feat(context): implement semantic context search using embeddings #10126

Open
opened 2026-04-17 03:54:48 +00:00 by HAL9000 · 0 comments
Owner

Background

The advanced context strategy system requires semantic search capabilities to find contextually relevant files beyond simple path-based selection. Embedding-based similarity search enables actors to receive the most relevant context for their current task, improving plan quality and reducing noise in context assembly.

Acceptance Criteria

  • SemanticContextSearcher class implemented with embedding-based similarity scoring
  • Integration with at least one embedding provider (e.g., OpenAI text-embedding-3-small)
  • Semantic search returns ranked list of context files by relevance score
  • Configurable similarity threshold in context policy YAML
  • Test coverage >= 97%

Metadata

  • Commit Message: feat(context): implement semantic context search using embeddings
  • Branch: feature/v3.6.0/semantic-context-search
  • Milestone: v3.6.0
  • Ref: #5172 EPIC: Advanced Context Strategies — Beyond Basic ACMS Pipeline (v3.6.0)

Subtasks

  • Define SemanticContextSearcher interface and data models
  • Implement embedding generation via provider abstraction
  • Implement cosine similarity scoring and ranking
  • Add semantic_search strategy to context policy YAML schema
  • Write unit tests for searcher and integration tests with mock embeddings

Definition of Done

  • Implementation complete and all acceptance criteria met
  • Tests written and passing (coverage >= 97%)
  • PR reviewed and merged
  • Parent epic updated

Automated by CleverAgents Bot
Supervisor: Epic Planning | Agent: epic-planning-pool-supervisor

## Background The advanced context strategy system requires semantic search capabilities to find contextually relevant files beyond simple path-based selection. Embedding-based similarity search enables actors to receive the most relevant context for their current task, improving plan quality and reducing noise in context assembly. ## Acceptance Criteria - [ ] `SemanticContextSearcher` class implemented with embedding-based similarity scoring - [ ] Integration with at least one embedding provider (e.g., OpenAI `text-embedding-3-small`) - [ ] Semantic search returns ranked list of context files by relevance score - [ ] Configurable similarity threshold in context policy YAML - [ ] Test coverage >= 97% ## Metadata - **Commit Message**: `feat(context): implement semantic context search using embeddings` - **Branch**: `feature/v3.6.0/semantic-context-search` - **Milestone**: v3.6.0 - **Ref**: #5172 EPIC: Advanced Context Strategies — Beyond Basic ACMS Pipeline (v3.6.0) ## Subtasks - [ ] Define `SemanticContextSearcher` interface and data models - [ ] Implement embedding generation via provider abstraction - [ ] Implement cosine similarity scoring and ranking - [ ] Add `semantic_search` strategy to context policy YAML schema - [ ] Write unit tests for searcher and integration tests with mock embeddings ## Definition of Done - Implementation complete and all acceptance criteria met - Tests written and passing (coverage >= 97%) - PR reviewed and merged - Parent epic updated --- **Automated by CleverAgents Bot** Supervisor: Epic Planning | Agent: epic-planning-pool-supervisor
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
cleveragents/cleveragents-core#10126
No description provided.