hyl64 77ce88dfcc fix(prompt): reserve system budget in message_fit_in (#14164) ...

## Summary
This PR fixes the `message_fit_in()` truncation bug reported in #13607.

Changes:
- fix the user-message truncation branch to reserve room for the system
prompt token budget
- guard the zero-token edge case to avoid dividing by zero in the
truncation ratio check
- add focused regression tests covering both the user-dominant
truncation path and the zero-token boundary case

## Validation
```bash
pytest -q --noconftest test/unit_test/rag/prompts/test_generator_message_fit_in.py
```

Result: `2 passed`

Closes #13607

2026-05-11 12:44:27 +08:00

..

advanced_rag

fix: handle missing 'total' key causing KeyError in deep research retrieval (#13942)

2026-05-09 10:57:51 +08:00

app

Feature/table parser column roles (#13710)

2026-05-11 10:06:04 +08:00

flow

Feat: add button for remove header & footer in pipeline (#14486)

2026-04-30 12:30:41 +08:00

graphrag

feat(graphrag): fix merge concurrency and add resume-from-checkpoint (#14238)

2026-05-06 15:01:01 +08:00

llm

fix: complete robustness fixes for rerank module addressing all review comments (#14265)

2026-05-11 12:40:41 +08:00

nlp

fix: handle missing parent chunk in retrieval_by_children (#14556)

2026-05-11 11:55:44 +08:00

prompts

fix(prompt): reserve system budget in message_fit_in (#14164)

2026-05-11 12:44:27 +08:00

res

Feat: Bitbucket connector (#12332)

2025-12-31 17:18:30 +08:00

svr

fix(keyword_extraction): accept Chinese commas/semicolons/newlines as keyword delimiters (#14540)

2026-05-11 12:05:24 +08:00

utils

Feature/table parser column roles (#13710)

2026-05-11 10:06:04 +08:00

__init__.py

Fix: incorrect async chat streamly output (#11679)

2025-12-03 11:15:45 +08:00

benchmark.py

Feat/tenant model (#13072)

2026-03-05 17:27:17 +08:00

raptor.py

feat: persist RAPTOR layer metadata on summary chunks (#13286)

2026-04-27 10:20:46 +08:00

settings.py

Move api.settings to common.settings (#11036)

2025-11-06 09:36:38 +08:00