Files
hyperguild/ingestion/internal/mcp/tools_answer_test.go
Mathias a56a4db963
All checks were successful
CI / Lint / Test / Vet (push) Successful in 10s
CI / Mirror to GitHub (push) Successful in 3s
feat(brain_answer): Qwen3-Reranker cross-encoder filter (opt-in)
Adds an opt-in cross-encoder rerank step between BM25 retrieval and LLM
synthesis. With BRAIN_RERANKER_URL set, brain_answer retrieves BM25
top-20, scores each excerpt against the query via Qwen3-Reranker on
Ollama, drops the "no" answers, and forwards up to 5 surviving sources
to the LLM. Unset, behaviour is unchanged (BM25 top-10 → LLM).

The reranker is a *filter*, not a re-ranker: Qwen3-Reranker emits a
binary yes/no token under its native chat template, and ties within the
"yes" set are broken by BM25 rank — what got retrieved first stays
ahead.

New package ingestion/internal/reranker:
- Client with URL, Model, HTTP fields.
- New(url, model) returns nil on empty url so callers can treat
  "feature disabled" as a single nil check.
- Score(ctx, query, docs) issues one /api/generate call per doc using
  the Qwen3-Reranker yes/no chat template (verbatim, because the model
  was trained on this exact wording). Parses the first non-think token.

Wiring:
- mcp.Server gains a WithReranker fluent setter to keep NewServer
  signature stable.
- brain_answer's BM25 limit jumps to 20 only when a reranker is wired,
  to give the filter something to do.
- cmd/server/main.go reads BRAIN_RERANKER_URL (+ optional
  BRAIN_RERANKER_MODEL, default dengcao/Qwen3-Reranker-0.6B:F16).

Tests cover: nil-on-empty-url, ordered yes/no scoring, request shape
(model, prompt contents, yes/no template), ambiguous response → 0,
empty doc slice, upstream-error propagation, plus an end-to-end
brain_answer integration that proves only the relevant note reaches the
LLM when noise.md is rejected.

