External/roboco
1
0
Fork 0
mirror of https://github.com/rennf93/roboco.git synced 2026-08-03 07:23:24 +02:00
Code Issues Packages Projects Releases Wiki Activity
Files
f793f79659a5817c7838e8bf45929ba9684e3ae5
roboco/tests/unit/billing/test_pricing.py
T
Renzo FGitHubRenn F
 6374bbbed0 feat(kimi): Kimi K3 provider on the official kimi-code CLI (#713) 
* feat(kimi): Kimi K3 provider on the official kimi-code CLI (Wave 1)

ModelProvider.KIMI routes through KimiCliProvider driving Moonshot's kimi
CLI on a Kimi subscription (OAuth device-code, no metered key). One-shot
delivery roles only (V1), interactive ban wired in both guard lists.

Auth: one shared RW auth mount; containers symlink credentials/ and
oauth/ (the CLI's cross-process refresh-lock dir) into a container-local
KIMI_CODE_HOME so every container and the host redeem the SAME rotating
refresh chain - live-verified that per-copy chains cross-invalidate after
the reuse-grace window. No orchestrator refresh daemon; an expires_at
preflight exits 78.

Config renderer mirrors the login-managed provider/model blocks
field-for-field (live-captured; the model value is the CLI-side name,
never the raw API id), plus per-role deny rules and the bash-guard as a
PreToolUse hook via a wrapper script (an env key on a hooks entry makes
the CLI silently drop ALL hooks - live-verified). Usage capture sums
wire.jsonl usage.record 4-bucket events; sniff classifies rate-limit/auth
from structured error text only, mapped to the shared 75/78 park
contract. Image installs the CLI latest-at-build (no version pin, by
policy) with the resolved version stamped as provenance, binary split to
/usr/local away from mutable state.

Migrations 090 (enum) + 091 (provider seed); catalog, pricing, routing
mode, and orchestrator park/usage wiring mirror the codex integration.

* feat(kimi): surface sweep + fleet-wide pin drop (Wave 2)

Compose x3 gain the agent-kimi-image service and the orchestrator's
read-write ~/.kimi-code mount + kimi-usage dir; .env.example documents
the Kimi block. Panel mirrors ModelProvider.KIMI and adds the kimi
routing mode (catalog filter, mode button, mix-picker group, badge) with
tests; provider routes gain the kimi remediation entry. CLAUDE.md and
docs/map document the runtime. Per the no-pins policy, agent-grok/
gemini/codex Dockerfiles drop their version pins for latest-at-build
with resolved-version provenance stamps (grok resolves 0.2.112 vs the
old 0.2.56 pin - verified by real builds of all four images).

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
2026-07-29 01:48:55 +02:00

835 lines
31 KiB
Python
Raw Blame History

"""
Unit tests for roboco.billing.pricing — calculate_cost().
Covers:
- Each model tier (opus, sonnet, haiku) with all 4 token types.
- Unknown model name returns 0.0 without raising.
- Empty model string returns 0.0 without raising.
- Substring match correctness: longer fragment wins
(e.g. 'claude-sonnet-4-6' matches 'claude-sonnet-4' not bare 'sonnet';
'claude-sonnet-5' matches its own promo entry).
"""
from __future__ import annotations
from datetime import date
import pytest
from roboco.billing import pricing as p
from roboco.billing.pricing import (
CostResult,
_is_anthropic_model,
calculate_cost,
calculate_cost_result,
input_price_per_million,
is_ollama_cloud_model,
)
