Commit Graph

8 Commits

Author SHA1 Message Date
Boden Fuller b8c5a3761b feat(agentops): make 3.0 hookless-first
Add DDD skill-domain contracts, hook lease inventory, replacement ports, artifact-first RPI skill boundaries, and release exact-SHA validation. Demote ao inject to a compatibility adapter and remove prompt-only default hooks.
2026-05-16 09:43:08 -04:00
Boden Fuller 8385cf6a64 chore: add release readiness gate 2026-05-02 18:46:12 -04:00
Boden Fuller 55ded76d0b fix(codex-spawn): bypass intent-echo on team-runner + smoke + validate scripts + tests
Substrate fix for the intent-echo hook trap. The Mac codex install ships
~/.codex/hooks.json with intent-echo.sh on UserPromptSubmit; long prompts
containing destructive verbs or scope-limiters trigger a HIGH-STAKES
preamble that captures as the assistant message. Non-interactive `codex
exec` then produces no real output.

team-runner.sh:226 is the load-bearing dispatcher behind /swarm, /crank,
/evolve, /codex-team, /red-team — patching it once propagates the fix to
every team-runtime skill. Mirror on the dry-run echo at :195.

smoke-test-codex-skills.sh prompts contain "only" (line 175); validate
prompt contains "only" (line 61). Both trigger today.
test-sandbox-mode.sh and test-structured-output.sh patched defensively
for drift resistance.

See .agents/findings/registry.jsonl entries f-2026-05-02-002 and
f-2026-05-02-003.
2026-05-02 12:34:56 -04:00
Boden Fuller 204501fde5 test(quarantine): promote codex integration suite 2026-04-11 23:06:54 -04:00
Boden Fuller 5d4e171dba feat(tests): advance GOALS.md directives #1, #2, #4
Promote 2 quarantined runtime tests (schema-validation, cross-runtime),
add install path smoke tests (24 checks), create flywheel lifecycle E2E
gate (capture → index → inject → retrieval). All 53 assertions passing.
2026-03-30 15:44:28 -04:00
Boden Fuller 14744283ec fix(tests): delete 10k LOC coverage padding, quarantine 72 unused tests, add context_assemble coverage (na-fvs)
Wave 1 of CI Test Effectiveness epic:

- Delete 24 cov*_test.go files (10,527 LOC) that inflated coverage with
  trivial != "" assertions without testing behavior
- Move initGitRepo helper to uat_smoke_test.go (was in deleted file)
- Quarantine 72 shell tests requiring external runtimes (Claude, Codex,
  OpenCode) to tests/_quarantine/ — none were in CI
- Add 6 new context_assemble tests covering rune-safe truncation, Shannon
  entropy, high-entropy redaction, and history formatting
- Audit 7 set -uo pipefail scripts: all are test harnesses with failure
  counters — intentionally correct without -e
- Update coverage ratchet baseline

Issues: na-fvs.1, na-fvs.2, na-fvs.3, na-fvs.4
2026-03-05 00:12:28 -05:00
Boden Fuller 35e048a7ce test(codex): add cross-runtime skill validation test (Directive 3)
Exercises the inject skill via both Claude Code runtime (ao inject --json)
and Codex CLI runtime (codex exec), verifying structured JSON output with
required fields. Gracefully degrades to PARTIAL when Codex CLI network
access is unavailable.
2026-03-02 22:56:15 -05:00
Boden Fuller 37d4b5b2ae Merge branch 'codex/rpi-supervisor-cli' into main 2026-02-21 19:41:50 -05:00