Timebomb2018 377ddd2b9b fix(llm): unify JSON output handling across providers and fix tool+json_output compatibility ...

- Remove redundant `response_format` injection for VOLCANO provider since it's unsupported; rely on system prompt injection instead
- Extend system prompt JSON injection logic to cover VOLCANO and tool-enabled cases universally
- Simplify model parameter construction by removing redundant `params["model_kwargs"] = model_kwargs` assignments
- Refactor `CompatibleChatOpenAI._get_request_payload` to strip `response_format` when tools are present, avoiding strict validation errors in langchain_openai
- Fix timestamp calculation order in `datetime_tool.py` to avoid integer truncation before multiplication

2026-04-17 14:19:40 +08:00

..

base

[fix] Pydantic save json error

2026-01-12 15:59:10 +08:00

cache

feat(cache): Add thread-safe Redis client and enable activity stats cache

2026-03-27 16:54:47 +08:00

config

refactor(agent): refactor Agent model parameters reset logic and add environment variable support

2026-04-17 11:00:22 +08:00

controllers

refactor(agent): 将重置模型参数接口改为获取默认参数

2026-04-17 11:34:11 +08:00

core

fix(llm): unify JSON output handling across providers and fix tool+json_output compatibility

2026-04-17 14:19:40 +08:00

i18n

[fix] i18n import error

2026-03-13 14:36:54 +08:00

locales

[add] i18n support zh,en

2026-03-11 10:45:07 +08:00

models

feat: Add quota check decorator and implement tenant-level API rate limiting

2026-04-13 11:58:14 +08:00

plugins

[add] plugin system and base sso module

2026-01-27 14:04:44 +08:00

repositories

Merge pull request #899 from wanxunyang/feature/add-quota-check-decorator

2026-04-16 13:48:40 +08:00

schemas

feat(llm): add json_output support for structured LLM responses

2026-04-16 16:27:55 +08:00

services

fix(knowledge_service): 修正知识创建时模型类型过滤条件

2026-04-17 11:38:45 +08:00

templates/agent

refactor(workflow): relocate template directory into workflow

2026-02-03 15:24:16 +08:00

utils

feat(workflow): add opening statement and citation support

2026-04-03 11:44:07 +08:00

__init__.py

Fix/memory bug fix (#171)

2026-01-26 11:53:34 +08:00

aioRedis.py

[fix] No event loop is set and defensive programming is not used for non-main thread calls.

2026-03-31 09:59:39 +08:00

celery_app.py

Merge branch 'feature/rag2' into develop

2026-04-13 13:46:19 +08:00

celery_worker.py

feat(multimodel): support multimodal memory display and improve code style

2026-03-13 14:47:56 +08:00

db.py

fix(workflow): allow right-hand operand to be optional when not required by comparison

2026-03-20 19:53:02 +08:00

dependencies.py

[add] app chat v1

2025-12-24 20:35:04 +08:00

main.py

feat(memory): add perceptual memory retrieval service with BM25+embedding fusion

2026-04-01 18:03:07 +08:00

query_ontology_matched_entities.py

[fix]Memory extraction output the core engineering effect

2026-02-09 21:23:24 +08:00

tasks.py

refactor(memory): tighten metadata field types and clean up descriptions

2026-04-16 17:29:00 +08:00

version_info.json

feat(llm): add json_output support for structured LLM responses

2026-04-16 16:27:55 +08:00