# ---------------------------------------------------------------------------
# Named constants (ruff PLR2004: magic values in comparisons must be named).
# ---------------------------------------------------------------------------
# Token counts
_M = 1_000_000 # 1 million tokens
# Pricing — per-1M USD, matches the _PRICING table in pricing.py
_OPUS_INPUT = 5.00
_OPUS_OUTPUT = 25.00
_OPUS_CACHE_READ = 0.50
_OPUS_CACHE_WRITE = 6.25
_SONNET_INPUT = 3.00
_SONNET_OUTPUT = 15.00
_SONNET_CACHE_READ = 0.30
_SONNET_CACHE_WRITE = 0.75
# Sonnet 5 — promotional pricing (33% off Sonnet 4.6, pay 67%) through 2026-08-31
_SONNET5_INPUT = 2.01
_SONNET5_OUTPUT = 10.05
_SONNET5_CACHE_READ = 0.201
_SONNET5_CACHE_WRITE = 0.5025
_HAIKU_INPUT = 1.00
_HAIKU_OUTPUT = 5.00
_HAIKU_CACHE_READ = 0.10
_HAIKU_CACHE_WRITE = 1.25
_HAIKU3_INPUT = 0.25 # claude-haiku-3 is cheaper than haiku-3-5 / haiku-4
# xAI Grok — priced non-Anthropic (per the xAI API)
_GROK_INPUT = 1.00
_GROK_OUTPUT = 2.00
_GROK_CACHE_READ = 0.20
_GROK_CACHE_WRITE = 1.00
# OpenAI Codex — priced non-Anthropic (ChatGPT-subscription CLI, priced here
# for cost attribution)
_CODEX_INPUT = 1.75
_CODEX_OUTPUT = 14.00
_CODEX_CACHE_READ = 0.175
_CODEX_CACHE_WRITE = 1.75
# Z.ai GLM-5.2 — priced non-Anthropic (Ollama Cloud's `glm-5.2:cloud` tag,
# subscription-billed but attributed at the API-equivalent rate). Source:
# https://docs.z.ai/guides/overview/pricing (fetched 2026-07-23).
_GLM_INPUT = 1.40
_GLM_OUTPUT = 4.40
_GLM_CACHE_READ = 0.26
_GLM_CACHE_WRITE = 1.40
# Moonshot Kimi — priced non-Anthropic (kimi-code CLI subscription, priced
# here for cost attribution like grok-build/gpt-5.3-codex).
_KIMI_K3_INPUT = 3.00
_KIMI_K3_OUTPUT = 15.00
_KIMI_K3_CACHE_READ = 0.30
_KIMI_K3_CACHE_WRITE = 3.00
_KIMI_CODING_INPUT = 0.95
_KIMI_CODING_OUTPUT = 4.00
_KIMI_CODING_CACHE_READ = 0.19
_KIMI_CODING_CACHE_WRITE = 0.95
_KIMI_CODING_HIGHSPEED_INPUT = 1.90
_KIMI_CODING_HIGHSPEED_OUTPUT = 8.00
_KIMI_CODING_HIGHSPEED_CACHE_READ = 0.38
_KIMI_CODING_HIGHSPEED_CACHE_WRITE = 1.90
# Tolerance for floating-point comparisons
_TOL = 1e-4
# ---------------------------------------------------------------------------
# Opus tier
# ---------------------------------------------------------------------------
class TestOpusTier:
"""claude-opus-4 family pricing."""
def test_input_only(self) -> None:
cost = calculate_cost("claude-opus-4-5", tokens_input=_M, tokens_output=0)
assert abs(cost - _OPUS_INPUT) < _TOL
def test_output_only(self) -> None:
cost = calculate_cost("claude-opus-4-5", tokens_input=0, tokens_output=_M)
assert abs(cost - _OPUS_OUTPUT) < _TOL
def test_cache_read_only(self) -> None:
cost = calculate_cost(
"claude-opus-4-5",
tokens_input=0,
tokens_output=0,
tokens_cache_read=_M,
)
assert abs(cost - _OPUS_CACHE_READ) < _TOL
def test_cache_write_only(self) -> None:
cost = calculate_cost(
"claude-opus-4-5",
tokens_input=0,
tokens_output=0,
tokens_cache_write=_M,
)
assert abs(cost - _OPUS_CACHE_WRITE) < _TOL
def test_all_token_types(self) -> None:
cost = calculate_cost(
"claude-opus-4-5",
tokens_input=_M,
tokens_output=_M,
tokens_cache_read=_M,
tokens_cache_write=_M,
)
expected = _OPUS_INPUT + _OPUS_OUTPUT + _OPUS_CACHE_READ + _OPUS_CACHE_WRITE
assert abs(cost - expected) < _TOL
def test_short_alias(self) -> None:
"""Bare 'opus' alias resolves to the opus tier."""
cost = calculate_cost("opus", tokens_input=_M, tokens_output=0)
assert abs(cost - _OPUS_INPUT) < _TOL
def test_returns_float(self) -> None:
cost = calculate_cost("claude-opus-4", tokens_input=100, tokens_output=50)
assert isinstance(cost, float)
# ---------------------------------------------------------------------------
# Sonnet tier
# ---------------------------------------------------------------------------
class TestSonnetTier:
"""claude-sonnet-4 family pricing (full rate — pre-promo / historical)."""
