Warden plan

28 - CR-14 (pending): Cost ledger break-even

tier: hermetic requires: []

28 - CR-14 (pending): Cost ledger break-even

Pending stub — GATED criterion. The precondition below is not built; this plan reports the criterion as pending (skip, never fail) until it lands. When it does, replace this stub with a real plan in the shape of 25-cr-18 / 26-cr-25 / 27-cr-20.

Criterion implemented (verbatim from the register)

Register: ~/.studio/master.withrobin.ai/project/rfc.one/criteria-register.md (status there: PENDING OWNER ACCEPTANCE; accepted by the 2026-08-31 proxy screen).

### CR-14 — Cost ledger break-even - Statement: Robin's total spend (slow-path writes + ingest checks + fast reads) falls below the alternative's at the read/write ratio pilot workspaces exhibit. - Metric: Break-even read count N* = (W(m) + m·σ·c_ing − m·g_base) / (r_base − r_fast), with r_base the per-query cost of the cheapest baseline read arm reaching quality parity (parity judged at the reasoning arm's evidence depth |C_q|, nDCG/precision at that depth); projection and ingest lines reported separately. - Dataset/inputs: Clean-series costs (W(m), r_fast at m = 20), injected-series c_ing, log-measured σ (Signals per artifact-generating request) and N̄ (reads per artifact-generating request); baseline arms: Signals-only hybrid and hybrid + reasoning-over-retrieved. - Threshold: N* ≤ N̄·m at m = 20. (r_fast < r_base is a sanity check, not a success.) - Drop condition: N* above N̄·m at observed ratios, or no break-even at all, falsifies the cost half of the thesis even if the quality half holds (feeds CR-19). - Source: Anchor §10.5. - Tier: gated — requires full stack plus replay harness and pilot logs.

Named precondition

Precondition: requires the full stack plus the replay harness and pilot logs. Not built at HEAD 7f379974 (verified 2026-08-31: no 'claims', 'dimensions', or 'initiatives' tables in server/src/db/schema.ts, and no conflicts_with edges anywhere in server/src or packages/). The replay harness and pilot logs have no code marker to probe.

Skip guard

set -uo pipefail
source "$WARDEN_LIB/assert.sh"
cd "${PROJECT_ROOT:-$(git rev-parse --show-toplevel)}"

SCHEMA=server/src/db/schema.ts
MISSING=""
grep -q "'claims'" "$SCHEMA" || MISSING="$MISSING claims-tables"

if [ -n "$MISSING" ]; then
  warden_skip "CR-14 — Cost ledger break-even" "pending: requires the full stack plus the replay harness and pilot logs — gated criterion, precondition not built (probes missing:$MISSING)"
else
  warden_skip "CR-14 — Cost ledger break-even" "schema probes now pass — upgrade this pending stub to a real plan before CR-14 can bind (probes are heuristic, not proof)"
fi

Shape (note for the next author)

Pending stub, hermetic on purpose: the guard reads the checkout only and emits skip in every branch, so this plan can never red a run — the criterion surfaces in every summary as pending with its precondition named. The probes are heuristic activation bells, not proof: quoted table names (and conflicts_with where the contradiction check is a precondition) flip the detail text when the machinery lands. The real plan must quote the criterion verbatim, turn its thresholds into warden_pass/warden_fail gates, and follow the conventions the three runnable plans set: machine-local fixtures (25-cr-18), NLI probe and versioned judge prompts (26-cr-25), data-keyed guard activation (27-cr-20).