peptide-repo/prautoblogger
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(cost): per-run cost governor — reserve-before-call enforcement

Browse Source 
Pipeline v2 Phase 1, commit 3/4. Cost_Governor reserves each call's
worst-case estimate (prompt chars/4 + max_tokens via the #18 pricing
chain) against the run ledger row with one atomic conditional UPDATE
(the #10 lock discipline) BEFORE dispatch, then settles to actuals after
each response; failed calls release their hold. Integrated inside
OpenRouter_Provider::send_chat_completion so EVERY text-LLM call path is
guarded with zero call-site changes; the image curl_multi batch reserves
its summed estimate in Image_Pipeline before generate_image_batch.

Breach: run halted (sticky), overage recorded, Cost_Ceiling_Exception
aborts the un-dispatched call, process_next_queued_article aborts the
remaining queued articles of halted/failed runs, and the Review Queue
shows a 'Halted runs' notice (runs halted pre-post have no draft to
list). Ceiling = prautoblogger_per_run_cost_ceiling_usd setting (default
constant $0.50, snapshotted at run start, 0 = disabled). Standalone
no-run calls, the monthly cap, and the AI Gateway path are unchanged.

Under-300: provider API-key fetch+validation moved verbatim to
OpenRouter_Request_Builder::resolve_api_key().

Agent-Session: pipeline-v2-phase1-engineer-20260612
This commit is contained in:
peptiderepo
2026-06-11 04:20:30 +00:00
parent 1b04809092
commit 04f09f5f24
13 changed files with 667 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
includes/core/class-image-pipeline.php
View File

@@ -125,6 +125,16 @@ class PRAutoBlogger_Image_Pipeline {
return $result;
}
// v0.18.0 — per-run governor: reserve the curl_multi batch's SUMMED
// worst-case estimate before dispatch (no-op outside a governed
// run). A breach halts the run and skips the whole batch.
try {
$batch_reservation = PRAutoBlogger_Cost_Governor::open_amount_reservation( $estimated_cost, 'image_batch' );
} catch ( PRAutoBlogger_Cost_Ceiling_Exception $e ) {
$result['errors'][] = $e->getMessage();
return $result;
}
// Build all prompts upfront (LLM calls happen here, sequentially).
$article_prompt = $this->prompt_builder->build_article_prompt( $article_data );
$batch_requests = array(
@@ -151,11 +161,19 @@ class PRAutoBlogger_Image_Pipeline {
try {
$batch_results = $this->provider->generate_image_batch( $batch_requests );
} catch ( \Throwable $e ) {
PRAutoBlogger_Cost_Governor::release( $batch_reservation );
PRAutoBlogger_Logger::instance()->error( 'Batch generation failed: ' . $e->getMessage(), 'image_pipeline' );
$result['errors'][] = $e->getMessage();
return $result;
}
// Settle the batch reservation to the actual per-image costs.
$actual_batch_cost = 0.0;
foreach ( $batch_results as $batch_entry ) {
$actual_batch_cost += (float) ( $batch_entry['cost_usd'] ?? 0 );
}
PRAutoBlogger_Cost_Governor::settle( $batch_reservation, $actual_batch_cost );
// Single-shot retry for any slot the provider flagged as NSFW-blocked.
if ( PRAutoBlogger_Image_NSFW_Retry::is_enabled() ) {
( new PRAutoBlogger_Image_NSFW_Retry( $this->provider, $this->prompt_builder ) )