Closes hyperguild#7.
2026-05-18 22:55:46 +02:00

156 lines
5.4 KiB
Go

package mcp_test
import (
"context"
"encoding/json"
"io"
"net/http"
"net/http/httptest"
"os"
"path/filepath"
"strings"
"testing"
"github.com/mathiasbq/hyperguild/ingestion/internal/mcp"
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
"github.com/mathiasbq/hyperguild/ingestion/internal/reranker"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func mockAnswerLLM(response string) pipeline.CompleteFunc {
return func(_ context.Context, _, _ string) (string, error) {
return response, nil
}
}
func brainDirWithContent(t *testing.T) string {
t.Helper()
dir := t.TempDir()
wikiDir := filepath.Join(dir, "wiki")
require.NoError(t, os.MkdirAll(wikiDir, 0o755))
require.NoError(t, os.WriteFile(filepath.Join(wikiDir, "test.md"), []byte(
"---\ntitle: Pass-rate Logging\ntype: spec\n---\n\nPass-rate logging tracks skill invocations.",
), 0o644))
return dir
}
func callTool(t *testing.T, ts *httptest.Server, name string, arguments map[string]any) map[string]any {
t.Helper()
req := map[string]any{
"jsonrpc": "2.0", "id": 1, "method": "tools/call",
"params": map[string]any{"name": name, "arguments": arguments},
}
resp, err := http.Post(ts.URL, "application/json", body(t, req))
require.NoError(t, err)
defer resp.Body.Close() //nolint:errcheck
var out map[string]any
require.NoError(t, json.NewDecoder(resp.Body).Decode(&out))
return out
}
func TestBrainAnswer_RerankerFiltersBeforeLLM(t *testing.T) {
brainDir := t.TempDir()
wikiDir := filepath.Join(brainDir, "wiki")
require.NoError(t, os.MkdirAll(wikiDir, 0o755))
// Two notes — both BM25-match the query, but only one is truly relevant.
require.NoError(t, os.WriteFile(filepath.Join(wikiDir, "good.md"), []byte(
"---\ntitle: Pass-rate Logging\n---\nPass-rate logging tracks skill invocations.",
), 0o644))
require.NoError(t, os.WriteFile(filepath.Join(wikiDir, "noise.md"), []byte(
"---\ntitle: Pass-rate Tangent\n---\nPass-rate appears here too but as a tangent.",
), 0o644))
// Fake Ollama reranker: yes only when prompt contains "tracks skill invocations".
rrSrv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
raw, _ := io.ReadAll(r.Body)
yes := strings.Contains(string(raw), "tracks skill invocations")
ans := "no"
if yes {
ans = "yes"
}
_ = json.NewEncoder(w).Encode(map[string]any{"response": ans, "done": true})
}))
defer rrSrv.Close()
// LLM mock captures the rendered sources so we can assert what reached it.
var sawSources string
llm := func(_ context.Context, _, user string) (string, error) {
sawSources = user
return "answer text", nil
}
srv := mcp.NewServer(brainDir, nil, nil, llm).
WithReranker(reranker.New(rrSrv.URL, "qwen3"))
ts := httptest.NewServer(srv)
defer ts.Close()
rpc := callTool(t, ts, "brain_answer", map[string]any{"query": "pass-rate logging"})
require.Nil(t, rpc["error"])
content := rpc["result"].(map[string]any)["content"].([]any)[0].(map[string]any)["text"].(string)
var result map[string]any
require.NoError(t, json.Unmarshal([]byte(content), &result))
sources := result["sources"].([]any)
require.Len(t, sources, 1, "reranker should drop noise.md")
assert.Equal(t, "wiki/good.md", sources[0])
assert.Contains(t, sawSources, "good.md")
assert.NotContains(t, sawSources, "noise.md")
}
func TestBrainAnswer_NoLLM(t *testing.T) {
srv := mcp.NewServer(t.TempDir(), nil, nil, nil)
ts := httptest.NewServer(srv)
defer ts.Close()
rpc := callTool(t, ts, "brain_answer", map[string]any{"query": "test"})
assert.NotNil(t, rpc["error"], "expected error when answerLLM is nil")
}
func TestBrainAnswer_Synthesizes(t *testing.T) {
brainDir := brainDirWithContent(t)
srv := mcp.NewServer(brainDir, nil, nil, mockAnswerLLM("Pass-rate logging is described in spec."))
ts := httptest.NewServer(srv)
defer ts.Close()
rpc := callTool(t, ts, "brain_answer", map[string]any{"query": "pass-rate logging"})
require.Nil(t, rpc["error"])
content := rpc["result"].(map[string]any)["content"].([]any)[0].(map[string]any)["text"].(string)
var result map[string]any
require.NoError(t, json.Unmarshal([]byte(content), &result))
assert.Equal(t, "Pass-rate logging is described in spec.", result["answer"])
assert.NotEmpty(t, result["sources"])
}
func TestBrainClassify_ReturnsJSON(t *testing.T) {
llmResp := `{"type":"spec","title":"My Spec","tags":["go","mcp"]}`
srv := mcp.NewServer(t.TempDir(), nil, nil, mockAnswerLLM(llmResp))
ts := httptest.NewServer(srv)
defer ts.Close()
rpc := callTool(t, ts, "brain_classify", map[string]any{"text": "# My Spec\n\nThis is a Go MCP spec."})
require.Nil(t, rpc["error"])
content := rpc["result"].(map[string]any)["content"].([]any)[0].(map[string]any)["text"].(string)
var result map[string]any
require.NoError(t, json.Unmarshal([]byte(content), &result))
assert.Equal(t, "spec", result["type"])
assert.Equal(t, "My Spec", result["title"])
}
func TestBrainClassify_StripsFences(t *testing.T) {
llmResp := "```json\n{\"type\":\"note\",\"title\":\"T\",\"tags\":[]}\n```"
srv := mcp.NewServer(t.TempDir(), nil, nil, mockAnswerLLM(llmResp))
ts := httptest.NewServer(srv)
defer ts.Close()
rpc := callTool(t, ts, "brain_classify", map[string]any{"text": "some text"})
require.Nil(t, rpc["error"])
content := rpc["result"].(map[string]any)["content"].([]any)[0].(map[string]any)["text"].(string)
var result map[string]any
require.NoError(t, json.Unmarshal([]byte(content), &result))
assert.Equal(t, "note", result["type"])
}