def test_input_only(self) -> None:
cost = calculate_cost("claude-sonnet-4-6", tokens_input=_M, tokens_output=0)
assert abs(cost - _SONNET_INPUT) < _TOL
def test_output_only(self) -> None:
cost = calculate_cost("claude-sonnet-4-6", tokens_input=0, tokens_output=_M)
assert abs(cost - _SONNET_OUTPUT) < _TOL
def test_cache_read_only(self) -> None:
cost = calculate_cost(
"claude-sonnet-4-6",
tokens_input=0,
tokens_output=0,
tokens_cache_read=_M,
)
assert abs(cost - _SONNET_CACHE_READ) < _TOL
def test_cache_write_only(self) -> None:
cost = calculate_cost(
"claude-sonnet-4-6",
tokens_input=0,
tokens_output=0,
tokens_cache_write=_M,
)
assert abs(cost - _SONNET_CACHE_WRITE) < _TOL
def test_all_token_types(self) -> None:
cost = calculate_cost(
"claude-sonnet-4-6",
tokens_input=_M,
tokens_output=_M,
tokens_cache_read=_M,
tokens_cache_write=_M,
)
expected = (
_SONNET_INPUT + _SONNET_OUTPUT + _SONNET_CACHE_READ + _SONNET_CACHE_WRITE
)
assert abs(cost - expected) < _TOL
def test_short_alias(self) -> None:
"""Bare 'sonnet' alias resolves to the sonnet tier."""
cost = calculate_cost("sonnet", tokens_input=_M, tokens_output=0)
assert abs(cost - _SONNET_INPUT) < _TOL
def test_35_variant(self) -> None:
"""claude-3-5-sonnet resolves to sonnet tier."""
cost = calculate_cost(
"claude-3-5-sonnet-20241022", tokens_input=_M, tokens_output=0
)
assert abs(cost - _SONNET_INPUT) < _TOL
class TestSonnet5PromoTier:
"""claude-sonnet-5 promotional pricing — 33% off Sonnet 4.6 (through
2026-08-31). A dedicated table entry wins over the bare 'sonnet' fragment."""
def test_input_only(self) -> None:
cost = calculate_cost("claude-sonnet-5", tokens_input=_M, tokens_output=0)
assert abs(cost - _SONNET5_INPUT) < _TOL
def test_output_only(self) -> None:
cost = calculate_cost("claude-sonnet-5", tokens_input=0, tokens_output=_M)
assert abs(cost - _SONNET5_OUTPUT) < _TOL
def test_cache_read_only(self) -> None:
cost = calculate_cost(
"claude-sonnet-5", tokens_input=0, tokens_output=0, tokens_cache_read=_M
)
assert abs(cost - _SONNET5_CACHE_READ) < _TOL
def test_cache_write_only(self) -> None:
cost = calculate_cost(
"claude-sonnet-5", tokens_input=0, tokens_output=0, tokens_cache_write=_M
)
assert abs(cost - _SONNET5_CACHE_WRITE) < _TOL
def test_all_token_types(self) -> None:
cost = calculate_cost(
"claude-sonnet-5",
tokens_input=_M,
tokens_output=_M,
tokens_cache_read=_M,
tokens_cache_write=_M,
)
expected = (
_SONNET5_INPUT
+ _SONNET5_OUTPUT
+ _SONNET5_CACHE_READ
+ _SONNET5_CACHE_WRITE
)
assert abs(cost - expected) < _TOL
def test_cheaper_than_sonnet4(self) -> None:
"""The promo must actually be cheaper than full Sonnet 4.6."""
five = calculate_cost("claude-sonnet-5", tokens_input=_M, tokens_output=_M)
four = calculate_cost("claude-sonnet-4-6", tokens_input=_M, tokens_output=_M)
assert five < four
def test_dated_variant_matches_promo(self) -> None:
"""A dated 'claude-sonnet-5-*' id still resolves to the promo entry."""
cost = calculate_cost(
"claude-sonnet-5-20260930", tokens_input=_M, tokens_output=0
)
assert abs(cost - _SONNET5_INPUT) < _TOL
# ---------------------------------------------------------------------------
# Haiku tier
# ---------------------------------------------------------------------------
class TestHaikuTier:
"""claude-haiku family pricing."""
