# V6 Token-Cost Contingency Plan — Price Shocks, Outages, Kill Criteria **Status:** Planning gap-fill per `V1_V7_PLAN_SET_AUDIT_2026-06-12.md` §6.2 ("no model-price-shock or provider-outage contingency for a product whose stated make-or-break bet is token cost"). **Date:** 2026-06-12. **Owners:** Moirai kernel owner (tiering levers), model-ops lead (routing, caching, dashboard), V6 product lead (player-visible degradation decisions, kill-criteria escalation), finance partner (weekly cost readings). Canonical inputs: per-tier token budgets and concurrency caps in `V6_DEPENDENCIES.md` §19 (:400–437) — Clotho ≤ 50k tokens/agent/active-minute (typical 15–25k with caching) on Opus-class; Lachesis ≤ 10k/agent/reflection (≈ ≤1,200/agent/game-minute amortised) on Sonnet-class; Atropos ≤ 15k/agent/ game-day and Vac ≤ 2k/parse on Haiku-class; Clotho scene cap design 16 / hard 24; Lachesis resident world 150–400; Solo-world hourly cognition cap with "homestead rest". The dependency doc deliberately leaves the dollar figure floating ("the dollar figure floats with provider pricing", dep:404–406); this document is where the dollars get computed and stress-tested. --- ## 1. Reference prices and unit-cost model Anthropic list prices (per MTok, as published in the Claude platform docs, cached 2026-06-04; re-verify quarterly): | Class (V6 routing, dep:426–428) | Model tier | Input | Output | Cache read (≈0.1× in) | Cache write 5-min (1.25× in) | Batch discount | | ------------------------------- | ---------- | ----- | ------ | --------------------- | ---------------------------- | --------------------------------------- | | Opus-class (Clotho) | Opus | $5.00 | $25.00 | $0.50 | $6.25 | n/a (interactive) | | Sonnet-class (Lachesis) | Sonnet | $3.00 | $15.00 | $0.30 | $3.75 | −50% on everything | | Haiku-class (Atropos, Vac) | Haiku | $1.00 | $5.00 | $0.10 | $1.25 | −50% (Atropos only; Vac is interactive) | ### 1.1 Reference scenario — cost per player-active-hour (all mix figures are planning assumptions adopted 2026-06-12, to be replaced by staging telemetry per the §19 cost gate) **Clotho.** Full-cognition agent-minute at the _typical_ 20k tokens (mid of the doc's 15–25k): split 90% input / 10% output ⇒ 18k in / 2k out; input mix 70% cache-read / 10% cache-write / 20% fresh: ``` reads 12,600 × $0.50/M = $0.0063 writes 1,800 × $6.25/M = $0.0113 fresh 3,600 × $5.00/M = $0.0180 output 2,000 × $25.0/M = $0.0500 per full-cognition agent-minute ≈ $0.0856 ``` Player attention is serial: assume dialogue/active-direction occupies 30% of active minutes with on average 1.5 agents in full cognition ⇒ 27 full-cognition agent-minutes per player-hour ⇒ $2.31. Ambient co-present Clotho agents (≤16 scene, plans cache-served, "cognition recomputed only on material change", arch:1156–1158): 12 agents × 42 min × 0.8k tokens, ~90% cache-read input, sparse output ⇒ ≈ $0.58. **Clotho ≈ $2.89/h** (input-side $1.34, output-side $1.55). **Lachesis.** 250 resident agents (mid of 150–400); 40% have a due reflection per cycle (the rest resolve from cached plans); 5 reflections/h (12-game-min cadence, 1 game-min = 1 real-min online); typical reflection 4k tokens (vs the 10k cap), 85/15 in/out ⇒ 2.0M tokens/h. Batched Sonnet with 50% of input as cache reads: ``` in 0.85M × $0.15 + 0.85M × $1.50 = $1.40 out 0.30M × $7.50 = $2.25 Lachesis ≈ $3.65/h ``` **Atropos.** 500 distant/offline agents advancing per player at typical 6k/game-day (cap 15k), 1 game-day ≈ 2 real-h online ⇒ 1.5M tokens/h, batched Haiku, 50% input cached ⇒ in $0.35 + out $0.56 ⇒ **≈ $0.91/h**. **Vac.** 30 voice parses/h × 1.2k typical (cap 2k) ⇒ **≈ $0.05/h**. **Clio.** Chronicle/arc-watch amortisation ⇒ **≈ $0.50/h** (0.30 in / 0.20 out). | Tier | $/player-active-hour | Input-side | Output-side | | ------------------------------ | -------------------- | ---------- | ----------- | | Clotho (Opus-class) | 2.89 | 1.34 | 1.55 | | Lachesis (Sonnet-class, batch) | 3.65 | 1.40 | 2.25 | | Atropos (Haiku-class, batch) | 0.91 | 0.35 | 0.56 | | Vac (Haiku-class) | 0.05 | 0.03 | 0.02 | | Clio (mixed, batch) | 0.50 | 0.30 | 0.20 | | **Reference total** | **$8.00** | **$3.42** | **$4.58** | Two readings of this table matter: 1. **The headline risk is not the Opus dialogue minutes — it is the 250 quietly reflecting residents.** Lachesis is the largest line despite the cheaper model, which is why the existing **[P2]** distillation note (V6_DEPENDENCIES.md:336) is the single biggest lever in §3. 2. **Budget caps ≠ expected spend.** If every tier ran at its cap (16 × 50k × 60 Clotho; 400 × 1,200 × 60 Lachesis; Atropos at 15k), the ceiling is ≈ $205 + $53 + $2 ≈ **$260/player-active-hour** — two orders of magnitude above reference. The token budgets are correctly framed as the _contract_ (dep:431–434); the dashboard target below is the _economic_ control, measured, not derived from caps. **Dashboard target (planning assumption adopted 2026-06-12):** launch at the $8.00 reference, trending to ≤ $5.00 by GA+2 quarters via §3 rungs 1–2. The target is recorded on the model-ops cost dashboard the dependency doc already designates as the live tracker. --- ## 2. Model-price-shock scenarios The audit asks specifically about **input-price** moves; cache read/write prices scale with input price (they are multipliers of it), so they shock together. Output prices held constant in S1/S2. | Scenario | Input-side | Total $/player-active-hour | Delta | | ----------------------------------- | ------------------- | -------------------------- | ------ | | S0 — today | $3.42 | **$8.00** | — | | S1 — input +50% | $3.42 × 1.5 = $5.13 | **$9.71** | +21.4% | | S2 — input +100% | $3.42 × 2.0 = $6.84 | **$11.42** | +42.8% | | S3 — full reprice +50% in _and_ out | — | **$12.00** | +50% | | S4 — full reprice +100% in and out | — | **$16.00** | +100% | Observations: (a) V6 is _output-heavy_ ($4.58 of $8.00) because agents generate dialogue, reflections, and beats — input-only shocks hurt less than intuition suggests, and **output-token discipline (shorter reflections, schema-constrained beats) is a real lever, not just caching**; (b) batch-tier work (Lachesis+Atropos+Clio ≈ $5.06 of $8.00) reprices with the batch discount — if a provider shock ever _removed_ the 50% batch discount instead, the hit would be +$5.06/h (+63%), worse than S2; the contingency below treats "batch-discount loss" as equivalent to S2-and-a-half and triggers the same ladder. --- ## 3. Mitigation ladder — in order, each rung quantified against S0 Rungs are ordered cheapest-first in player-experience cost; each is independently deployable and gated by the existing eval posture (a routing or cap change ships only with `V6/evals/*` suites green at their `minimumPassRate`s, per arch:1307–1327). | Rung | Lever | Mechanics | Δ vs S0 | Running total | | ----- | ------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------- | ------------- | | **1** | **Cache hit-rate improvements** (current Clotho typical is already "15–25k _with caching_") | Deterministic prompt assembly per shared-prefix rules; persona/policy/Ori-dossier prefixes on 1-h TTL caches keyed per agent; plan-cache reuse on the Ori (arch:1156–1158). Clotho input mix 70→85% reads (full-cog input $0.0356→$0.0223/agent-min); Lachesis batch reads 50→75% (in $1.40→$0.83) | **−$0.98** | $7.02 | | **2** | **Lachesis/Atropos distillation** — the existing P2 note (dep:336) promoted to P1 upon any shock | Distilled/fine-tuned Haiku-class for reflection and summary workloads; Lachesis post-rung-1 $3.08 → $1.03; Atropos −30% | **−$2.32** | $4.70 | | **3** | **Scene-cap tightening 16 → 8** (design target; hard cap 24 → 12) | Halves ambient Clotho upkeep (−$0.27) and, more importantly, halves the _tail_: cap-spend ceiling $205 → $103/h; p95 scenes are where Clotho blowouts live | **−$0.30 mean** | $4.40 | | **4** | **Solo-world hourly-cap reduction + homestead rest default-on** | Lachesis due-reflection fraction 40% → 27% (−$0.33 post-rung-2); Atropos batch −33% (−$0.21); the cap and rest multiplier already exist (dep:423–424, arch:1150–1155) | **−$0.54** | **$3.86** | **Net:** the full ladder reaches ≈ **$3.86/h (−52%)**. Under S2 (+100% input) applied to the post-ladder mix, cost ≈ $5.4/h — still **below today's unmitigated $8.00**. The ladder absorbs a full +100% input-price shock; under S4 (full +100% reprice) post-ladder cost ≈ $7.7/h, i.e., S4 consumes the entire ladder. Anything beyond S4 forces §5 structural moves. Deliberately _not_ on the ladder: silently faking cognition (hardcoded "reflections"), shrinking safety/eval coverage, or cutting the Isis gate — forbidden under the quality standard; degradation must be honest (arch: 1167–1169: "the player is told honestly if their world is running degraded"). --- ## 4. Provider-outage degradation — player-visible contract and recovery The BT/HTN fallback is already specced: cheap execution is co-located with the world server and survives a cognition outage (arch:657–660, 704, 728, 759–760); "a cognition outage costs richness, never the world" (arch:422–424). This section defines the _contract_ — what the player sees, tier by tier. ### Degradation tiers | State | Trigger | Player-visible contract | | ------------------------------------------------ | ---------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **D0 normal** | — | Full fidelity. | | **D1 — Opus-class unavailable or 529-saturated** | Provider incident on the Clotho route | Clotho reroutes to Sonnet-class. Honest banner: "Your companions are thinking a little more simply right now." Dialogue continues; behavior evals for the Sonnet route are pre-certified in CI (a standing `clotho-sonnet-fallback` eval profile kept green at all times, so the reroute is push-button, not a scramble). | | **D2 — all interactive cognition unavailable** | Full provider outage / network partition | World never pauses: agents keep schedules, navigation, gestures, and cached barks via BT/HTN. Free conversation is declined honestly in-fiction _and_ in-UI ("Abeni can't find her words right now — she'll remember what you did"). Vac voice→intent parsing is down, but the structured intent builder still issues objectives (non-voice parity, arch:864–870) executed by BT/HTN. **No Ori writes are fabricated**: perception-derived events buffer durably (see `ori-dr-and-compaction.md` §3.5); reflections/summaries defer. Crossroads holds extend; **irreversible transitions freeze** — no `Departed`/`Transcended`/`Died` resolution while cognition is degraded (the Ereshkigal state machines simply do not advance, arch:983–1024). | | **D3 — batch tier also unavailable** | Extended outage | As D2, plus Chronicle/Book generation pauses; on the player's next return Clio covers the gap from the buffered events ("while the threads were tangled…") — which is exactly its narrative-reconciliation job (arch:894–897). | ### Recovery contract - **Playability RTO: 0** (the world never stopped). - **Full-fidelity restore: ≤ 15 min** after provider recovery (tier reassignment is recomputed every tick; rehydration is the normal escalation path, arch:1171–1173). - **Backlog drain:** deferred Lachesis/Atropos work drains via batch at a catch-up budget ≤ 1.5× the normal hourly tier budget until clear; drain SLO 6 h. Catch-up never exceeds per-tier token caps — an outage must not become a cost incident. - **No retroactive fabrication:** drained reflections process buffered episodes with their original timestamps; if the player witnessed degraded behavior, Clio writes one reconciliation beat, logged as such. - Multi-provider hedging is **out of scope at launch** (V6 consumes V1 model-ops routing; adding a second provider is a V1-platform decision). This plan's posture: degrade honestly within one provider, and keep the D1 Sonnet profile + distilled-model rung warm so the dependency is on _a_ capable model, not on one price point. --- ## 5. Kill criteria Measured quantity: **blended cognition cost per player-active-hour**, weekly reading from the model-ops dashboard (the metric dep:431–434 already tracks), trailing-4-week average, evaluated every Monday by model-ops lead + finance partner; product lead owns escalation. **Trigger (X, Y):** trailing cost **> $12.00** (1.5× the $8.00 reference) for **6 consecutive weekly readings** _with ladder rungs 1–2 already deployed_. **Then (Z), staged:** 1. **Within 7 days:** deploy rungs 3–4 (scene cap 8, Solo hourly cap −33%, homestead rest default-on) with the §4 honesty banner and a player comms note. These are player-visible; shipping them is a product decision made _now_, in this document, so the on-call isn't negotiating it mid-incident. 2. **Within 30 days:** re-route Clotho default Opus-class → Sonnet-class behind the full agent-behavior + safety eval gates (all `minimumPassRate: 1` suites must stay at 1; `value-refusal`, `persona`, `crisis`, `minor-protection` are non-negotiable). If the Sonnet route cannot hold the eval bar, this step is **rejected** and we proceed to 3. 3. **If cost remains > $12.00 for 8 further weeks, or step 2 fails evals:** executive go/no-go on V6 live-service posture — halt regional expansion, freeze Commons cognition growth (interest-management radius down, wild- agent foundry seeding paused), and a formal decision memo on continuing, re-scoping (Solo-only product), or sunsetting, with the unit economics in this document attached. **Emergency override:** trailing cost **> $20.00** (2.5×) for **2 consecutive weeks** at any time ⇒ rungs 3–4 plus Clotho hard cap 8 immediately, without waiting for the 6-week window. **Standing review:** this plan's prices (§1) re-verified quarterly against the provider price list; the reference model re-derived from staging telemetry at every release via `verify:v6 moirai-cost-load-readiness` (`V6/release/moirai-cost-load-readiness.v6release.json`), which remains the binding release gate. All scenario arithmetic above is reproducible from the tables in §1 — anyone disputing a number should be able to re-derive it on one page, which is the point.