refactor(librarian): teach proper ast_grep_search discipline

ast_grep_search was mentioned exactly once in the librarian prompt
(bundled as 'grep/ast_grep_search for function/class') with no syntax
guidance. When the librarian cloned a repo and tried to match code
shape, it fell into the same regex-in-AST trap as the main agent.

Two targeted edits, no rewrite of the surrounding request-classification
flow:

- Phase 1 TYPE B 'Find the implementation' now separates ast_grep_search
  (code shape) from grep (text/literals) and reminds the LLM that AST
  patterns use $VAR and $$$ and are not regex.
- TOOL REFERENCE adds a dedicated ast_grep_search row with valid
  examples and the explicit regex anti-pattern list, alongside tightened
  guidance for grep_app and grep so the LLM picks the right tool for
  cross-repo vs single-repo, text vs shape.
This commit is contained in:
YeonGyu-Kim
2026-04-22 12:29:00 +09:00
parent 5ef2a3fa7c
commit f0dd0464d8
2 changed files with 95 additions and 5 deletions
@@ -0,0 +1,84 @@
/// <reference types="bun-types" />
import { describe, expect, it } from "bun:test"
import { createLibrarianAgent } from "./librarian"
describe("librarian agent ast-grep discipline", () => {
const model = "openai/gpt-5.4-mini-fast"
it("#given the prompt #when inspecting TOOL REFERENCE #then documents ast_grep_search", () => {
// given
const agent = createLibrarianAgent(model)
// when
const prompt = agent.prompt ?? ""
// then
expect(prompt).toContain("ast_grep_search")
expect(prompt).toContain("$$$")
expect(prompt).toContain("function $NAME($$$) { $$$ }")
})
it("#given the prompt #when inspecting #then warns against regex inside ast_grep_search", () => {
// given
const agent = createLibrarianAgent(model)
// when
const prompt = agent.prompt ?? ""
// then
expect(prompt.toLowerCase()).toContain("not regex")
expect(prompt).toContain("|")
expect(prompt).toContain(".*")
expect(prompt).toContain("\\w")
})
it("#given the prompt #when inspecting #then directs LLM to grep/grep_app for text search", () => {
// given
const agent = createLibrarianAgent(model)
// when
const prompt = agent.prompt ?? ""
// then
expect(prompt.toLowerCase()).toContain("for text")
expect(prompt).toContain("grep_app")
})
it("#given the prompt #when inspecting Implementation phase #then recommends ast_grep_search for code shape", () => {
// given
const agent = createLibrarianAgent(model)
// when
const prompt = agent.prompt ?? ""
// then
expect(prompt).toContain("ast_grep_search for code shape")
})
it("#given the prompt #when inspecting #then preserves the evidence + permalink contract", () => {
// given
const agent = createLibrarianAgent(model)
// when
const prompt = agent.prompt ?? ""
// then
expect(prompt).toContain("GitHub permalinks")
expect(prompt).toContain("MANDATORY CITATION FORMAT")
})
it("#given the prompt #when inspecting #then preserves request classification phases", () => {
// given
const agent = createLibrarianAgent(model)
// when
const prompt = agent.prompt ?? ""
// then
expect(prompt).toContain("TYPE A: CONCEPTUAL")
expect(prompt).toContain("TYPE B: IMPLEMENTATION")
expect(prompt).toContain("TYPE C: CONTEXT")
expect(prompt).toContain("TYPE D: COMPREHENSIVE")
})
})