R1: move phpcs:ignore out of SQL string in class-analysis-prompts.php:81
(same pattern as v0.18.2 cost-reporter fix). GA4 self-improvement loop
has returned empty context on every pipeline run since v0.16.0 — this
restores get_performance_context() to the LLM. Sibling occurrence also
fixed in class-post-assembler.php:112.
R2(a): update_generation_stage() now renews STATUS_TTL on every stage call
so the transient outlasts long LLM calls during background runs.
R2(b): on_ajax_generation_status() detects lock-held-but-transient-gone
when lock age > STATUS_TTL (= Hostinger background-process kill).
Marks stuck run failed, releases lock, returns status:error with
'infrastructure timeout' message. Daily reaper remains the backstop.
R3: when transient absent but lock held within TTL, return status:running
(with started_at from lock) instead of status:idle.
Executor split: class-executor.php was 351 lines (>300). AJAX generation
handlers extracted to new class-generation-status-poller.php (260 lines);
executor now 226 lines. Public hook wiring unchanged via delegation.
Generation_Lock gains get_acquired_at() for R2b/R3 lock-age checks.
Tests: AnalysisPromptsTest (regression SQL + behavioral context shaping),
GenerationStatusPollerTest (R2a TTL renewal, R2b abort, R3 running,
idle path).
Closes: R1 (analysis-prompts SQL), R2 (manual-run resilience), R3 (honest status)
Version: 0.18.3
Agent-Session: prab-v0183-20260612
Pipeline v2 Phase 1, commit 2/4. Prompt_Registry (read) +
Prompt_Registry_Writer (immutable create/activate/seed) over the new
prompts table; canonical v1 bodies extracted verbatim into
Prompt_Defaults(+Editorial) — single source for BOTH the seed migration
(Migrate_Prompt_Seed_V0180, flag-gated, self-healing) and the in-code
fallback, so a missing table renders byte-identical prompts and never
fatals. Call sites swapped: Content_Prompts, Analysis_Prompts,
Chief_Editor, LLM_Research_Provider. Includes the image-composer seam
keys image.rewriter_system + image.style_template (composer PR consumes,
must not add its own prompt storage).
Pinning: Cost_Tracker::set_run_id() registers the process run context,
ensures the runs ledger row, and pins active versions once per run;
log_api_call/log_image_generation stamp prompt_version (run pins) +
agent_role (stage map) on every generation_log row. Single-pass keeps
stage 'draft' and stamps content.single_pass explicitly.
Under-300 refactors: Content_Generator's four duplicated span/log blocks
consolidated into execute_stage() (301 -> 224 lines, behavior
identical); get_avg_tokens_for_stages body moved to Cost_Reporter with a
delegating wrapper kept for API compatibility.
Tests: byte-identical fallback renders (single_pass/outline/polish/
editor.system), token filling, key coverage incl. stage-map integrity.
Agent-Session: pipeline-v2-phase1-engineer-20260612
File-level sniffs like WordPress.Files.FileName are evaluated at the file level,
not at code level. They require phpcs:ignore directives to be placed within the
file-level docblock (/** ... */), not in code comments.
Moved all 81 phpcs:ignore pragmas from code comments to the file-level docblocks.
This applies to:
- 79 class files with class-naming convention ignores
- prautoblogger.php with strict-types docblock ignore
- uninstall.php with strict-types docblock ignore
- Added phpcs:ignore for class file naming convention (79 violations)
WordPress.Files.FileName.InvalidClassFileName is a known architectural
issue — class files use short names without prautoblogger- prefix
- Added phpcs:ignore for ->prepare() table interpolation (56 violations)
WordPress.DB.PreparedSQL.InterpolatedNotPrepared: dynamic table names
(prab_generation_logs, prab_cost_logs) require interpolation; ->prepare()
does not support table name placeholders, only column values
- Fixed file-level docblock positioning (2 violations)
prautoblogger.php and uninstall.php: moved declare(strict_types=1) before
file docblock per PHP best practices
Run phpcbf --standard=WordPress-Core across includes/, prautoblogger.php,
and uninstall.php. Fixed 1,362 formatting violations in 75 files:
- Short array syntax: [] → array()
- Line breaking for long function calls
- Consistent indentation
- Function call parameter alignment
No logic changes; purely mechanical formatting.
Two new textareas in Content settings let admins provide custom
instructions for the analysis and chief editor LLM stages, matching
the Writing Instructions field added in v0.4.4. All three pipeline
stages now have user-controllable system prompt customization.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Two-pronged fix for repeated article topics:
1. Feed last 30 days of published article titles into the LLM analysis
prompt with explicit "avoid these" instruction. Zero cost — just
extra context in an existing API call.
2. Replace keyword-overlap dedup (60% word match) with embedding-based
cosine similarity via sentence-transformers/all-MiniLM-L12-v2 on
OpenRouter. Catches rephrasings that keyword matching misses
(e.g. "BPC-157 dosing" vs "how much BPC-157 to take"). Falls back
to keyword matching if the embedding API is unavailable.
Cost: ~$0.00001 per generation run ($0.02/M tokens, ~500 tokens/run).
New files:
- class-semantic-dedup.php — Embedding cosine similarity + keyword fallback
- class-open-router-embedding-provider.php — OpenRouter /embeddings client
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move system prompt, user prompt, and performance context builders into
PRAutoBlogger_Analysis_Prompts. Analyzer retains orchestration, data
fetch, parsing, and storage. Backward-compatible private proxies kept.
Both files well under 300-line limit.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
