buua436 78b4906f7a fix: tighten embedding truncation threshold (#16123) ...

### What problem does this PR solve?
Use a 95% max_length threshold before truncating embedding inputs, which
reduces the chance of provider-side invalid-parameter errors on
near-limit chunks.

### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)

2026-06-17 14:18:02 +08:00

..

joint_services

Feat: model provider (#16028)

2026-06-15 19:10:33 +08:00

services

fix: tighten embedding truncation threshold (#16123)

2026-06-17 14:18:02 +08:00

__init__.py

fix: propagate memory tenant id in task collect (#15837)

2026-06-09 17:47:48 +08:00

db_models.py

fix: rename dialog_id to chat_id in chat_channel (backend + frontend) (#16096)

2026-06-16 19:02:20 +08:00

db_utils.py

Add time utils (#10849)

2025-10-28 19:09:14 +08:00

init_data.py

Fix: model list (#15860)

2026-06-10 14:59:57 +08:00

reload_config_base.py

Format file format from Windows/dos to Unix (#1949)

2024-08-15 09:17:36 +08:00

runtime_config.py

Admin: add 'show version' (#11079)

2025-11-06 19:24:46 +08:00

template_utils.py

feat: support multiple canvas_types for agent templates and remove duplicate files (#14030)

2026-04-13 20:26:30 +08:00