name: context-engine description: Performs hybrid semantic/lexical search with neural reranking for codebase retrieval. Use for finding implementations, Q&A grounded in source code, and cross-session persistent memory.

Context-Engine

Search and retrieve code context from any codebase using hybrid vector search (semantic + lexical) with neural reranking.

Decision Tree: Choosing the Right Tool

What do you need?
    |
    +-- Find code locations/implementations
    |       |
    |       +-- Simple query --> info_request
    |       +-- Need filters/control --> repo_search
    |
    +-- Understand how something works
    |       |
    |       +-- Want LLM explanation --> context_answer
    |       +-- Just code snippets --> repo_search with include_snippet=true
    |
    +-- Find similar code patterns (retry loops, error handling, etc.)
    |       |
    |       +-- Have code example --> pattern_search with code snippet (if enabled)
    |       +-- Describe pattern --> pattern_search with natural language (if enabled)
    |
    +-- Find specific file types
    |       |
    |       +-- Test files --> search_tests_for
    |       +-- Config files --> search_config_for
    |
    +-- Find relationships
    |       |
    |       +-- Who calls this function --> search_callers_for OR symbol_graph
    |       +-- Who imports this module --> search_importers_for
    |       +-- Symbol graph navigation (callers/defs/importers) --> symbol_graph
    |       +-- Multi-hop callers (callers of callers) --> neo4j_graph_query (transitive_callers)
    |       +-- Impact analysis (what breaks if I change X) --> neo4j_graph_query (impact)
    |       +-- Dependency graph --> neo4j_graph_query (dependencies)
    |       +-- Circular dependency detection --> neo4j_graph_query (cycles)
    |
    +-- Git history --> search_commits_for
    |
    +-- Store/recall knowledge --> memory_store, memory_find
    |
    +-- Blend code + notes --> context_search with include_memories=true

Primary Search: repo_search

Use repo_search (or its alias code_search) for most code lookups. Reranking is ON by default.

{
  "query": "database connection handling",
  "limit": 10,
  "include_snippet": true,
  "context_lines": 3
}

Returns:

{
  "results": [
    {"score": 3.2, "path": "src/db/pool.py", "symbol": "ConnectionPool", "start_line": 45, "end_line": 78, "snippet": "..."}
  ],
  "total": 8,
  "used_rerank": true
}

Multi-query for better recall - pass a list to fuse results:

{
  "query": ["auth middleware", "authentication handler", "login validation"]
}

Apply filters to narrow results:

{
  "query": "error handling",
  "language": "python",
  "under": "src/api/",
  "not_glob": ["**/test_*", "**/*_test.*"]
}

Search across repos:

{
  "query": "shared types",
  "repo": ["frontend", "backend"]
}

Use repo: "*" to search all indexed repos.

Available Filters

• language - Filter by programming language
• under - Path prefix (e.g., "src/api/")
• path_glob - Include patterns (e.g., ["/*.ts", "lib/"])
• not_glob - Exclude patterns (e.g., ["**/test_*"])
• symbol - Symbol name match
• kind - AST node type (function, class, etc.)
• ext - File extension
• repo - Repository filter for multi-repo setups
• case - Case-sensitive matching

Simple Lookup: info_request

Use info_request for natural language queries with minimal parameters:

{
  "info_request": "how does user authentication work"
}

Add explanations:

{
  "info_request": "database connection pooling",
  "include_explanation": true
}

Q&A with Citations: context_answer

Use context_answer when you need an LLM-generated explanation grounded in code:

{
  "query": "How does the caching layer invalidate entries?",
  "budget_tokens": 2000
}

Returns an answer with file/line citations. Use expand: true to generate query variations for better retrieval.

Pattern Search: pattern_search (Optional)

Note: This tool may not be available in all deployments. If pattern detection is disabled, calls return {"ok": false, "error": "Pattern search module not available"}.

Find structurally similar code patterns across all languages. Accepts either code examples or natural language descriptions—auto-detects which.

Code example query - find similar control flow:

{
  "query": "for i in range(3): try: ... except: time.sleep(2**i)",
  "limit": 10,
  "include_snippet": true
}

Natural language query - describe the pattern:

{
  "query": "retry with exponential backoff",
  "limit": 10,
  "include_snippet": true
}

Cross-language search - Python pattern finds Go/Rust/Java equivalents:

{
  "query": "if err != nil { return err }",
  "language": "go",
  "limit": 10
}

Explicit mode override - force code or description mode:

{
  "query": "error handling",
  "query_mode": "description",
  "limit": 10
}

Key parameters:

• query - Code snippet OR natural language description
• query_mode - "code", "description", or "auto" (default)
• language - Language hint for code examples (python, go, rust, etc.)
• limit - Max results (default 10)
• min_score - Minimum similarity threshold (default 0.3)
• include_snippet - Include code snippets in results
• context_lines - Lines of context around matches
• aroma_rerank - Enable AROMA structural reranking (default true)
• aroma_alpha - Weight for AROMA vs original score (default 0.6)
• target_languages - Filter results to specific languages

Returns:

{
  "ok": true,
  "results": [...],
  "total": 5,
  "query_signature": "L2_2_B0_T2_M0",
  "query_mode": "code",
  "search_mode": "aroma"
}

The query_signature encodes control flow: L (loops), B (branches), T (try/except), M (match).

