mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
a3f84f3165
Haiku can't reliably emit the structured envelopes the lifecycle now runs on — pass_review's per-AC criteria_verified, delegate's covers_parent_criteria, the findings ledger. A haiku QA/PM claims, gets validation-rejected, idles, respawns, and loops without advancing a task (2026-07-24 live: fe-qa on haiku looped four awaiting_qa tasks to zero progress). The per-token savings (~2x under the Sonnet-5 promo, 3x after) are dwarfed by the cost of a review that never completes. Three coordinated changes: ROLE_MODEL_MAP's qa/documenter defaults move haiku -> sonnet (the actual source of the live incident); the cost_tiered developer:low -> haiku seed retires to empty (the floor would upgrade it anyway); and a structured-verb capability floor upgrades any below-floor Anthropic assignment to sonnet at resolution — from a pin, a ROLE row, or a future map edit — in both the assignment and legacy paths. Non-Anthropic providers are untouched (an Anthropic-tier floor, not a provider policy). pr_reviewer/auditor stay on opus. Co-authored-by: Renn F <rennf93@users.noreply.github.com>
37 lines
1.3 KiB
Python
37 lines
1.3 KiB
Python
"""MODEL_MAP resolves the short aliases to current, priced model ids."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from roboco.billing.pricing import calculate_cost
|
|
from roboco.models.runtime import MODEL_MAP, ROLE_MODEL_MAP
|
|
|
|
_M = 1_000_000
|
|
|
|
|
|
def test_sonnet_alias_resolves_to_sonnet_5() -> None:
|
|
assert MODEL_MAP["sonnet"] == "claude-sonnet-5"
|
|
|
|
|
|
def test_opus_alias_unchanged() -> None:
|
|
# CEO preference: stay on Opus 4.6 (4.7/4.8 not preferred).
|
|
assert MODEL_MAP["opus"] == "claude-opus-4-6"
|
|
|
|
|
|
def test_sonnet_5_is_priced() -> None:
|
|
# Guard against pointing an alias at an unpriced model (silent $0 cost-count).
|
|
cost = calculate_cost(MODEL_MAP["sonnet"], tokens_input=_M, tokens_output=0)
|
|
assert cost > 0.0
|
|
|
|
|
|
def test_no_lifecycle_role_routes_below_the_structured_verb_floor() -> None:
|
|
# Retired haiku from lifecycle roles (2026-07-24): a haiku QA/documenter
|
|
# can't emit the structured review envelopes (criteria_verified, findings)
|
|
# and loops without passing. No role's default may be a haiku-class tier.
|
|
for role, model in ROLE_MODEL_MAP.items():
|
|
assert "haiku" not in model.lower(), f"{role} routes to a below-floor {model}"
|
|
|
|
|
|
def test_main_pm_role_routes_to_sonnet() -> None:
|
|
# Phase 2 experiment: main_pm off Opus (Sonnet 5 cache-write ~12x cheaper).
|
|
assert ROLE_MODEL_MAP["main_pm"] == "sonnet"
|