feat(brain): add Gemini as brain_answer's third LLM tier
llm.Router was primary-then-fallback (berget -> iguana ollama). Both have failed together at least once in production (berget 5xx outage + a cold fallback model exceeding the shared timeout budget), leaving brain_answer/brain_classify fully down. Router gains an optional Tertiary *Client, tried only if both Primary and Fallback fail. Nil-safe — existing 2-tier deployments (no BRAIN_LLM_TERTIARY_URL) behave exactly as before. main.go wires it from BRAIN_LLM_TERTIARY_URL/MODEL + GEMINI_API_KEY, pointed at Google's OpenAI-compatible Gemini endpoint (generativelanguage.googleapis.com/v1beta/openai/) — llm.Client already speaks OpenAI-shaped chat-completions, so no new client type needed. Tests: TestRouter_FallsBackToTertiaryWhenPrimaryAndFallbackFail, TestRouter_TertiaryNotCalledWhenFallbackSucceeds, TestRouter_AllThreeFail, TestRouter_NilTertiary (2-tier backward-compat). Full suite green (both modules, -race), golangci-lint clean. Deployment env vars (infra repo, separate commit — GitOps, TBD there too): BRAIN_LLM_TERTIARY_URL, BRAIN_LLM_TERTIARY_MODEL, GEMINI_API_KEY secretRef. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
@@ -236,6 +236,11 @@ func main() {
|
|||||||
fallbackModel := envOr("BRAIN_LLM_FALLBACK_MODEL", "gemma4:31b")
|
fallbackModel := envOr("BRAIN_LLM_FALLBACK_MODEL", "gemma4:31b")
|
||||||
router.Fallback = llm.New(fallbackURL, "", fallbackModel, timeout)
|
router.Fallback = llm.New(fallbackURL, "", fallbackModel, timeout)
|
||||||
}
|
}
|
||||||
|
if tertiaryURL := os.Getenv("BRAIN_LLM_TERTIARY_URL"); tertiaryURL != "" {
|
||||||
|
tertiaryModel := envOr("BRAIN_LLM_TERTIARY_MODEL", "gemini-2.5-flash")
|
||||||
|
tertiaryKey := os.Getenv("GEMINI_API_KEY")
|
||||||
|
router.Tertiary = llm.New(tertiaryURL, tertiaryKey, tertiaryModel, timeout)
|
||||||
|
}
|
||||||
answerComplete = router.Complete
|
answerComplete = router.Complete
|
||||||
logger.Info("brain answer LLM configured", "primary", primaryURL, "model", primaryModel)
|
logger.Info("brain answer LLM configured", "primary", primaryURL, "model", primaryModel)
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -5,14 +5,18 @@ import (
|
|||||||
"fmt"
|
"fmt"
|
||||||
)
|
)
|
||||||
|
|
||||||
// Router calls Primary first; on any error falls back to Fallback.
|
// Router calls Primary first; on any error falls back to Fallback, then to
|
||||||
// Fallback may be nil, in which case primary errors are returned directly.
|
// Tertiary. Fallback and Tertiary may each be nil — a nil tier is skipped and
|
||||||
|
// the chain returns the errors accumulated so far.
|
||||||
type Router struct {
|
type Router struct {
|
||||||
Primary *Client
|
Primary *Client
|
||||||
Fallback *Client
|
Fallback *Client
|
||||||
|
Tertiary *Client
|
||||||
}
|
}
|
||||||
|
|
||||||
// Complete implements pipeline.CompleteFunc, routing through Primary then Fallback.
|
// Complete implements pipeline.CompleteFunc, routing through Primary, then
|
||||||
|
// Fallback, then Tertiary — trying each configured tier in order and
|
||||||
|
// returning the first success.
