refactor(memory-config): refactor memory config to use workspace models and remove reflection model - #1994
Merged
Merged
Conversation
…ls and remove reflection model - Remove reflection_model_id from memory config schema, repository, and service - Resolve embedding, llm, rerank, vision, and audio models from workspace defaults instead of per-config overrides - Update redis_cache to support UUID return types and add shared invalidation helpers - Switch emotion_config_service to AsyncSession and drop emotion_model_id validation
Contributor
审阅者指南（Reviewer's Guide）重构了内存（memory）及相关配置，使其依赖工作区（workspace）级别的模型分配，而不是每个配置的模型 ID；改进了 Redis 缓存行为及失效逻辑；并从 API 和存储中移除了显式的反思（reflection）/情绪（emotion）模型配置，改为依赖工作区模型。 使用工作区 LLM 模型的 reflection_run 时序图sequenceDiagram
actor User
participant MemoryReflectionController
participant MemoryConfigRepository
participant Workspace
participant ModelConfigService
User->>MemoryReflectionController: reflection_run(config_id)
MemoryReflectionController->>MemoryConfigRepository: get_config_with_workspace_async(config_id)
MemoryConfigRepository-->>MemoryReflectionController: (MemoryConfig, Workspace)
MemoryReflectionController->>Workspace: read llm
Workspace-->>MemoryReflectionController: llm_id
MemoryReflectionController->>ModelConfigService: get_model_by_id_async(db, model_id=llm_id, tenant_id)
ModelConfigService-->>MemoryReflectionController: model details
MemoryReflectionController-->>User: reflection result (using workspace.llm)
文件级变更（File-Level Changes）
提示与命令（Tips and commands）与 Sourcery 交互（Interacting with Sourcery）
自定义你的体验（Customizing Your Experience）访问你的 dashboard 来：
获取帮助（Getting Help）Original review guide in EnglishReviewer's GuideRefactors memory and related configs to rely on workspace-level model assignments instead of per-config model IDs, improves Redis cache behavior and invalidation, and removes explicit reflection/emotion model configuration from APIs and storage in favor of workspace models. Sequence diagram for reflection_run using workspace LLM modelsequenceDiagram
actor User
participant MemoryReflectionController
participant MemoryConfigRepository
participant Workspace
participant ModelConfigService
User->>MemoryReflectionController: reflection_run(config_id)
MemoryReflectionController->>MemoryConfigRepository: get_config_with_workspace_async(config_id)
MemoryConfigRepository-->>MemoryReflectionController: (MemoryConfig, Workspace)
MemoryReflectionController->>Workspace: read llm
Workspace-->>MemoryReflectionController: llm_id
MemoryReflectionController->>ModelConfigService: get_model_by_id_async(db, model_id=llm_id, tenant_id)
ModelConfigService-->>MemoryReflectionController: model details
MemoryReflectionController-->>User: reflection result (using workspace.llm)
File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
API Breaking Change ReportComparing against Breaking change approval label:
oasdiffOutputopenapi-diffOutputGate decisionNo breaking changes detected. The check passed without approval override. |
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Hey - 我在这里给出了一些总体反馈：
- 现在在创建反射配置时，会忽略
config_data中存在的任何reflection_model_id，而是始终从 workspace 的 models 中推导得到；如果这是有意为之，建议从仍然保留该字段的请求/响应负载或代码路径中将其移除，以避免让人误以为用户仍可配置它，从而造成困惑。 - 在
workspace_service.update_workspace中，内存配置缓存的失效前缀为memory_config:{db_workspace.memory_config}；如果memory_config是 UUID 或其他非字符串类型，显式地转换为str可能更加安全，以避免出现不易察觉的 key 格式不一致问题。
给 AI Agents 的提示
请根据这次代码审查中的评论进行修改：
## 整体评论
- 现在在创建反射配置时，会忽略 `config_data` 中存在的任何 `reflection_model_id`，而是始终从 workspace 的 models 中推导得到；如果这是有意为之，建议从仍然保留该字段的请求/响应负载或代码路径中将其移除，以避免让人误以为用户仍可配置它，从而造成困惑。
- 在 `workspace_service.update_workspace` 中，内存配置缓存的失效前缀为 `memory_config:{db_workspace.memory_config}`；如果 `memory_config` 是 UUID 或其他非字符串类型，显式地转换为 `str` 可能更加安全，以避免出现不易察觉的 key 格式不一致问题。帮我变得更有用吧！请在每条评论下点 👍 或 👎，我会根据你的反馈改进后续的评审。
Original comment in English
Hey - I've left some high level feedback:
- Reflection config creation now ignores any
reflection_model_idpresent inconfig_dataand always derives it from workspace models; if this is intentional, consider removing the field from any remaining request/response payloads or code paths that still suggest it can be user-configured to avoid confusion. - In
workspace_service.update_workspace, the invalidation prefix for memory config cache ismemory_config:{db_workspace.memory_config}; ifmemory_configis a UUID or other non-string type, it may be safer to explicitly cast tostrto avoid subtle key format inconsistencies.
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- Reflection config creation now ignores any `reflection_model_id` present in `config_data` and always derives it from workspace models; if this is intentional, consider removing the field from any remaining request/response payloads or code paths that still suggest it can be user-configured to avoid confusion.
- In `workspace_service.update_workspace`, the invalidation prefix for memory config cache is `memory_config:{db_workspace.memory_config}`; if `memory_config` is a UUID or other non-string type, it may be safer to explicitly cast to `str` to avoid subtle key format inconsistencies.Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
Collaborator
Author
|
remove model config from v1/memory_config/update_config_extracted v1/memory_config/update_config_emotion v1/memory_config/update_config_reflection |
keeees
approved these changes
Aug 12, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary by Sourcery
对内存相关配置与工作区级模型设置进行对齐，简化反射/情绪/抽取配置，并改进 Redis 缓存及缓存失效工具。
New Features:
Bug Fixes:
Enhancements:
Documentation:
Chores:
Original summary in English
Summary by Sourcery
Align memory-related configuration with workspace-level model settings, simplify reflection/emotion/extraction configs, and improve Redis caching and cache invalidation utilities.
New Features:
Bug Fixes:
Enhancements:
Documentation:
Chores: