code-yeongyu Senpi QA
QA the omo Senpi adapter (packages/omo-senpi/) and the task engine
(packages/senpi-task/) by driving the REAL senpi binary. Unit tests never
count as live QA here: bun run test:senpi is the package gate, the drivers in
packages/omo-senpi/scripts/qa/ are the harness proof.
Golden rules
- Evidence lives at exactly one path. Every artifact goes under
.omo/evidence/omo-senpi-adapter/<slug>/. Pick it withscripts/resolve-evidence-dir.mjsand nothing else — a hand-typed path is how runs end up somewhere likelocal-ignore/qa-evidence/, which no reviewer reads and the PR cannot cite. - The real agent dir stays untouched. The live drivers build their own
isolated
SENPI_CODING_AGENT_DIRand deliberately IGNORE a caller-provided one, so~/.senpi/agentis never used as the sandbox. Report the driver'srealSenpiUntouched/ changed-path fields and the isolated agent-dir path; treat a whole-directory digest as supporting evidence, not proof by itself. - No binary means SKIP, not silence. When
senpiis absent the live drivers reportSKIPorFAILin their final JSON rather than degrading to the real home. ASKIPis not a pass — say so in the evidence README. - The captured JSON is the evidence. No file on disk means the QA did not happen, which means no commit and no push.
Resolve the evidence directory first
ev="$(node .agents/skills/senpi-qa/scripts/resolve-evidence-dir.mjs \
--repo-root "$(git rev-parse --show-toplevel)" --slug <YYYYMMDD>-<short-slug>)"
mkdir -p "$ev"
The resolver returns an absolute path and creates nothing, so the caller decides
when the directory appears. A slug is ONE relative segment of lowercase letters,
digits, and hyphens (20260820-senpi-qa-contract). Separators, ./..,
traversal, absolute paths, and a non-git root are rejected with a non-zero exit
and a message naming the offending slug.
Router: pick your case
| You changed… | Run | Proves |
|---|---|---|
| Any adapter code, as the fast precondition | node packages/omo-senpi/scripts/qa/drive.mjs --self-test |
the driver + isolation harness itself works |
| Adapter wiring reaching a live session | node packages/omo-senpi/scripts/qa/drive.mjs |
a real senpi run with the plugin loaded, isolated agent dir, and no attributed real-home changes |
| Task lifecycle (single + batch) | SENPI_BIN="$(command -v senpi)" node packages/omo-senpi/scripts/qa/task-e2e.mjs |
live task start/stream/terminal states |
| Team delivery, shutdown, reclaim, restart recovery | SENPI_BIN="$(command -v senpi)" node packages/omo-senpi/scripts/qa/team-e2e.mjs |
injection delivery and exactly-once recovery |
| Task RPC driver scripts | node packages/omo-senpi/scripts/qa/task-rpc-e2e.mjs --self-test |
the RPC surface contract |
| Skill delivery into a task | SENPI_BIN="$(command -v senpi)" node packages/omo-senpi/scripts/qa/task-load-skills-e2e.mjs |
skills reach the child |
| Continuation behavior | node packages/omo-senpi/scripts/qa/probe-continuation.mjs |
turns continue as expected |
| DAG state machine / runners | bun test packages/senpi-task |
unit + chaos invariants (NOT live proof) |
Point a driver's output at the resolved directory, e.g.:
TASK_E2E_OUT_DIR="$ev/live-task-dag" SENPI_BIN="$(command -v senpi)" \
node packages/omo-senpi/scripts/qa/task-e2e.mjs
Package gate
tsgo --noEmit -p packages/omo-senpi/tsconfig.json
bun run test:senpi
Write the evidence README
Every run leaves $ev/README.md a reviewer can read without rerunning anything.
The required sections are the repo-wide evidence rules in the root
AGENTS.md (what was tested / observed / why it is enough /
what was omitted). For Senpi, record the driver's changed-path/isolation fields
and sandbox agent-dir path. Some drivers report sandbox paths without removing
them; the caller must delete every task-owned sandbox and verify child PIDs are
terminal before writing the cleanup receipt.