Allow empty text for non-target AI rewrites

This commit is contained in:
Your Name
2026-07-30 09:14:54 +05:00
parent 519474e4ff
commit 858fa4cc46
3 changed files with 7 additions and 2 deletions
+4
View File
@@ -794,6 +794,10 @@ AI получает JSON-массив:
2026-07-30 один пост (`id=2348`) был платно отправлен в Sonnet 4.6 983 раза, 2026-07-30 один пост (`id=2348`) был платно отправлен в Sonnet 4.6 983 раза,
потому что failed снова попадал в claim и цикл сразу продолжал работу. Failed потому что failed снова попадал в claim и цикл сразу продолжал работу. Failed
посты нужно возвращать в `pending` только явным ручным действием. посты нужно возвращать в `pending` только явным ручным действием.
Sonnet 4.6 в этом кейсе возвращал `category_id=18` (`Не целевой контент`) и
пустой `text`, объясняя отказ в `notes`; это валидный AI-отказ, а не ошибка
рерайта. Проверка минимальной длины текста применяется только к целевым
категориям.
После failed AI batch worker помечает конкретные посты как `failed` и продолжает После failed AI batch worker помечает конкретные посты как `failed` и продолжает
обрабатывать другие `pending` посты. Ошибка показывается на `/workers` из обрабатывать другие `pending` посты. Ошибка показывается на `/workers` из
heartbeat meta и отправляется Telegram-уведомлением получателям heartbeat meta и отправляется Telegram-уведомлением получателям
+1
View File
@@ -103,6 +103,7 @@ As of 2026-07-29:
- Current live writer model setting checked on 2026-07-29: `ai_writer_model = anthropic/claude-sonnet-4-6`. - Current live writer model setting checked on 2026-07-29: `ai_writer_model = anthropic/claude-sonnet-4-6`.
- Sonnet 4.6 can return `rewrites` as a JSON string instead of a list. `validate_rewrites()` in `src/vk_parser_app/workers/ai_writer.py` now parses stringified `rewrites` before validation. - Sonnet 4.6 can return `rewrites` as a JSON string instead of a list. `validate_rewrites()` in `src/vk_parser_app/workers/ai_writer.py` now parses stringified `rewrites` before validation.
- 2026-07-30 incident: post `2348` was retried 983 times by AI writer because automatic claim included `rewrite_status='failed'`; estimated internal cost was `$16.465977`. Live setting `ai_writer_enabled` was switched to `false` manually to stop spend. Automatic AI qualifier/writer claims must not include `failed`; failed posts require an explicit manual reset to `pending`. AI writer/qualifier keep running after a failed batch, show the error on `/workers`, and send a Telegram alert via daily-report/TG-poster bot recipients. - 2026-07-30 incident: post `2348` was retried 983 times by AI writer because automatic claim included `rewrite_status='failed'`; estimated internal cost was `$16.465977`. Live setting `ai_writer_enabled` was switched to `false` manually to stop spend. Automatic AI qualifier/writer claims must not include `failed`; failed posts require an explicit manual reset to `pending`. AI writer/qualifier keep running after a failed batch, show the error on `/workers`, and send a Telegram alert via daily-report/TG-poster bot recipients.
- Sonnet 4.6 may return `category_id=18` (`Не целевой контент`) with empty `text` and the explanation in `notes`. This is valid AI rejection, not a writer error; `validate_rewrites()` allows short/empty text only for non-target category.
## Prompt Architecture ## Prompt Architecture
+2 -2
View File
@@ -152,8 +152,6 @@ def validate_rewrites(
if post_id not in expected_ids: if post_id not in expected_ids:
raise ValueError(f"AI returned unexpected id={post_id}") raise ValueError(f"AI returned unexpected id={post_id}")
text = strip_leading_emoji_markers(str(item.get("text") or "").strip()) text = strip_leading_emoji_markers(str(item.get("text") or "").strip())
if len(text) < 40:
raise ValueError(f"AI returned too short rewrite for id={post_id}")
by_id = {int(c["id"]): c for c in categories if c.get("id") is not None} by_id = {int(c["id"]): c for c in categories if c.get("id") is not None}
by_name = {str(c["name"]).lower(): c for c in categories if c.get("name")} by_name = {str(c["name"]).lower(): c for c in categories if c.get("name")}
if item.get("category_id") is not None: if item.get("category_id") is not None:
@@ -170,6 +168,8 @@ def validate_rewrites(
seen.add(post_id) seen.add(post_id)
category_tag = normalize_hash_tag(category_row.get("tag") or category_row.get("name") or "", "category") category_tag = normalize_hash_tag(category_row.get("tag") or category_row.get("name") or "", "category")
reject_by_category = int(category_row["id"]) == NON_TARGET_CATEGORY_ID or category_tag.lower() in NON_TARGET_CATEGORY_TAGS reject_by_category = int(category_row["id"]) == NON_TARGET_CATEGORY_ID or category_tag.lower() in NON_TARGET_CATEGORY_TAGS
if not reject_by_category and len(text) < 40:
raise ValueError(f"AI returned too short rewrite for id={post_id}")
out.append( out.append(
{ {
"id": post_id, "id": post_id,