production-baseline passes

These six passed real end-to-end measurements against production `50b932a142216331b8d476042b454bc123739c40`, using the exact retained source, model and build/native receipts. They are individual passing evidence, not a claim that the entire campaign or all current source definitions qualify.

| Scenario | Actual frozen human query |
|---|---|
| `activity.audit-change` | Who changed the priority of the website task? |
| `agent-chat.reopen-conversation` | Take me back to my conversation with Morgan. |
| `agents.change-manager` | Have Morgan report to Riley from now on. |
| `cli-operations.choose-cli-context` | Show me how to point my terminal at the Acorn company. |
| `cli-operations.create-from-cli` | Give me the CLI command to create a website task for Morgan in Launch. |
| `companies.rename-company` | Rename this company to Acorn Studio. |

### Supported cause classes versus unresolved labels

| Cause class supported by retained evidence | Examples / interpretation |
|---|---|
| Native turn deadline | The six sampled cases listed below reached their canonical query and native run before the 120-second deadline; inner/provider cause unknown. Earlier independently reviewed timeout results retain their own evidence. |
| Mandatory evidence packaging | Sign-in and chat-disabled finals failed because three mandatory files were missing despite 6/6 browser observations. |
| Credential custody / privacy scan | Named OpenRouter-key match in export-document-cli’s provider WAL; two separate unknown-identity database matches. All remain overall failures. |
| Scenario outcome or fixture/UI assertion | Related-work, hire-denied and the saved-correction/continuation waits retain their actual failed assertions; no blanket model attribution. |
| Explicit prerequisite failure | Repair-cost-recording lacks a genuine saved retryable accounting prerequisite; its supported construction remains unresolved. Earlier invitation-guard failures retain the unmerged core dependency. |
| Not yet diagnosed | Unsampled “initial identity response” or “Observed provider run failed” labels are original wait/error messages, not proof of pre-query failure, provider outage, or a shared root cause. |

### Privacy failures remain failures

`cli-operations.export-document-cli` failed the persisted-state privacy scan with an exact match explicitly attributed by the scanner to `OPENROUTER_API_KEY` in an OpenCode database WAL file. The operation that placed it there is unresolved. Its supported-command outcome was already failed; privacy scanning independently preserves the overall failure. Filename-only inspection of the authenticated 35-entry artifact ZIP confirms no matched WAL, database file, or disposable-home tree was packaged. No database payload was inspected. This does not waive the finding or establish that all outputs were safe.

`assistant-connections.decline-consent` and `assistant-connections.revoke-personal-grant` separately failed with exact registered-secret matches in the disposable home database. Those two matched values’ identities remain **unknown**; the newer named-key finding does not retrospectively identify them. Their matched database files are absent from retained report artifacts. No model/provider disclosure cause is established. Full scan protections remain unchanged. Only sanitized summaries and existing allowlisted projections are published; no raw database, credential, transcript, screenshot, or private diagnostic sidecar is included.

### What the sampled failure evidence establishes

A read-only check of six retained results independently bound each actual canonical human comment to its native run: `agents.managed-profile`, `budgets-costs.resolve-budget`, `cases.browse-cases`, `cases.create-case`, `cases.cases-disabled`, and `budgets-costs.spend-breakdown`. All six failed with the recorded native 120-second turn deadline. Their inner/provider cause is unresolved; the evidence does not establish a provider outage. In particular, “initial identity response” is a generic wait label for the first two, **not a pre-query setup failure**. Unsampled rows retain their original messages and unknown stage/cause where proof is missing.

`cases.related-work` reached grading and failed its accessible-work-state-and-links and no-name-inference-or-private-disclosure checks. `cases.close-case` and `cases.handoff-same-task` timed out at their closure/continuation waits; no universal cause is inferred. Repair-cost-recording stopped at an accounting prerequisite, whose fixture-versus-supported-path diagnosis remains open. Setup/hello usage is unknown when unexposed, never assumed zero.