Specialized Search Tools

search_tests_for - Find test files:

{"query": "UserService", "limit": 10}

search_config_for - Find config files:

{"query": "database connection", "limit": 5}

search_callers_for - Find callers of a symbol:

{"query": "processPayment", "language": "typescript"}

search_importers_for - Find importers:

{"query": "utils/helpers", "limit": 10}

symbol_graph - Symbol graph navigation (callers / definition / importers):

{"symbol": "ASTAnalyzer", "query_type": "definition", "limit": 10}

{"symbol": "get_embedding_model", "query_type": "callers", "under": "scripts/", "limit": 10}

{"symbol": "qdrant_client", "query_type": "importers", "limit": 10}

• Supports language, under, depth, and output_format like other tools.
• Use depth=2 or depth=3 for multi-hop traversals (callers of callers).
• If there are no graph hits, it falls back to semantic search.
• Note: Results are "hydrated" with ~500-char source snippets for immediate context.

neo4j_graph_query - Advanced graph traversals (requires NEO4J_GRAPH=1):

{"symbol": "normalize_path", "query_type": "impact", "depth": 2}

{"symbol": "get_embedding_model", "query_type": "transitive_callers", "depth": 2}

{"symbol": "run_hybrid_search", "query_type": "dependencies", "limit": 15}

Query types:

search_commits_for - Search git history:

{"query": "fixed authentication bug", "limit": 10}

change_history_for_path - File change summary:

{"path": "src/api/auth.py", "include_commits": true}

Memory: Store and Recall Knowledge

Use memory_store to persist information for later retrieval:

{
  "information": "Auth service uses JWT tokens with 24h expiry. Refresh tokens last 7 days.",
  "metadata": {"topic": "auth", "date": "2024-01"}
}

Use memory_find to retrieve stored knowledge by similarity:

{"query": "token expiration", "limit": 5}

Use context_search to blend code results with stored memories:

{
  "query": "authentication flow",
  "include_memories": true,
  "per_source_limits": {"code": 6, "memory": 3}
}

Index Management

qdrant_index_root - First-time setup or full reindex:

{}

With recreate (drops existing data):

{"recreate": true}

qdrant_index - Index only a subdirectory:

{"subdir": "src/"}

qdrant_prune - Remove deleted files from index:

{}

qdrant_status - Check index health:

{}

qdrant_list - List all collections:

{}

Workspace Tools

workspace_info - Get current workspace and collection:

{}

list_workspaces - List all indexed workspaces:

{}

collection_map - View collection-to-repo mappings:

{"include_samples": true}

set_session_defaults - Set defaults for session:

{"collection": "my-project", "language": "python"}

Query Expansion

expand_query - Generate query variations for better recall:

{"query": "auth flow", "max_new": 2}

Output Formats

• json (default) - Structured output
• toon - Token-efficient compressed format

Set via output_format parameter.

Aliases and Compat Wrappers

Aliases:

• code_search = repo_search (identical behavior)

Cross-server tools:

• memory_store / memory_find — Memory server tools for persistent knowledge

Compat wrappers accept alternate parameter names:

• repo_search_compat - Accepts q, text, top_k as aliases
• context_answer_compat - Accepts q, text as aliases

Use the primary tools when possible. Compat wrappers exist for legacy clients.

Error Handling

Tools return structured errors, typically via error field and sometimes ok: false:

{"ok": false, "error": "Collection not found. Run qdrant_index_root first."}
{"error": "Timeout during rerank"}

Common issues:

• Collection not found - Run qdrant_index_root to create the index
• Empty results - Broaden query, check filters, verify index exists
• Timeout on rerank - Set rerank_enabled: false or reduce limit

Best Practices

1. Start broad, then filter - Begin with a semantic query, add filters if too many results
2. Use multi-query - Pass 2-3 query variations for better recall on complex searches
3. Include snippets - Set include_snippet: true to see code context in results
4. Store decisions - Use memory_store to save architectural decisions and context for later
5. Check index health - Run qdrant_status if searches return unexpected results
6. Prune after refactors - Run qdrant_prune after moving/deleting files
7. Index before search - Always run qdrant_index_root on first use or after cloning a repo
8. Use pattern_search for structural matching - When looking for code with similar control flow (retry loops, error handling), use pattern_search instead of repo_search (if enabled)
9. Describe patterns in natural language - pattern_search understands "retry with backoff" just as well as actual code examples (if enabled)