def test_input_only(self) -> None:
cost = calculate_cost("claude-haiku-4-5", tokens_input=_M, tokens_output=0)
assert abs(cost - _HAIKU_INPUT) < _TOL
def test_output_only(self) -> None:
cost = calculate_cost("claude-haiku-4-5", tokens_input=0, tokens_output=_M)
assert abs(cost - _HAIKU_OUTPUT) < _TOL
def test_cache_read_only(self) -> None:
cost = calculate_cost(
"claude-haiku-4-5",
tokens_input=0,
tokens_output=0,
tokens_cache_read=_M,
)
assert abs(cost - _HAIKU_CACHE_READ) < _TOL
def test_cache_write_only(self) -> None:
cost = calculate_cost(
"claude-haiku-4-5",
tokens_input=0,
tokens_output=0,
tokens_cache_write=_M,
)
assert abs(cost - _HAIKU_CACHE_WRITE) < _TOL
def test_all_token_types(self) -> None:
cost = calculate_cost(
"claude-haiku-4-5",
tokens_input=_M,
tokens_output=_M,
tokens_cache_read=_M,
tokens_cache_write=_M,
)
expected = _HAIKU_INPUT + _HAIKU_OUTPUT + _HAIKU_CACHE_READ + _HAIKU_CACHE_WRITE
assert abs(cost - expected) < _TOL
def test_short_alias(self) -> None:
"""Bare 'haiku' alias resolves to the haiku tier."""
cost = calculate_cost("haiku", tokens_input=_M, tokens_output=0)
assert abs(cost - _HAIKU_INPUT) < _TOL
def test_haiku3_variant(self) -> None:
"""claude-haiku-3 has lower pricing than haiku-3-5."""
cost = calculate_cost("claude-haiku-3", tokens_input=_M, tokens_output=0)
assert abs(cost - _HAIKU3_INPUT) < _TOL
# ---------------------------------------------------------------------------
# Grok tier (xAI — priced non-Anthropic)
# ---------------------------------------------------------------------------
class TestGrokTier:
"""grok-build-0.1 pricing — a non-Anthropic model that IS billed per token."""
def test_input_only(self) -> None:
cost = calculate_cost("grok-build-0.1", tokens_input=_M, tokens_output=0)
assert abs(cost - _GROK_INPUT) < _TOL
def test_output_only(self) -> None:
cost = calculate_cost("grok-build-0.1", tokens_input=0, tokens_output=_M)
assert abs(cost - _GROK_OUTPUT) < _TOL
def test_cached_input(self) -> None:
cost = calculate_cost(
"grok-build-0.1", tokens_input=0, tokens_output=0, tokens_cache_read=_M
)
assert abs(cost - _GROK_CACHE_READ) < _TOL
def test_all_token_types(self) -> None:
cost = calculate_cost(
"grok-build-0.1",
tokens_input=_M,
tokens_output=_M,
tokens_cache_read=_M,
tokens_cache_write=_M,
)
expected = _GROK_INPUT + _GROK_OUTPUT + _GROK_CACHE_READ + _GROK_CACHE_WRITE
assert abs(cost - expected) < _TOL
def test_grok_is_not_treated_as_anthropic(self) -> None:
"""Priced, but not an Anthropic model (no warn-on-unpriced path)."""
assert _is_anthropic_model("grok-build-0.1") is False
# Still resolves to a real (non-zero) per-token cost.
assert calculate_cost("grok-build-0.1", tokens_input=_M, tokens_output=0) > 0.0
# ---------------------------------------------------------------------------
# Codex tier (OpenAI — priced non-Anthropic)
# ---------------------------------------------------------------------------
class TestCodexTier:
"""gpt-5.3-codex pricing — a real input/output split, unlike grok's fold."""
def test_input_only(self) -> None:
cost = calculate_cost("gpt-5.3-codex", tokens_input=_M, tokens_output=0)
assert abs(cost - _CODEX_INPUT) < _TOL
def test_output_only(self) -> None:
cost = calculate_cost("gpt-5.3-codex", tokens_input=0, tokens_output=_M)
assert abs(cost - _CODEX_OUTPUT) < _TOL
def test_cached_input(self) -> None:
cost = calculate_cost(
"gpt-5.3-codex", tokens_input=0, tokens_output=0, tokens_cache_read=_M
)
assert abs(cost - _CODEX_CACHE_READ) < _TOL
def test_cache_write(self) -> None:
cost = calculate_cost(
"gpt-5.3-codex", tokens_input=0, tokens_output=0, tokens_cache_write=_M
)
assert abs(cost - _CODEX_CACHE_WRITE) < _TOL
def test_all_token_types(self) -> None:
cost = calculate_cost(
"gpt-5.3-codex",
tokens_input=_M,
tokens_output=_M,
tokens_cache_read=_M,
tokens_cache_write=_M,
)
expected = _CODEX_INPUT + _CODEX_OUTPUT + _CODEX_CACHE_READ + _CODEX_CACHE_WRITE
assert abs(cost - expected) < _TOL
def test_codex_is_not_treated_as_anthropic(self) -> None:
assert _is_anthropic_model("gpt-5.3-codex") is False
assert calculate_cost("gpt-5.3-codex", tokens_input=_M, tokens_output=0) > 0.0
def test_output_is_pricier_than_input(self) -> None:
# Codex's real split makes output 8x input — the property grok's
# single-total fold structurally cannot express.
assert _CODEX_OUTPUT > _CODEX_INPUT
# ---------------------------------------------------------------------------
# Kimi tier (Moonshot — priced non-Anthropic, four login-managed aliases)
# ---------------------------------------------------------------------------
class TestKimiTier:
"""kimi-code/* pricing — cache_write folds to the input rate, same
convention as grok-build/gpt-5.3-codex (no published cache-write discount)."""
def test_k3_all_token_types(self) -> None:
cost = calculate_cost(
"kimi-code/k3",
tokens_input=_M,
tokens_output=_M,
tokens_cache_read=_M,
tokens_cache_write=_M,
)
expected = (
_KIMI_K3_INPUT
+ _KIMI_K3_OUTPUT
+ _KIMI_K3_CACHE_READ
+ _KIMI_K3_CACHE_WRITE
)
assert abs(cost - expected) < _TOL
def test_k3_256k_prices_the_same_as_k3(self) -> None:
# "kimi-code/k3" is a PREFIX of "kimi-code/k3-256k" — longest-fragment
# wins in _lookup_prices must resolve the 256k alias to its own entry,
# not silently fall through to the bare k3 fragment (same rates here,
# but the resolution path is what's under test).
cost = calculate_cost("kimi-code/k3-256k", tokens_input=_M, tokens_output=0)
assert abs(cost - _KIMI_K3_INPUT) < _TOL
def test_kimi_for_coding_all_token_types(self) -> None:
cost = calculate_cost(
"kimi-code/kimi-for-coding",
tokens_input=_M,
tokens_output=_M,
tokens_cache_read=_M,
tokens_cache_write=_M,
)
expected = (
_KIMI_CODING_INPUT
+ _KIMI_CODING_OUTPUT
+ _KIMI_CODING_CACHE_READ
+ _KIMI_CODING_CACHE_WRITE
)
assert abs(cost - expected) < _TOL
def test_kimi_for_coding_highspeed_resolves_its_own_longer_fragment(self) -> None:
# "kimi-code/kimi-for-coding" is a PREFIX of
# "kimi-code/kimi-for-coding-highspeed" — longest-fragment-wins must
# resolve the highspeed alias to its OWN (pricier) rate, not the base
# coding tier's cheaper one.
cost = calculate_cost(
"kimi-code/kimi-for-coding-highspeed", tokens_input=_M, tokens_output=0
)
assert abs(cost - _KIMI_CODING_HIGHSPEED_INPUT) < _TOL
assert cost > calculate_cost(
"kimi-code/kimi-for-coding", tokens_input=_M, tokens_output=0
)
def test_kimi_is_not_treated_as_anthropic(self) -> None:
assert _is_anthropic_model("kimi-code/k3") is False
assert calculate_cost("kimi-code/k3", tokens_input=_M, tokens_output=0) > 0.0
def test_output_is_pricier_than_input(self) -> None:
assert _KIMI_K3_OUTPUT > _KIMI_K3_INPUT
assert _KIMI_CODING_OUTPUT > _KIMI_CODING_INPUT
assert _KIMI_CODING_HIGHSPEED_OUTPUT > _KIMI_CODING_HIGHSPEED_INPUT
# ---------------------------------------------------------------------------
# GLM-5.2 tier (Ollama Cloud — priced non-Anthropic, grounded in a citable
# published rate; see the module's pricing-table comment for the source).
# ---------------------------------------------------------------------------
class TestGlmTier:
"""glm-5.2:cloud pricing — Ollama Cloud, priced like grok-build/codex."""