`cases.case-history` retains its overall run failure plus a reporter privacy diagnostic that omitted trace/report ZIP payloads. Only its closed result is projected here; no raw diagnostic or omitted payload is published. `cases.update-case-facts` failed a timeout while waiting for the saved correction’s second phase; no new cause or retry permission is inferred.

### Correction allowance and actual passes

The two new initial CLI passes are `cli-operations.choose-cli-context` (9/9) and `cli-operations.create-from-cli` (8/8), each with genuine source/native/build and same-cell restore proof. Reopen-conversation passed its sole final correction 9/9 with genuine same-run build/native proof; its original overall failure remains retained. Four scenarios exhausted their correction allowance and remain failed: create-backlog, sign-in, chat-disabled, and hire-denied. Sign-in and chat-disabled each passed 6/6 browser observations but failed overall because three mandatory evidence files were missing; neither is a pass. Comment-reference’s final correction remains unmeasured in this snapshot. A reviewed material correction is required for any remaining final attempt; unchanged timeouts get no retry.

Source `d4e8906dc36af80bff50cf5585954f0780b3ed27`, production `50b932a142216331b8d476042b454bc123739c40`, actual AWS lifecycle and embedded database are retained per measurement. Earlier remote production8373 history is preserved separately. The [historical local Codex campaign](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/historical-local-codex-chat-catalog-20261027-158measured-86unrun/) has 17 historical passes / 141 failed / 86 unrun and contributes no current remote pass credit. Six incomplete or blocked journeys remain in the denominator; implementation is not equivalent to verified passage.

### Live passes (6)

- `activity.audit-change`
- `agent-chat.reopen-conversation`
- `agents.change-manager`
- `cli-operations.choose-cli-context`
- `cli-operations.create-from-cli`
- `companies.rename-company`

### Live failures pending reviewed disposition or final correction (47)

- `access.cli-authorization`
- `access.other-company`
- `access.private-resource`
- `activity.agent-feedback`
- `activity.company-overview`
- `activity.find-runs`
- `activity.work-timeline`
- `agent-chat.conference-room`
- `agent-chat.multiple-handoffs`
- `agent-chat.remember-and-follow-up`
- `agent-chat.track-delegated-work`
- `agents.agent-api-key`
- `agents.choose-primary`
- `agents.configure-required-agent`
- `agents.edit-instructions`
- `agents.hire-needs-approval`
- `agents.managed-profile`
- `agents.pause-agent`
- `agents.resume-agent`
- `agents.retire-agent`
- `app-permissions.ask-before-action`
- `app-permissions.new-quarantined-action`
- `app-permissions.read-allowed-write-off`
- `app-permissions.test-as-agent`
- `assistant-connections.decline-consent`
- `assistant-connections.device-login`
- `assistant-connections.revoke-personal-grant`
- `budgets-costs.explain-hard-stop`
- `budgets-costs.repair-cost-recording`
- `budgets-costs.resolve-budget`
- `budgets-costs.set-budget`
- `budgets-costs.spend-breakdown`
- `cases.browse-cases`
- `cases.case-history`
- `cases.cases-disabled`
- `cases.close-case`
- `cases.create-case`
- `cases.handoff-same-task`
- `cases.related-work`
- `cases.update-case-facts`
- `chat-channels.provider-disabled`
- `cli-operations.export-document-cli`
- `inbox-search.archive-without-grant`
- `inbox-search.show-my-work`
- `tasks.ambiguous-task`
- `tasks.comment-with-reference`
- `tasks.delegate-announcement`

### Permanently failed after the one correction (4)

- `access.sign-in`
- `agent-chat.chat-disabled`
- `agents.hire-denied`
- `tasks.create-backlog`

