All 8 actionable findings accepted; R9-R11 were confirmations.
Blockers:
- R1: sys:gsub("N", ...) would corrupt "No prose / commentary /
numbering" → "16o prose" etc. Switch to %d + string.format.
- R2: §5 had a 2-slot NORRIS_SUFFIX_TEMPLATE redesign that
contradicted §11's "don't change the template; append helper
output after". §5 now shows the helper-append approach.
Important:
- R3: preplan bypasses call_broker (no fallback retry) — keep that
by design; retry would silently swap planning models. Documented
in §10 Risks so it doesn't get "fixed" later.
- R4: no pcall around run_norris → ctx.norris_active/_goal/_tasks
can leak across launches if a Norris step crashes. Fix: clear all
three at the TOP of run_norris before preplan. Cheaper than full
pcall wrap; handles the stale-tasks vector.
- R5: clarified C3 commit scope — safety.lua ONLY in C3; the
executor cfg resolution + preplan wiring lands in C4.
- R6: Context:reset() now also clears self.norris_tasks (defensive;
:reset is unreachable mid-Norris but one line is cheap).
Nits:
- R7: timeout_ms = pre_cfg.timeout_ms or 60000 (respect the
configured per-model timeout).
- R8: "Status:" → "Terminal output:" in §1 acceptance criterion.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Resolves direction for #89. Splits Norris into two roles:
- Preplanner (cloud) fires ONCE at :norris launch; emits TASK: list.
- Executor (local) handles each TASK; existing HALT protocol intact.
ctx.norris_tasks anchor survives eviction (mirrors ctx.norris_goal).
Cost category 'norris-preplan' separates the cloud preplan call
from per-step executor cost in :cost detail.
Graceful fall-back when cfg.norris.preplanner is unset OR preplan
call fails — Norris runs as today (single-model). No regression for
existing users.
PHASE0 §11 amended to add Phase 10 row.
Manifest declares 6 Open Questions for analyze step; 12 design
decisions table; module-touch table; 4-pillar plan.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
marfrit