p-sw/BoxBrain
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

docs: document conversation memory pipeline

Shinwoo PARK
2026-05-11 23:14:00 +09:00
parent 3a78db2b59
commit dd73711b68
2 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
API-Reference.md

@@ -140,6 +140,7 @@ Class-based entrypoint for inbound replies, proactive openings, and entry listin
### `replyToConversation(db, input)` ### `replyToConversation(db, input)`
Persists an inbound message and generates a DM-style response turn. Persists an inbound message and generates a DM-style response turn.
When `input.memoryPipeline` is provided, the turn can also classify durable inbound/outbound messages and persist extracted IdentityDB facts back into the persona space.
```ts ```ts
replyToConversation(db: IdentityDB, input: ReplyToConversationInput): Promise<ConversationTurnResult> replyToConversation(db: IdentityDB, input: ReplyToConversationInput): Promise<ConversationTurnResult>
@@ -148,6 +149,7 @@ replyToConversation(db: IdentityDB, input: ReplyToConversationInput): Promise<Co
### `startConversation(db, input)` ### `startConversation(db, input)`
Generates a proactive outbound opening turn with no inbound user message. Generates a proactive outbound opening turn with no inbound user message.
The same optional `memoryPipeline` can classify and extract durable proactive outbound memories.
```ts ```ts
startConversation(db: IdentityDB, input: StartConversationInput): Promise<ConversationTurnResult> startConversation(db: IdentityDB, input: StartConversationInput): Promise<ConversationTurnResult>
@@ -167,6 +169,12 @@ Required model roles for turn generation:
- `contextualMemoryModel: StructuredModelAdapter` - `contextualMemoryModel: StructuredModelAdapter`
- `responseModel: StructuredModelAdapter` - `responseModel: StructuredModelAdapter`
Optional long-term memory pipeline:
- `memoryPipeline.classifierModel: StructuredModelAdapter`
- `memoryPipeline.extractorModel: StructuredModelAdapter`
- `memoryPipeline.source?: string`
## `memory` ## `memory`
### `FactDraftMemoryStore` ### `FactDraftMemoryStore`

1
Home.md

@@ -17,6 +17,7 @@ It is not a finished chatbot product. It is a **framework-first runtime library*
- availability persistence with schedule/manual/tool overrides - availability persistence with schedule/manual/tool overrides
- availability snapshots with current and next-transition resolution - availability snapshots with current and next-transition resolution
- DM-style conversation orchestration for inbound replies and proactive openings - DM-style conversation orchestration for inbound replies and proactive openings
- optional two-stage memory extraction for durable inbound/outbound conversation facts
- human-like first-reply and typing delay helpers - human-like first-reply and typing delay helpers
## What is still planned ## What is still planned