Files
prautoblogger/tests/unit/Providers/OpenRouterPricingTest.php
peptiderepo e6e3f85542 fix(cost): resolve snapshot-suffixed model IDs to base pricing before conservative estimate
OpenRouter sometimes returns a dated snapshot ID as the response model
(request deepseek/deepseek-v4-flash -> response model
deepseek/deepseek-v4-flash-20260423). The pricing chain missed the
registry on those IDs and booked the conservative $10/$30 per-M
estimate: today's prod single-pass run logged $0.582 against a true
flash-tier cost of roughly 1-2 cents. Inflated actuals eat the
Cost_Governor per-run ceiling (default $0.50; today's run would have
halted) and the monthly $5 budget gate (~9 days to self-block).

Fix at the single pricing seam (OpenRouter_Pricing::estimate_cost):
on a lookup miss, strip a trailing 8-digit 20-prefixed -YYYYMMDD
snapshot suffix and retry the hardcoded table + cached models list
once with the base ID. The conservative fallback is unchanged when
the base ID is also unknown. Governor reserve/settle and
generation-log booking all price through this seam, so every path
survives snapshot IDs.

Tests: snapshot ID resolves to the base price when only the base ID
is registered; an unknown ID without a suffix still gets the
conservative estimate; a non-date trailing digit run (foo-202612345)
is never stripped.

Agent-Session: pipeline-v2-phase1-pricing-fix-20260611
2026-06-11 16:23:43 +07:00