### Implemented but not yet run (119)

- `cli-operations.feedback-bundle`
- `cli-operations.inspect-run-cli`
- `cli-operations.owned-dev-instance`
- `companies.agent-observability`
- `companies.archive-company`
- `companies.configure-decision-model`
- `companies.export-company`
- `companies.fast-responses`
- `companies.import-preview`
- `companies.prompt-injection-guard`
- `companies.switch-company`
- `connection-setup.choose-provider`
- `connection-setup.notion-declined`
- `connection-setup.secure-api-key`
- `connection-setup.unreachable-mcp`
- `developer-labs.component-reference`
- `developer-labs.gated-lab`
- `developer-labs.interaction-fixture`
- `developer-labs.long-thread-performance`
- `documents-artifacts.find-artifact`
- `documents-artifacts.produce-download`
- `documents-artifacts.resolve-feedback`
- `documents-artifacts.revise-delivery`
- `documents-artifacts.write-plan`
- `execution-environments.choose-capable-target`
- `gateways-profiles.connect-client`
- `gateways-profiles.create-gateway`
- `gateways-profiles.inspect-gateway-error`
- `gateways-profiles.rotate-token`
- `goals.align-existing-work`
- `goals.create-goal-tree`
- `goals.explain-purpose`
- `inbox-search.archive-partial-failure`
- `inbox-search.find-design`
- `instance-operations.backup-and-restore`
- `instance-operations.diagnose-health`
- `instance-operations.instance-settings`
- `instance-operations.provision-runtime`
- `instance-operations.restart-service`
- `instance-operations.update-instance`
- `navigation-preferences.find-project-view`
- `onboarding.first-work`
- `plugins.configure-plugin`
- `plugins.disable-plugin`
- `plugins.install-plugin`
- `plugins.use-plugin-tool`
- `projects.archive-project`
- `projects.create-project`
- `projects.project-defaults`
- `projects.project-work`
- `questions-and-approvals.accept-one-proposal`
- `questions-and-approvals.ambiguous-yes`
- `questions-and-approvals.approve-tool-once`
- `questions-and-approvals.decline-tool`
- `questions-and-approvals.defer-and-reopen`
- `questions-and-approvals.duplicate-answer`
- `questions-and-approvals.formal-hire-revision`
- `questions-and-approvals.multi-part-question`
- `questions-and-approvals.necessary-question`
- `questions-and-approvals.reject-and-revise`
- `questions-and-approvals.review-plan`
- `recovery.browser-reconnect`
- `recovery.controller-restart`
- `recovery.explain-stall`
- `recovery.post-stop-message`
- `recovery.retry-exhausted`
- `recovery.source-action`
- `routines.create-daily-brief`
- `routines.manage-other-owner`
- `routines.pause-owned`
- `routines.plugin-managed-routine`
- `routines.read-history`
- `routines.run-now`
- `routines.webhook-trigger`
- `runs-adapters.inspect-failed-run`
- `runs-adapters.list-model-options`
- `runs-adapters.reset-session`
- `secrets.ask-for-plaintext`
- `secrets.configure-company-secret`
- `secrets.least-scope-delivery`
- `secrets.secret-proposal`
- `skills.author-skill`
- `skills.explicit-restriction`
- `skills.find-and-install`
- `skills.fork-read-only`
- `skills.review-update`
- `skills.studio-test`
- `status-cards.archive-card`
- `status-cards.create-card`
- `status-cards.explain-card`
- `status-cards.other-authors-card`
- `status-cards.refresh-card`
- `steering.approval-delivery`
- `steering.discard-queued-message`
- `steering.edit-queued-message`
- `steering.interrupt-with-direction`
- `steering.preserve-draft`
- `steering.queue-follow-up`
- `steering.steer-active`
- `steering.stop-versus-pause`
- `task-coordination.block-on-design`
- `task-coordination.delegate-with-context`
- `task-coordination.independent-review`
- `task-coordination.pause-tree`
- `task-coordination.reject-dependency-cycle`
- `tasks.assignment-conflict`
- `tasks.attachment-brief`
- `tasks.edit-properties`
- `tasks.organize-open-work`
- `tasks.website-task`
- `tasks.website-without-project`
- `teams.configure-team`
- `teams.find-team`
- `teams.install-team`
- `teams.preview-install`
- `workspaces.close-and-reopen`
- `workspaces.inspect-git`
- `workspaces.locate-files`
- `workspaces.preview-service`

