Framework and Language Coverage

Framework and Language Coverage

agent_architecture detects common agent orchestration patterns and applies configurable language filtering.

Framework Detection Coverage

The detector family covers these framework patterns:

Framework	Typical Anchors
LangGraph	StateGraph, .compile()
CrewAI	Agent(, Crew(
LangChain Agents	AgentExecutor, .run(, .call(, .invoke(
AutoGen	AssistantAgent(, GroupChat(, GroupChatManager(, initiate_chat(
OpenAI Agents SDK	Runner.run(, Runner.run_sync(, Runner.run_streamed(
Pydantic AI	pydantic_ai.Agent(, .run_sync(, .iter(

Call sites are deduplicated by (file, line) to avoid overcounting. Generic invoke/compile patterns are counted only when a framework anchor exists in the same file.

Language Filtering Behavior

The optional metrics[].config.languages filter is extension-based.

• If languages is empty, no language filter is applied.
• If set, only call sites in matching extensions are kept.

Supported language values and mapped extensions:

languages value	Extensions
python	.py
typescript, ts, javascript, js	.ts, .tsx, .js, .jsx, .mjs, .cjs
rust	.rs

Example:

metrics:
  - id: agent_architecture
    config:
      languages: ["python", "typescript"]

AST vs Pattern Fallback

At a high level:

• Python and TypeScript call-site detection uses AST parsing when parse succeeds.
• If parsing fails, detection falls back to pattern-based matching.
• Rust is currently pattern-based for these agent patterns.

For loop-guard checks, Python can use same-function AST context to improve guard detection confidence.

Known Limitations and FP/FN Caveats

• Heuristic pattern matching may produce false positives in unrelated helper code with similar naming.
• Framework wrappers and internal abstraction layers can hide call sites and cause false negatives.
• Extension-based filtering depends on file names; non-standard extensions can be excluded unintentionally.
• Schema validation detection focuses on common conventions (Pydantic/Zod/JSON-like patterns) and may miss custom validators.
• Confidence can vary by detector mode (AST-backed vs line/pattern heuristics).

Practical Recommendations

1. Start without a languages filter to establish baseline visibility.
2. Add languages only if you need to scope CI runtime or ownership boundaries.
3. Pair policy thresholds with finding review before strict enforcement.