exostring/new_vk_parser
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Alert on AI worker auto-disable

Browse Source
This commit is contained in:
Your Name
2026-07-30 09:05:36 +05:00
parent bb67e9509b
commit e289e3a7f9
7 changed files with 106 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
STATE.md
+1 -1
View File
@@ -102,7 +102,7 @@ As of 2026-07-29:
- 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.
- 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` to stop spend. Automatic AI qualifier/writer claims must not include `failed`; failed posts require an explicit manual reset to `pending`. AI writer/qualifier now also set their own `*_enabled=false` after any failed AI batch, so one broken prompt/model/post cannot burn money indefinitely.
- 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` to stop spend. Automatic AI qualifier/writer claims must not include `failed`; failed posts require an explicit manual reset to `pending`. AI writer/qualifier now also set their own `*_enabled=false` after any failed AI batch, show the error on `/workers`, and send a Telegram alert via daily-report/TG-poster bot recipients, so one broken prompt/model/post cannot burn money indefinitely or fail silently.
## Prompt Architecture