### Future: unmerged invitation core prerequisite (20)

- `assistant-connections.consent-read-only`
- `connection-setup.wrong-person-resolves`
- `documents-artifacts.private-download`
- `documents-artifacts.restore-document`
- `inbox-search.archive-done`
- `inbox-search.notification-audience`
- `inbox-search.restore-archive`
- `inbox-search.show-decisions`
- `navigation-preferences.broken-link`
- `navigation-preferences.dismiss-announcement`
- `navigation-preferences.edit-profile`
- `navigation-preferences.quick-search`
- `navigation-preferences.sidebar-order`
- `projects.private-project`
- `projects.share-project`
- `questions-and-approvals.wrong-reviewer`
- `secrets.personal-secret`
- `tasks.completion-with-gate`
- `tasks.private-task`
- `tasks.share-private-task`

### Future: explicit external prerequisite missing (42)

- `agents.ambiguous-cloud-code`
- `agents.existing-grok-bot`
- `agents.hire-claude-code`
- `agents.hire-needs-account`
- `app-permissions.grant-one-agent`
- `app-permissions.revoke-account`
- `assistant-connections.connect-external-assistant`
- `assistant-connections.use-scoped-client`
- `chat-channels.channel-file`
- `chat-channels.connect-slack`
- `chat-channels.link-sender`
- `chat-channels.outbound-email`
- `chat-channels.repair-endpoint`
- `chat-channels.reply-in-thread`
- `chat-channels.reply-to-email`
- `connection-setup.channel-prerequisites`
- `connection-setup.notion-agent-unassigned`
- `connection-setup.notion-connected`
- `connection-setup.notion-expired`
- `connection-setup.notion-missing`
- `connection-setup.notion-wrong-account`
- `connection-setup.return-from-login`
- `connection-setup.save-and-resume`
- `execution-environments.add-computer`
- `execution-environments.assign-computer`
- `execution-environments.prepare-image`
- `execution-environments.test-computer`
- `gateways-profiles.define-profile`
- `onboarding.choose-first-runtime`
- `onboarding.new-company`
- `onboarding.new-instance`
- `onboarding.resume-wizard`
- `projects.add-repository`
- `projects.replace-repository`
- `recovery.unknown-email-outcome`
- `recovery.workspace-repair`
- `runs-adapters.upgrade-runner`
- `runs-adapters.validate-hire`
- `secrets.vault-reference`
- `workspaces.prepare-repository`
- `workspaces.private-repository-no-access`
- `workspaces.recover-lost-sandbox`

### Future: incomplete journey or missing public product path (6)

- `access.invite-teammate`
- `access.manage-membership`
- `activity.routine-audit`
- `agents.restore-instructions`
- `budgets-costs.subscription-fees`
- `skills.enable-for-agent`



## Historical local Codex:17 original initial passes

These are original local one-time measurements of provider `codex`, model `gpt-5.6-sol`, production baseline8373 with original per-attempt source/definition identities. They are **not current OpenCode or updated-production qualification**. Across158 attempted IDs:17 initial passes,141 initial failures,159 retained measurements including one historical correction, and86 unrun. [Immutable historical report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/historical-local-codex-chat-catalog-20261027-158measured-86unrun/) and [original summary](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/historical-local-codex-chat-catalog-20261027-158measured-86unrun/summary.md). Unpriced cost is unknown, not zero.

- access.private-resource
- agents.agent-api-key
- assistant-connections.decline-consent
- chat-channels.provider-disabled
- companies.archive-company
- companies.rename-company
- inbox-search.archive-partial-failure
- instance-operations.instance-settings
- projects.project-work
- questions-and-approvals.accept-one-proposal
- questions-and-approvals.ambiguous-yes
- runs-adapters.list-model-options
- steering.preserve-draft
- task-coordination.reject-dependency-cycle
- tasks.create-backlog
- tasks.delegate-announcement
- tasks.website-task

## Campaign feedback review

0 distinct feedback items await review. Collection gaps and failed submissions remain separate findings.