def test_input_only(self) -> None:
cost = calculate_cost("glm-5.2:cloud", tokens_input=_M, tokens_output=0)
assert abs(cost - _GLM_INPUT) < _TOL
def test_output_only(self) -> None:
cost = calculate_cost("glm-5.2:cloud", tokens_input=0, tokens_output=_M)
assert abs(cost - _GLM_OUTPUT) < _TOL
def test_cached_input(self) -> None:
cost = calculate_cost(
"glm-5.2:cloud", tokens_input=0, tokens_output=0, tokens_cache_read=_M
)
assert abs(cost - _GLM_CACHE_READ) < _TOL
def test_cache_write(self) -> None:
cost = calculate_cost(
"glm-5.2:cloud", tokens_input=0, tokens_output=0, tokens_cache_write=_M
)
assert abs(cost - _GLM_CACHE_WRITE) < _TOL
def test_all_token_types(self) -> None:
cost = calculate_cost(
"glm-5.2:cloud",
tokens_input=_M,
tokens_output=_M,
tokens_cache_read=_M,
tokens_cache_write=_M,
)
expected = _GLM_INPUT + _GLM_OUTPUT + _GLM_CACHE_READ + _GLM_CACHE_WRITE
assert abs(cost - expected) < _TOL
def test_glm_is_not_treated_as_anthropic(self) -> None:
assert _is_anthropic_model("glm-5.2:cloud") is False
assert calculate_cost("glm-5.2:cloud", tokens_input=_M, tokens_output=0) > 0.0
def test_bare_glm_tag_without_cloud_suffix_still_prices(self) -> None:
"""The fragment match is on 'glm-5.2', independent of the ':cloud'
tag suffix — a differently-tagged variant still resolves."""
cost = calculate_cost("glm-5.2", tokens_input=_M, tokens_output=0)
assert abs(cost - _GLM_INPUT) < _TOL
# ---------------------------------------------------------------------------
# Unknown / edge cases — must return 0.0 without raising
# ---------------------------------------------------------------------------
class TestUnknownModels:
def test_unknown_model_name_returns_zero(self) -> None:
cost = calculate_cost("gpt-4o", tokens_input=_M, tokens_output=_M)
assert cost == 0.0
def test_empty_string_returns_zero(self) -> None:
cost = calculate_cost("", tokens_input=_M, tokens_output=_M)
assert cost == 0.0
def test_gibberish_returns_zero(self) -> None:
cost = calculate_cost(
"totally-unknown-model-xyz", tokens_input=100, tokens_output=100
)
assert cost == 0.0
def test_zero_tokens_with_unknown_model_returns_zero(self) -> None:
cost = calculate_cost("unknown", tokens_input=0, tokens_output=0)
assert cost == 0.0
def test_does_not_raise_on_unknown_model(self) -> None:
"""Must not raise regardless of token counts."""
try:
calculate_cost(
"not-a-claude-model",
tokens_input=999_999,
tokens_output=999_999,
)
except Exception as exc:
pytest.fail(f"calculate_cost raised unexpectedly: {exc}")
# ---------------------------------------------------------------------------
# Substring match correctness
# ---------------------------------------------------------------------------
# Named constants for the comparison floor/ceiling used in these tests.
_ZERO_COST = 0.0
_SONNET_CHEAPER_THAN_OPUS = True # structural assertion in the test below
class TestSubstringMatchPriority:
def test_claude_sonnet_4_resolves_non_zero(self) -> None:
"""'claude-sonnet-4-6' must find a match (non-zero cost)."""
cost = calculate_cost("claude-sonnet-4-6", tokens_input=_M, tokens_output=0)
assert cost > _ZERO_COST
def test_haiku3_cheaper_than_haiku4(self) -> None:
"""claude-haiku-3 is cheaper than claude-haiku-4 — longest-match wins."""
haiku3_cost = calculate_cost("claude-haiku-3", tokens_input=_M, tokens_output=0)
haiku4_cost = calculate_cost("claude-haiku-4", tokens_input=_M, tokens_output=0)
# haiku-3 ($0.25/1M) < haiku-4 ($1.00/1M)
assert haiku3_cost < haiku4_cost
def test_non_claude_model_returns_zero(self) -> None:
"""A random non-Claude model must not match any Claude pricing entry."""
non_opus_cost = calculate_cost("llama-3-70b", tokens_input=_M, tokens_output=0)
assert non_opus_cost == _ZERO_COST
def test_opus_model_non_zero(self) -> None:
"""Claude opus model resolves to non-zero cost."""
opus_cost = calculate_cost("claude-opus-4", tokens_input=_M, tokens_output=0)
assert opus_cost > _ZERO_COST
def test_zero_tokens_returns_zero_for_known_model(self) -> None:
"""Known model with 0 tokens has 0 cost."""
cost = calculate_cost("claude-opus-4", tokens_input=0, tokens_output=0)
assert cost == _ZERO_COST
def test_case_insensitive_matching(self) -> None:
"""Model name matching is case-insensitive."""
lower_cost = calculate_cost(
"claude-sonnet-5", tokens_input=1000, tokens_output=1000
)
upper_cost = calculate_cost(
"CLAUDE-SONNET-5", tokens_input=1000, tokens_output=1000
)
assert lower_cost == upper_cost
assert lower_cost > _ZERO_COST
# ---------------------------------------------------------------------------
# Provider awareness — non-Anthropic models have no per-token cost
# ---------------------------------------------------------------------------
class TestProviderAwareness:
"""Genuinely-free local Ollama costs 0.0 per token; an ungrounded Ollama
Cloud model also costs 0.0 (we have no rate for it — see
``is_ollama_cloud_model`` for the caller-side distinction from "free"). A
GROUNDED Ollama Cloud model (glm-5.2) is priced for real — see
``TestGlmTier``."""
def test_ollama_prefixed_model_returns_zero(self) -> None:
"""Self-hosted Ollama models (``ollama/`` prefix) have no API cost."""
cost = calculate_cost("ollama/llama3", tokens_input=_M, tokens_output=_M)
assert cost == _ZERO_COST
def test_ungrounded_ollama_cloud_model_returns_zero(self) -> None:
"""An Ollama Cloud (``:cloud`` tag) model with no table entry has no
rate to price from — still 0.0 (not "unpriced"; see TestCostResult)."""
cost = calculate_cost(
"some-future-model:cloud", tokens_input=_M, tokens_output=_M
)
assert cost == _ZERO_COST
def test_bare_local_model_returns_zero(self) -> None:
"""A bare local embedding model has no per-token cost."""
cost = calculate_cost("qwen3-embedding:0.6b", tokens_input=_M, tokens_output=0)
assert cost == _ZERO_COST
def test_is_anthropic_model_true_for_claude_names(self) -> None:
for name in ("claude-opus-5", "claude-fable-5", "opus", "sonnet", "haiku"):
assert _is_anthropic_model(name) is True, name
def test_is_anthropic_model_false_for_non_claude_names(self) -> None:
for name in ("ollama/llama3", "glm-5.2:cloud", "qwen3-embedding", "gpt-4o"):
assert _is_anthropic_model(name) is False, name
# ---------------------------------------------------------------------------
# Structured cost result — distinguish unpriced Anthropic from genuinely-free
# (#65). ``calculate_cost`` keeps returning a plain float for existing callers;
# ``calculate_cost_result`` returns a ``CostResult`` so a caller can tell real
# spend we failed to price ($0, unpriced=True) apart from local inference
# ($0, unpriced=False).
# ---------------------------------------------------------------------------
class TestCostResult:
def test_unpriced_anthropic_model_is_flagged(self) -> None:
result = calculate_cost_result(
"claude-brand-new-unpriced", tokens_input=_M, tokens_output=0
)
assert isinstance(result, CostResult)
assert result.cost_usd == 0.0
assert result.unpriced is True
assert result.is_anthropic is True
def test_free_non_anthropic_model_is_not_unpriced(self) -> None:
result = calculate_cost_result(
"ollama/qwen3-embedding", tokens_input=_M, tokens_output=0
)
assert result.cost_usd == 0.0
assert result.unpriced is False
assert result.is_anthropic is False
def test_priced_anthropic_model_is_not_unpriced(self) -> None:
result = calculate_cost_result(
"claude-sonnet-5", tokens_input=_M, tokens_output=0
)
assert result.cost_usd > 0.0
assert result.unpriced is False
def test_priced_non_anthropic_grok_is_not_unpriced(self) -> None:
result = calculate_cost_result(
"grok-build-0.1", tokens_input=_M, tokens_output=0
)
assert result.cost_usd > 0.0
assert result.unpriced is False
assert result.is_anthropic is False
def test_priced_non_anthropic_codex_is_not_unpriced(self) -> None:
result = calculate_cost_result(
"gpt-5.3-codex", tokens_input=_M, tokens_output=0
)
assert result.cost_usd > 0.0
assert result.unpriced is False
assert result.is_anthropic is False
def test_priced_non_anthropic_kimi_is_not_unpriced(self) -> None:
result = calculate_cost_result("kimi-code/k3", tokens_input=_M, tokens_output=0)
assert result.cost_usd > 0.0
assert result.unpriced is False
assert result.is_anthropic is False
def test_calculate_cost_matches_structured_cost_usd(self) -> None:
model = "claude-opus-5"
assert (
calculate_cost(model, tokens_input=_M, tokens_output=_M)
== calculate_cost_result(model, tokens_input=_M, tokens_output=_M).cost_usd
)
def test_empty_model_is_not_unpriced(self) -> None:
