## What works, what failed, and what is still future

Status from authenticated retained measurements at 2026-10-27T21:05:48.461662+00:00. Current remote results use OpenCode/OpenRouter model `deepseek/deepseek-v4.1-flash-1017`. Historical Codex passes are separate and contribute no current pass credit.

| Current remote status | Scenarios |
|---|---:|
| Live passes | 3 |
| Live failures pending reviewed disposition or final correction | 23 |
| Permanently failed after the one correction | 1 |
| Implemented but not yet run | 149 |
| Future: unmerged invitation core prerequisite | 20 |
| Future: explicit external prerequisite missing | 42 |
| Future: incomplete journey or missing public product path | 6 |
| **Total frozen denominator** | **244** |

**27 distinct measured scenarios; 28 attempts (3 passed, 25 failed).** Latest allowed outcomes are 3 passed / 24 failed / 217 unrun. First attempts remain immutable: tasks.create-backlog failed both its initial and sole correction. All other measured scenarios currently have one attempt.

A pending, queued, held, or unadmitted cancelled job is not a measured scenario. The 188-cell selection is not 188 completed journeys. “Pending reviewed disposition or final correction” requires review; it does not authorize a retry. An actual material correction is required. “Permanently failed” means the single correction budget is exhausted.

The eighteen authenticated completions from [bulk run 40580283071](https://github.com/paperclipai/paperclip/actions/runs/40580283071) contain one pass and seventeen failures. All eighteen cleanup checks passed. After zero active paid cells were verified, the workflow was normally cancelled to avoid further admission with the shared descriptor defect. The 170 queued/waiting cells were unadmitted and consume no ordinals. Individual cancelled-job statuses were not fully retrieved; pre-cancel zero-active and terminal workflow evidence are retained.

New measurements bind source `50d9ecad91ba9dee6c4a8c8335ad053fd93517f4`, production `50b932a142216331b8d476042b454bc123739c40`, actual AWS lifecycle, embedded database, and original framework start times. Historical remote baseline 8373 remains preserved separately. Live passes have genuine build/native proof; final selected-definition and baseline eligibility remains distinct. No heartbeat usage does not establish zero setup/hello usage or zero cost.

### Closed bulk cohort: observed stages and causes

| Scenario | Outcome | Observed stage | Evidence-supported cause | Correction allowance |
|---|---|---|---|---|
| activity.audit-change | Passed 9/9 | Canonical observation and one native run | Independent audit provenance and state checks passed | No correction needed |
| access.sign-in | Failed | Browser boundary; zero native runs | Invalidated-session boundary assertion failed; status semantics under review | One, only after reviewed correction |
| activity.agent-feedback | Failed | Pre-query validation; zero native runs | Runtime sourceFiles descriptor drift; definition evidence absent | One, after coherent metadata correction |
| access.private-resource | Failed | Canonical observation and one run | Observed provider run failed; underlying cause unknown | One, only if a material correction is justified |
| access.other-company | Failed | Canonical observation and one run | Observed provider run failed; underlying cause unknown | One, only if a material correction is justified |
| access.cli-authorization | Failed | Initial identity-response phase; one run | Initial response failed; CLI authorization phase not proven | One, only if a material correction is justified |
| activity.work-timeline | Failed | Setup guard; zero native runs | Known invitation prerequisite blocked before token-path acceptance | One, after prerequisite is safely available |
| activity.find-runs | Failed | Canonical observation; three run IDs | Settled exact-task-and-agent-run-links assertion failed | One, only if a material correction is justified |
| agent-chat.chat-disabled | Failed | Browser boundary; zero native runs | Ordinary-agent-cannot-change-instance-gate assertion failed | One, only if a material correction is justified |
| activity.company-overview | Failed | Canonical observation and one run | Settled grounded-blocker assertion failed | One, only if a material correction is justified |
| agents.choose-primary | Failed | Setup guard; zero runs | Known invitation prerequisite blocked before acceptance | Held behind core prerequisite |
| agent-chat.reopen-conversation | Failed despite 9/9 observed checks | Two run IDs; final evidence capture | Public screenshot route guard rejected chat route | One, only after reviewed capture correction |
| agents.configure-required-agent | Failed | Canonical observation and one run | Shorter-update configuration/history assertions failed | One, only if material correction is justified |
| agent-chat.remember-and-follow-up | Failed | Conversation history; three run IDs | Selected-preview and unestablished-choice assertions failed | One, only if material correction is justified |
| agent-chat.conference-room | Failed | Initial identity-response phase; one run | Initial identity response timeout; underlying cause unknown | No unchanged timeout retry |
| agents.agent-api-key | Failed | Initial identity-response phase; one run | Initial identity response failed; key workflow not proven | One, only if material correction is justified |
| agent-chat.multiple-handoffs | Failed | Handoff/history phase; four run IDs | Headline feedback save wait timed out | One, only if material correction is justified |
| agent-chat.track-delegated-work | Failed | Handoff wait; four run IDs | Observer reported null companyId while waiting for Morgan handoff | One, only if material correction is justified |

Finally-captured oracle observations are retained separately from proof that a normal terminal matcher was reached. Run IDs are not automatically native executions; queued/cancelled work remains distinct.

### Live passes (3)

- `activity.audit-change`
- `agents.change-manager`
- `companies.rename-company`

### Live failures pending reviewed disposition or final correction (23)

- `access.cli-authorization`
- `access.other-company`
- `access.private-resource`
- `access.sign-in`
- `activity.agent-feedback`
- `activity.company-overview`
- `activity.find-runs`
- `activity.work-timeline`
- `agent-chat.chat-disabled`
- `agent-chat.conference-room`
- `agent-chat.multiple-handoffs`
- `agent-chat.remember-and-follow-up`
- `agent-chat.reopen-conversation`
- `agent-chat.track-delegated-work`
- `agents.agent-api-key`
- `agents.choose-primary`
- `agents.configure-required-agent`
- `agents.hire-denied`
- `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 (1)

- `tasks.create-backlog`

### Implemented but not yet run (149)

- `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.choose-cli-context`
- `cli-operations.create-from-cli`
- `cli-operations.export-document-cli`
- `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.