Warden plan
tier: hermetic requires: []
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.
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-17 — Router accuracy - Statement: The Router labels requests retrieve/reason/author accurately enough that downstream failures are attributable to the components under test, not misrouting. - Metric: Primary: routing accuracy. Also: the two misroute rates separately (slow-misroute wastes compute; shallow-misroute returns a shallower answer). - Dataset/inputs: 300 requests per workspace sampled from logs, labeled by two annotators (κ reported); a disjoint portion is the Router's fine-tuning set. - Threshold: Accuracy ≥0.9; shallow-misroute rate ≤0.05. - Drop condition: Below either bar, the Router's inputs are revisited before any downstream result is interpreted (redesign, not drop). - Source: Anchor §10.7. - Tier: gated — requires the Router component (fine-tuned; anchor §8 — the anchor's other trained component) and the fast/slow runtime it routes between.
Precondition: requires the Router component (fine-tuned; the anchor's other trained component) and the fast/slow runtime it routes between. 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/). No crisp code marker exists for the Router or the fast/slow runtime; this stub skips unconditionally.
set -uo pipefail
source "$WARDEN_LIB/assert.sh"
cd "${PROJECT_ROOT:-$(git rev-parse --show-toplevel)}"
# No greppable code marker exists for this precondition yet — unconditional
# pending skip; the upgrade decision is human.
warden_skip "CR-17 — Router accuracy" "pending: requires the Router component (fine-tuned; the anchor's other trained component) and the fast/slow runtime it routes between — gated criterion, precondition not built"
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 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).