colima-integration procedure — revision 10f80d6e

Procedure colima-integration · revision 10f80d6e · 2026-09-13

What this test proves

One colima invocation runs the canonical Hermes testbed test.sh, then asks real agents in that fixture to execute AT9, AT10, and AT11. Every step records an independent verdict, execution continues after failure, and the aggregate passes only when all four panels pass.

Evidence layout

The driver writes exactly one run directory under site/reports/integration/colima/<run>/. Step runners own only the step.json and raw sidecars in the directory passed by the driver. scripts/integration/render_colima.py is the sole renderer for step panels, the run page, integration.json, and the sibling envelope. The four steps always run in the sequence above.

Changes

The revision sections below identify each driver revision that produced committed evidence.

Flow

Run canonical testbed test.sh

1: hermes-skills

2: task-start AT9

3: assignment AT10

4: prompt-handoffs AT11

Aggregate PASS/FAIL

Render integration.json and panels

runner revision 10f80d6e

Steps

stepactionobservableevidence
1Run `colima-hermes-skills` in the fixturethe seven skill reports and fixture health checks have a retained verdict`steps/NN-hermes-skills/step.json` and raw sidecars
2Run `colima-task-start` in the same fixturetask-start notification, ordering, and reminder cases have a retained verdict`steps/NN-task-start/step.json`
3Run `colima-assignment` in the same fixtureassignment/task-pass cases have a retained verdict`steps/NN-assignment/step.json`
4Run `colima-prompt-handoffs` in the same fixturethe fixture agent's public task-event and doctor observations have a retained verdict`steps/NN-prompt-handoffs/step.json`

Revision note: refactor(bb8): drive colima checks through fixture prompts