|
||||||
func (r *Router) Complete(ctx context.Context, system, user string) (string, error) {
|
func (r *Router) Complete(ctx context.Context, system, user string) (string, error) {
|
||||||
out, err := r.Primary.Complete(ctx, system, user)
|
out, err := r.Primary.Complete(ctx, system, user)
|
||||||
if err == nil {
|
if err == nil {
|
||||||
@@ -22,8 +26,15 @@ func (r *Router) Complete(ctx context.Context, system, user string) (string, err
|
|||||||
return "", fmt.Errorf("primary llm: %w", err)
|
return "", fmt.Errorf("primary llm: %w", err)
|
||||||
}
|
}
|
||||||
out, err2 := r.Fallback.Complete(ctx, system, user)
|
out, err2 := r.Fallback.Complete(ctx, system, user)
|
||||||
if err2 != nil {
|
if err2 == nil {
|
||||||
|
return out, nil
|
||||||
|
}
|
||||||
|
if r.Tertiary == nil {
|
||||||
return "", fmt.Errorf("primary llm: %w; fallback llm: %v", err, err2)
|
return "", fmt.Errorf("primary llm: %w; fallback llm: %v", err, err2)
|
||||||
}
|
}
|
||||||
|
out, err3 := r.Tertiary.Complete(ctx, system, user)
|
||||||
|
if err3 != nil {
|
||||||
|
return "", fmt.Errorf("primary llm: %w; fallback llm: %v; tertiary llm: %v", err, err2, err3)
|
||||||
|
}
|
||||||
return out, nil
|
return out, nil
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -69,3 +69,78 @@ func TestRouter_NilFallback(t *testing.T) {
|
|||||||
_, err := r.Complete(context.Background(), "sys", "user")
|
_, err := r.Complete(context.Background(), "sys", "user")
|
||||||
assert.Error(t, err)
|
assert.Error(t, err)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func TestRouter_FallsBackToTertiaryWhenPrimaryAndFallbackFail(t *testing.T) {
|
||||||
|
fail := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||||
|
http.Error(w, "unavailable", http.StatusServiceUnavailable)
|
||||||
|
}))
|
||||||
|
defer fail.Close()
|
||||||
|
tertiary := mockServer(t, "from-tertiary")
|
||||||
|
defer tertiary.Close()
|
||||||
|
|
||||||
|
r := &Router{
|
||||||
|
Primary: New(fail.URL, "", "m", time.Second),
|
||||||
|
Fallback: New(fail.URL, "", "m", time.Second),
|
||||||
|
Tertiary: New(tertiary.URL, "", "m", time.Second),
|
||||||
|
}
|
||||||
|
out, err := r.Complete(context.Background(), "sys", "user")
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, "from-tertiary", out)
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestRouter_TertiaryNotCalledWhenFallbackSucceeds(t *testing.T) {
|
||||||
|
fail := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||||
|
http.Error(w, "unavailable", http.StatusServiceUnavailable)
|
||||||
|
}))
|
||||||
|
defer fail.Close()
|
||||||
|
fallback := mockServer(t, "from-fallback")
|
||||||
|
defer fallback.Close()
|
||||||
|
tertiary := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||||
|
t.Error("tertiary must not be called when fallback succeeds")
|
||||||
|
}))
|
||||||
|
defer tertiary.Close()
|
||||||
|
|
||||||
|
r := &Router{
|
||||||
|
Primary: New(fail.URL, "", "m", time.Second),
|
||||||
|
Fallback: New(fallback.URL, "", "m", time.Second),
|
||||||
|
Tertiary: New(tertiary.URL, "", "m", time.Second),
|
||||||
|
}
|
||||||
|
out, err := r.Complete(context.Background(), "sys", "user")
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, "from-fallback", out)
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestRouter_AllThreeFail(t *testing.T) {
|
||||||
|
fail := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||||
|
http.Error(w, "err", http.StatusBadGateway)
|
||||||
|
}))
|
||||||
|
defer fail.Close()
|
||||||
|
|
||||||
|
r := &Router{
|
||||||
|
Primary: New(fail.URL, "", "m", time.Second),
|
||||||
|
Fallback: New(fail.URL, "", "m", time.Second),
|
||||||
|
Tertiary: New(fail.URL, "", "m", time.Second),
|
||||||
|
}
|
||||||
|
_, err := r.Complete(context.Background(), "sys", "user")
|
||||||
|
assert.Error(t, err)
|
||||||
|
assert.Contains(t, err.Error(), "primary llm")
|
||||||
|
assert.Contains(t, err.Error(), "fallback llm")
|
||||||
|
assert.Contains(t, err.Error(), "tertiary llm")
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestRouter_NilTertiary(t *testing.T) {
|
||||||
|
// Existing 2-tier deployments (no BRAIN_LLM_TERTIARY_URL) must keep working
|
||||||
|
// exactly as before — Tertiary is opt-in, not required.
|
||||||
|
fail := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||||
|
http.Error(w, "err", http.StatusBadGateway)
|
||||||
|
}))
|
||||||
|
defer fail.Close()
|
||||||
|
|
||||||
|
r := &Router{
|
||||||
|
Primary: New(fail.URL, "", "m", time.Second),
|
||||||
|
Fallback: New(fail.URL, "", "m", time.Second),
|
||||||
|
}
|
||||||
|
_, err := r.Complete(context.Background(), "sys", "user")
|
||||||
|
assert.Error(t, err)
|
||||||
|
assert.NotContains(t, err.Error(), "tertiary")
|
||||||
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user