osiman/SuperBizAgent-java
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(rag): chunk evidence identity, dedup, and search port

Browse Source 
Preserve same-document multi-chunk evidence with evidenceKey identity,
per-document caps, retrieve-k/return-n split, and a dense KnowledgeSearchPort.
Archives Delivery 1 OpenSpec change as the foundation for hybrid retrieval.
This commit is contained in:
zhuyongxin
2026-07-27 18:26:15 +08:00
parent 99d4f6f216
commit ac1f831903
34 changed files with 2880 additions and 298 deletions
Download Patch File Download Diff File Expand all files Collapse all files
openspec/specs/rag-log-projections/spec.md
+9 -3
View File
@@ -3,18 +3,23 @@
## Purpose
Define bounded RAG and Mock query-log projections that execute through the stage 3A ToolBoundary and expose only the frozen ACI contracts to the Agent.
## Requirements
### Requirement: RAG projection SHALL expose bounded document evidence only
The RAG adapter SHALL accept the logical `query` request, execute the existing knowledge tool through ToolBoundary, and project only `RagToolResult` fields. Context packs, retrieval traces, rerank traces, scores, hit reasons, domains, messages and full document bodies SHALL NOT appear in the Agent result.
The RAG adapter SHALL accept the logical `query` request, execute the existing knowledge tool through ToolBoundary, and project only `RagToolResult` fields. Context packs, retrieval traces, rerank traces, scores, hit reasons, domains, messages and full document bodies SHALL NOT appear in the Agent result. Projected evidence identity SHALL be chunk-scoped when chunk identity is available, allowing multiple excerpts from one logical source document.
#### Scenario: Project only bounded RAG evidence
- **WHEN** the adapter receives a logical query and the knowledge backend returns a result
- **THEN** it invokes through ToolBoundary and exposes only the bounded `RagToolResult` evidence fields, excluding retrieval internals and full document bodies
#### Scenario: Multiple chunks from one source may project
- **WHEN** the backend returns multiple evidence blocks with the same source and different chunk-scoped identities
- **AND** projection budgets allow them
- **THEN** the projected evidence list SHALL include more than one item for that source
- **AND** each item SHALL have a distinct `document_id`
### Requirement: Query-log projection SHALL preserve logical scope and Mock provenance
The query-log adapter SHALL accept only logical topic, query and optional lookback minutes, execute the existing Mock source through ToolBoundary, and project `source_kind=MOCK`, complete scope, match count, returned count, bounded patterns, bounded timeline events and truncation.
@@ -41,3 +46,4 @@ Both adapters SHALL pass the framework `tool_call_id` and RunContext to the exis
- **WHEN** either the RAG or query-log adapter executes
- **THEN** it passes the exact framework `tool_call_id` and RunContext through ToolBoundary without creating a second identifier, parallel store, raw response path, or legacy audit side effect