266 lines
9.8 KiB
PHP

<?php
/**
* Tests for PRAutoBlogger_OpenRouter_Pricing.
*
* Validates the pricing API with instance methods for model prices and cost estimation.
*
* @package PRAutoBlogger\Tests\Providers
*/
namespace PRAutoBlogger\Tests\Providers;
use PRAutoBlogger\Tests\BaseTestCase;
use Brain\Monkey\Functions;
class OpenRouterPricingTest extends BaseTestCase {
/**
* @var \PHPUnit\Framework\MockObject\MockObject Mock $wpdb for Logger.
*/
private $wpdb;
protected function setUp(): void {
parent::setUp();
// Logger (called on unknown-model warning) accesses $wpdb->prefix and $wpdb->insert.
$this->wpdb = $this->create_mock_wpdb();
$this->wpdb->method( 'insert' )->willReturn( 1 );
$GLOBALS['wpdb'] = $this->wpdb;
// Stub get_option for Logger's log_level and Pricing's API key lookup.
$this->stub_get_option( [
'prautoblogger_log_level' => 'info',
'prautoblogger_openrouter_api_key' => '',
] );
// Stub current_time — used by Logger when writing log entries.
$this->stub_current_time( '2026-04-12 10:00:00' );
// OpenRouterPricing::get_available_models() calls get_transient() to check cache.
// Return a valid cached model list so it doesn't try to make HTTP calls.
Functions\when( 'get_transient' )->alias(
function ( string $key ) {
if ( 'prautoblogger_openrouter_models' === $key ) {
return [
[
'id' => 'google/gemini-2.0-flash-001',
'name' => 'Gemini 2.0 Flash',
'context_length' => 32768,
'pricing' => [ 'prompt' => 0.10, 'completion' => 0.40 ],
],
[
'id' => 'anthropic/claude-sonnet-4',
'name' => 'Claude Sonnet 4',
'context_length' => 200000,
'pricing' => [ 'prompt' => 3.00, 'completion' => 15.00 ],
],
];
}
return false;
}
);
Functions\when( 'set_transient' )->justReturn( true );
}
protected function tearDown(): void {
unset( $GLOBALS['wpdb'] );
parent::tearDown();
}
/**
* Test Pricing can be instantiated.
*/
public function test_openrouter_pricing_instantiation(): void {
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$this->assertInstanceOf( \PRAutoBlogger_OpenRouter_Pricing::class, $pricing );
}
/**
* Test get_available_models returns array.
*/
public function test_get_available_models_returns_array(): void {
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$models = $pricing->get_available_models();
$this->assertIsArray( $models );
}
/**
* Test get_available_models returns non-empty array.
*/
public function test_get_available_models_not_empty(): void {
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$models = $pricing->get_available_models();
$this->assertNotEmpty( $models );
}
/**
* Test estimate_cost returns float.
*/
public function test_estimate_cost_returns_float(): void {
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$cost = $pricing->estimate_cost( 'google/gemini-2.0-flash-001', 1000, 500 );
$this->assertIsFloat( $cost );
}
/**
* Test estimate_cost with zero tokens returns zero or non-negative.
*/
public function test_estimate_cost_with_zero_tokens(): void {
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$cost = $pricing->estimate_cost( 'google/gemini-2.0-flash-001', 0, 0 );
$this->assertIsFloat( $cost );
$this->assertGreaterThanOrEqual( 0.0, $cost );
}
/**
* Test estimate_cost with positive tokens.
*/
public function test_estimate_cost_with_positive_tokens(): void {
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$cost = $pricing->estimate_cost( 'google/gemini-2.0-flash-001', 1000, 1000 );
$this->assertIsFloat( $cost );
$this->assertGreaterThanOrEqual( 0.0, $cost );
}
/**
* Test estimate_cost with unknown model.
*/
public function test_estimate_cost_with_unknown_model(): void {
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$cost = $pricing->estimate_cost( 'unknown/fake-model', 1000, 500 );
// Unknown models may return 0.0 or a fallback value.
$this->assertIsFloat( $cost );
$this->assertGreaterThanOrEqual( 0.0, $cost );
}
/**
* Test estimate_cost consistency.
*/
public function test_estimate_cost_consistency(): void {
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$cost1 = $pricing->estimate_cost( 'google/gemini-2.0-flash-001', 1000, 500 );
$cost2 = $pricing->estimate_cost( 'google/gemini-2.0-flash-001', 1000, 500 );
// Same inputs should yield same results.
$this->assertSame( $cost1, $cost2 );
}
/**
* Test estimate_cost increases with tokens.
*/
public function test_estimate_cost_increases_with_tokens(): void {
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$cost_small = $pricing->estimate_cost( 'google/gemini-2.0-flash-001', 100, 100 );
$cost_large = $pricing->estimate_cost( 'google/gemini-2.0-flash-001', 1000, 1000 );
// Larger token counts should cost more or equal.
$this->assertGreaterThanOrEqual( $cost_small, $cost_large );
}
/**
* Test available models includes known OpenRouter models.
*/
public function test_available_models_includes_popular_models(): void {
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$models = $pricing->get_available_models();
// At least some models should be present.
$this->assertGreaterThan( 0, count( $models ) );
}
/**
* Test a snapshot-suffixed response model ID resolves to the base model's price.
*
* OpenRouter sometimes returns a dated snapshot ID as the response model
* (e.g. 'deepseek/deepseek-v4-flash-20260423' for a
* 'deepseek/deepseek-v4-flash' request). Pricing must strip the date
* suffix and bill at the base model's rate, not the conservative fallback.
*/
public function test_estimate_cost_snapshot_suffix_resolves_to_base_model_price(): void {
Functions\when( 'get_transient' )->alias(
function ( string $key ) {
if ( 'prautoblogger_openrouter_models' === $key ) {
return [
[
'id' => 'deepseek/deepseek-v4-flash',
'name' => 'DeepSeek V4 Flash',
'context_length' => 131072,
'pricing' => [ 'prompt' => 0.05, 'completion' => 0.20 ],
],
];
}
return false;
}
);
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$base_cost = $pricing->estimate_cost( 'deepseek/deepseek-v4-flash', 1000, 500 );
$snapshot_cost = $pricing->estimate_cost( 'deepseek/deepseek-v4-flash-20260423', 1000, 500 );
// Billed exactly like the base model: (1000 * 0.05 + 500 * 0.20) / 1M.
$this->assertSame( $base_cost, $snapshot_cost );
$this->assertEqualsWithDelta( 0.00015, $snapshot_cost, 1e-12 );
// And not at the conservative fallback rate (10/30 per M = 0.025 here).
$this->assertNotEquals( 0.025, $snapshot_cost );
}
/**
* Test an unknown model with no date suffix still gets the conservative estimate.
*/
public function test_estimate_cost_unknown_model_without_suffix_uses_conservative_estimate(): void {
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$cost = $pricing->estimate_cost( 'unknown/fake-model', 1000, 500 );
// Conservative fallback: (1000 * $10 + 500 * $30) / 1M.
$this->assertEqualsWithDelta( 0.025, $cost, 1e-12 );
}
/**
* Test a trailing digit run that is not an 8-digit date is never stripped.
*
* 'foo-202612345' has nine trailing digits — even with 'foo' and 'foo-2'
* registered, no stripping may occur and the conservative estimate applies.
*/
public function test_estimate_cost_non_date_suffix_is_not_stripped(): void {
Functions\when( 'get_transient' )->alias(
function ( string $key ) {
if ( 'prautoblogger_openrouter_models' === $key ) {
return [
[
'id' => 'foo',
'name' => 'Foo',
'context_length' => 8192,
'pricing' => [ 'prompt' => 0.01, 'completion' => 0.02 ],
],
[
'id' => 'foo-2',
'name' => 'Foo 2',
'context_length' => 8192,
'pricing' => [ 'prompt' => 0.01, 'completion' => 0.02 ],
],
];
}
return false;
}
);
$pricing = new \PRAutoBlogger_OpenRouter_Pricing();
$cost = $pricing->estimate_cost( 'foo-202612345', 1000, 500 );
// Nine trailing digits is not a snapshot date — conservative estimate applies.
$this->assertEqualsWithDelta( 0.025, $cost, 1e-12 );
}
}