# An empty model name is a caller bug, not an unpriced-Anthropic miss.
result = calculate_cost_result("", tokens_input=_M, tokens_output=0)
assert result.cost_usd == 0.0
assert result.unpriced is False
# ---------------------------------------------------------------------------
# Sonnet-5 promo date gate — promo on/ before 2026-08-31, list rate after.
# ---------------------------------------------------------------------------
def test_sonnet5_promo_active_on_or_before_2026_08_31(
monkeypatch: pytest.MonkeyPatch,
) -> None:
class _D:
@staticmethod
def today() -> date:
return date(2026, 8, 31)
monkeypatch.setattr(p, "date", _D)
assert p._lookup_prices("claude-sonnet-5") == (
_SONNET5_INPUT,
_SONNET5_OUTPUT,
_SONNET5_CACHE_READ,
_SONNET5_CACHE_WRITE,
)
class TestIsOllamaCloudModel:
"""The ':cloud' tag convention, shared by pricing.py's own attribution
logic and external callers (the TG cockpit's spend label)."""
def test_cloud_tagged_model_is_cloud(self) -> None:
assert is_ollama_cloud_model("glm-5.2:cloud") is True
assert is_ollama_cloud_model("SOME-MODEL:CLOUD") is True
def test_local_model_is_not_cloud(self) -> None:
assert is_ollama_cloud_model("ollama/llama3") is False
assert is_ollama_cloud_model("qwen3-embedding:0.6b") is False
def test_anthropic_model_is_not_cloud(self) -> None:
assert is_ollama_cloud_model("claude-sonnet-5") is False
def test_empty_string_is_not_cloud(self) -> None:
assert is_ollama_cloud_model("") is False
def test_sonnet5_reverts_to_list_rate_after_2026_08_31(
monkeypatch: pytest.MonkeyPatch,
) -> None:
class _D:
@staticmethod
def today() -> date:
return date(2026, 9, 1)
monkeypatch.setattr(p, "date", _D)
assert p._lookup_prices("claude-sonnet-5") == (
_SONNET_INPUT,
_SONNET_OUTPUT,
_SONNET_CACHE_READ,
_SONNET_CACHE_WRITE,
)
# ---------------------------------------------------------------------------
# input_price_per_million — the cost-tiered complexity-override comparator
# ---------------------------------------------------------------------------
class TestInputPricePerMillion:
"""The downgrade-only comparator for complexity overrides (no explicit
tier ordering exists in the model catalog, so the input rate stands in
for "which tier is costlier")."""
def test_orders_haiku_below_sonnet_below_opus(self) -> None:
assert (
input_price_per_million("haiku")
< input_price_per_million("sonnet")
< input_price_per_million("opus")
)
def test_matches_pricing_table_value(self) -> None:
assert input_price_per_million("haiku") == _HAIKU_INPUT
assert input_price_per_million("sonnet") == _SONNET_INPUT
assert input_price_per_million("opus") == _OPUS_INPUT
def test_grok_priced_below_sonnet(self) -> None:
"""Grok legitimately downgrades-from sonnet under this comparator."""
assert input_price_per_million("grok-build-0.1") < input_price_per_million(
"sonnet"
)
def test_unpriced_non_anthropic_model_is_free_tier(self) -> None:
"""A self-hosted / ungrounded-Ollama-Cloud model has no per-token
rate — treated as the cheapest possible tier, so it can never be
rejected as "costlier" by the downgrade-only policy."""
assert input_price_per_million("some-future-model:cloud") == 0.0
assert input_price_per_million("my-custom-self-hosted-model:7b") == 0.0
def test_grounded_ollama_cloud_model_has_real_rate(self) -> None:
"""GLM-5.2 is now grounded in a real published rate, unlike an
unpriced Ollama Cloud model."""
assert input_price_per_million("glm-5.2:cloud") == _GLM_INPUT
def test_empty_model_returns_zero(self) -> None:
assert input_price_per_million("") == 0.0
def test_case_insensitive(self) -> None:
assert input_price_per_million("HAIKU") == input_price_per_million("haiku")
Reference in New Issue View Git Blame Copy Permalink