Skip to content

v5.9 verification — agent guardrails and feedback loop ​

Status: verified locally on Linux/tmux; hosted CI not run; macOS/Herdr checklist manual and unexecuted Date: 2026-11-06 Specification: #105 Tickets: #106 through #112 Branch: fix/v59-review Base: integration/ensemble-v5.9 at 7c79e48

This is the specification-level verification record. It covers all seven v5.9 tickets and the post-merge two-axis code review fixes. The earlier 2026-11-05-v59-t2.md and 2026-11-05-v59-t7.md records remain ticket-scoped; this -v59.md record is the evidence the tracker audit looks for. The record does not close #105 or any ticket. At the time of writing, GitHub reports #105 with 7/7 children closed, so it is ready for a maintainer to close after this record lands.

v5.9 is environment and tooling work. It does not change composer behavior, init, skill routing, permissions, or any other product runtime surface.

Environment ​

ItemValue
OSLinux
Terminal hosttmux 3.5a
Node26.12.1
npm12.2.1
OpenCode2.2.5
fdfdfind 10.2.0
Git2.47.3

The repository type-checks against @opencode/plugin 2.2.1. The live checks exercise the installed OpenCode 2.2.5 host. These are different version surfaces, as recorded in the runtime guide.

Ticket coverage ​

TicketDelivered
T1 #106test:live:fake:all, test:live:all, the fail-fast PASS/FAIL/SKIP matrix, and test:live:latency. The known flaky T4 fixture now uses a bounded 180s wait with a subtask diagnostic and no retry loop.
T2 #107CI live job for the fake/empty suite with pinned Ubuntu, Node, OpenCode, tmux, and fd; require-mode preflight; local skip-and-exit-zero preserved.
T3 #108Reviewer standards for judgement calls and the two-axis review workflow, linked from the contribution guide.
T4 #109Table-driven service routing regression matrix covering skill text against explicit recipients, file references, DM/group, multi-agent, and mixed anchors.
T5 #110ADR 0001: Native-skill boundary, linked from implementation and agent instructions.
T6 #111One-time unused-symbol cleanup, then noUnusedLocals and noUnusedParameters in tsconfig.json; npm run verify green.
T7 #112Version-spec closure rule, read-only npm run issue:hygiene, handoff reference split, and the repeatable macOS/Herdr checklist.

Review fixes ​

Spec findings:

FindingResolution
Matrix assumed /tmp/opencode existedscripts/live-matrix.sh creates the temp parent before mktemp. src/v2/live-matrix.test.ts runs the matrix with a clean TMPDIR and no pre-existing opencode directory.
Skip detection scraped log textThe harness writes ENSEMBLE_LIVE_SKIP_MARKER on the local skip path; the matrix reads that file. Local skip still exits zero and require mode still fails. Covered by the matrix tests.
Hygiene matched the T2 ticket record as spec evidenceverificationRecord now requires the spec's own -v59.md record, not -v59-t2.md. src/v2/issue-hygiene.test.ts covers ticket-only versus final-record directories.
Preflight required fd for the fake suitescripts/live-preflight.sh defaults to fake scope and requires/prints fd only for all. CI keeps its fd install.
Historical v5.6/v5.7 records were editedReverted those two files to their delivered content. Current v5.8 and v5.9 records keep the checklist link.
Only ticket records existed for v5.9This final record.
Documentation index omitted v5.9 and v5.6docs/README.md lists v5.9, v5.8, v5.7, and v5.6.
Hosted CI was not runRecorded under Not run below; no hosted CI pass is claimed.

Standards findings:

FindingResolution
Latency probe duplicated the › cursor literalThe probe reads settingsCursorMark(true) from src/v2/tui/settings.ts instead of restating the marker.
Dead railAgentLabel helper and testRemoved both; railGroupLine remains the live helper.
Duplicated subtask node readerlive_subtask_read is the single reader for field polling and timeout diagnostics.
issue-hygiene.mjs exported internal helpersExports removed; tests exercise the CLI at its public seam.
Duplicated skip-versus-fail proseScripts README is the authoritative contract; contribution, runtime, and review docs point to it.
Preflight tool/version checks were inconsistentOne version normalizer compares Node and OpenCode exactly; the fd gate uses the same skip/require path as other tools. Covered by src/v2/live-preflight.test.ts.

Commands ​

All commands ran sequentially on the branch before handoff. No hosted CI job was triggered.

CommandResult
npm run verifyPass — strict type check, then 673 tests passed, 0 failed, 0 skipped.
npm run test:live:fake:allPass — fake 167s, fake-empty 8s; 2 passed, 0 failed, 0 skipped, 0 not run in 175s. The suite also passed an earlier run (174s) before the final harness-reader refactor.
npm run test:livePass — real host catalog; packaged plugin, palette, prose /init, and visible System Agent init verified. No skip line.
npm run test:live:preflightPass — fake scope: node v26.12.1, opencode v2.2.5, tmux 3.5a; fd not required.
npm run test:live:preflight -- allPass — also reports fd 10.2.0.
npm run issue:hygienePass — reports #105 open with 7/7 children closed and docs/verification/2026-11-06-v59.md.
npm run issue:hygiene -- --allPass — #105 resolves to this record; #99, #90, and #78 resolve to their final records; no ticket record is used as spec evidence.
node --test --experimental-strip-types src/v2/live-matrix.test.tsPass — 3 tests: clean-host temp root, structural skip marker, required-skip failure.
bash -n scripts/live-matrix.sh scripts/live-preflight.sh scripts/live-latency-probe.sh scripts/lib/live-harness.sh scripts/live-check-fake.sh scripts/live-check-fake-empty.sh scripts/live-check.shPass — no shell syntax errors.
git diff --checkPass — no whitespace errors.

The aggregate matrix ran the scenarios in order and printed one summary. The fresh-host matrix test uses a temporary TMPDIR with no pre-existing opencode directory and a HOME without the nvm OpenCode install, so the scenarios take the local skip path without starting a server or model.

Not run ​

  • Hosted GitHub Actions: not triggered or executed from this environment. The workflow file and equivalent local commands were checked, and the deterministic suite passed locally, but this record does not claim a passing hosted CI run. The live job still requires its first hosted execution.
  • npm run test:live:all as one command: not invoked. Its fake, empty, and real scenarios were run separately (test:live:fake:all then test:live), so the full matrix content is covered without a second three-minute fake run.
  • macOS/Herdr: not run. This environment is Linux/tmux. The repeatable checklist remains manual and unexecuted until a run is recorded there.
  • Real-model checks in CI: intentionally not part of the CI job; they stay local and are not required.

Tracker state ​

  • #105 remains open and was not closed by this branch.
  • #106–#112 are not closed by this record.
  • #99, #90, and #78 were not reopened or rewritten.
  • The v5.6 and v5.7 verification records were restored to their delivered content; only the current v5.8 record gained a checklist pointer.

Released under the MIT License.