# Setup health diagnostic outside the 244-scenario campaign

[Actual Actions run](https://github.com/paperclipai/paperclip/actions/runs/40544678316). One failed setup diagnostic; cleanup passed. This is NOT a canonical scenario measurement, an initial or a correction. It does not change the 244-scenario denominator.

One ordinary automatic lifecycle hello failed: opencode_hello_probe_failed, category UNKNOWN. The working directory, headless permissions, command resolution and validation-via-probe checks were informational; they do not prove the hello succeeded or identify its root cause. No canonical chat was sent:0 issues,0 conversations,0 comments and0 heartbeat runs. Automatic hello provider calls/tokens/cost remain UNKNOWN; zero heartbeat usage is not zero model usage.

Source139d83b7779ea0ec7edb49446221f50719d67d17. Native OpenCode/OpenRouter model openrouter/deepseek/deepseek-v4.1-flash-1017. Actual AWS On-Demand/x86_64 host and pinned PostgreSQL18.6amd64 Docker qualified. Original authenticated artifact/result bytes remain unchanged.

## Working, failed and future coverage

- [Historical partial Codex report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/historical-local-codex-chat-catalog-20261027-158measured-86unrun/):17 original initial passes,141 initial failures across158 attempted IDs;159 original retained measurements. These are historical one-time outcomes, not current OpenCode confidence.
- [Historical pass names, six incomplete journeys and all86 unrun IDs](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/historical-local-codex-chat-catalog-20261027-158measured-86unrun/summary.md). Six are **incomplete or blocked journeys**, not complete E2E coverage: access.invite-teammate, access.manage-membership, activity.routine-audit, agents.restore-instructions, budgets-costs.subscription-fees, skills.enable-for-agent. Registration and executable prerequisite probes do not make their intended journeys complete.
- [Original OpenCode backlog initial failure](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-40530790741-1/):one actual scenario initial failed setup before canonical chat;243 initials remain unrun. All244 remain behavior-unverified. The outside244 health diagnostic adds no scenario attempt.

The original historical publication is immutable and unchanged; this summary clarifies its earlier registration wording. No old pass is carried into the new model rate. No production/core PR was merged for these measurements.

## Campaign feedback review

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