Files
hyperguild/cmd/routing/main.go
mathiasandClaude Opus 4.8 da9bdc4cbb
CI / Lint / Test / Vet (push) Successful in 13s
CI / Mirror to GitHub (push) Successful in 4s
fix(routing): repair pass-rate instrumentation (3 bugs) — #73, #35
The #35 data gate could never fill: a real review call routed cleanly to
qwen36 but /pass-rate stayed total:0 under every key. Root cause was three
independent defects in the session_log path, each alone fatal:

- A: a successful routed call logged final_status "skip", never "pass".
  /pass-rate computes pass/(pass+fail) and skips count as neither, so the
  >=0.90 gate was mathematically unreachable. Success now logs "pass".
- B: every record was written under skill "_routing", so /pass-rate?skill=
  review|debug (what #35 measures) always read zero. Now uses the real
  e.Skill; routing decisions stay groupable via session_id "_routing".
- C: the session_log POST to the bearer-gated ingestion /mcp carried no
  Authorization header → silent 401, swallowed by best-effort logging
  (the documented mcpclient-empty-token-silent-401 footgun). Logger now
  takes a token (BRAIN_MCP_TOKEN) and sets the bearer when non-empty.

Tests rewritten to assert correct behavior (they had encoded the bugs:
"skip" on success, "_routing" skill). New test covers the auth header and
the empty-token path.

Infra (BRAIN_MCP_TOKEN ExternalSecret + env on the routing deployment) and
redeploy follow separately. Refs #73, #35.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-30 08:36:18 +02:00

171 lines
5.8 KiB
Go

package main
// The internal/skills/{debug,retrospective,review,trainer} packages imported
// below are also imported by cmd/supervisor. Plan 7 (supervisor retirement)
// MUST NOT delete these four packages — the routing pod is their second
// consumer. Plan 7 deletes only internal/skills/{tdd,spec,tier} (the skills
// that don't route to local), the supervisor binary, and supervisor manifests.
// See docs/superpowers/specs/2026-05-04-mode-2-routing-pod-design.md (Constraints).
import (
"context"
"log/slog"
"net/http"
"os"
"time"
"github.com/mathiasbq/supervisor/internal/auth"
"github.com/mathiasbq/supervisor/internal/config"
iexec "github.com/mathiasbq/supervisor/internal/exec"
"github.com/mathiasbq/supervisor/internal/githubclient"
"github.com/mathiasbq/supervisor/internal/mcp"
"github.com/mathiasbq/supervisor/internal/mcpclient"
"github.com/mathiasbq/supervisor/internal/registry"
"github.com/mathiasbq/supervisor/internal/routing"
"github.com/mathiasbq/supervisor/internal/skills/debug"
"github.com/mathiasbq/supervisor/internal/skills/project"
"github.com/mathiasbq/supervisor/internal/skills/retrospective"
"github.com/mathiasbq/supervisor/internal/skills/review"
"github.com/mathiasbq/supervisor/internal/skills/trainer"
)
func main() {
logger := slog.New(slog.NewTextHandler(os.Stderr, nil))
slog.SetDefault(logger)
cfg, err := config.LoadRouting()
if err != nil {
logger.Error("config load failed", "err", err)
os.Exit(1)
}
configDir := envOr("SUPERVISOR_CONFIG_DIR", "/app/config/supervisor")
mustRead := func(path string) string {
b, err := os.ReadFile(configDir + "/" + path)
if err != nil {
logger.Error("read prompt failed", "path", path, "err", err)
os.Exit(1)
}
return string(b)
}
llm := iexec.NewLiteLLM(cfg.LiteLLMBaseURL, cfg.LiteLLMAPIKey, 0)
router := &routing.Router{
Fetcher: routing.NewFetcher(cfg.BrainURL, "7d", time.Duration(cfg.PassRateTTLSeconds)*time.Second),
Logger: routing.NewLogger(cfg.BrainURL, cfg.BrainMCPToken),
Policy: routing.Policy{Floor: cfg.RouteLocalFloor, Ceil: cfg.RouteLocalCeil},
FastModel: cfg.FastModel,
ThinkingModel: cfg.ThinkingModel,
Complete: llm.Complete,
}
// Skill packages call CompleteFunc(ctx, model, system, user) — no session_id
// or project_root in the signature. Rather than modifying every skill's API
// (and inflating Plan 6's blast radius), the routing pod logs every decision
// under a fixed session_id "_routing". Operators query
// `GET /pass-rate?skill=_routing&window=...` to inspect routing health.
const routingSessionID = "_routing"
wrap := func(skillName string) routing.CompleteFunc {
return func(ctx context.Context, _, system, user string) (string, int64, error) {
// The model param is ignored: the router picks the model based on policy.
return router.Run(ctx, routing.RunInput{
Skill: skillName,
System: system,
User: user,
SessionID: routingSessionID,
ProjectRoot: "",
})
}
}
reg := registry.New()
reg.Register(review.New(review.Config{
SkillPrompt: mustRead("review.md"),
DefaultModel: cfg.FastModel,
CompleteFunc: review.CompleteFunc(wrap("review")),
}))
reg.Register(debug.New(debug.Config{
SkillPrompt: mustRead("debug.md"),
DefaultModel: cfg.FastModel,
CompleteFunc: debug.CompleteFunc(wrap("debug")),
}))
reg.Register(retrospective.New(retrospective.Config{
SkillPrompt: mustRead("retrospective.md"),
DefaultModel: cfg.FastModel,
CompleteFunc: retrospective.CompleteFunc(wrap("retrospective")),
}))
reg.Register(trainer.New(trainer.Config{
ReaderPrompt: mustRead("trainer-reader.md"),
WriterPrompt: mustRead("trainer-writer.md"),
DefaultModel: cfg.FastModel,
CompleteFunc: trainer.CompleteFunc(wrap("trainer")),
}))
if cfg.GiteaMCPURL != "" {
mcpC, err := mcpclient.New(cfg.GiteaMCPURL, cfg.GiteaMCPToken)
if err != nil {
logger.Error("mcpclient init for project_create — GITEA_MCP_URL is set but GITEA_MCP_TOKEN is empty (check routing-secrets)", "err", err)
os.Exit(1)
}
var ghClient *githubclient.Client
if cfg.GitHubPAT != "" {
ghClient = githubclient.New(cfg.GitHubPAT)
}
reg.Register(project.New(project.Config{
Client: mcpC,
GitHub: ghClient,
GiteaOwner: cfg.GiteaOwner,
GitHubOwner: cfg.GitHubOwner,
GitHubPAT: cfg.GitHubPAT,
InfraRepo: cfg.InfraRepo,
}))
logger.Info("project_create registered", "gitea_mcp_url", cfg.GiteaMCPURL,
"gitea_owner", cfg.GiteaOwner, "github_owner", cfg.GitHubOwner,
"infra_repo", cfg.InfraRepo, "github_pat_set", cfg.GitHubPAT != "")
} else {
logger.Info("project_create skipped — GITEA_MCP_URL not set")
}
var validator *auth.Validator
if dexURL := os.Getenv("DEX_ISSUER_URL"); dexURL != "" {
audience := os.Getenv("MCP_AUDIENCE")
v, err := auth.NewValidator(dexURL, audience)
if err != nil {
logger.Error("build jwt validator", "err", err)
os.Exit(1)
}
validator = v
logger.Info("jwt auth enabled", "issuer", dexURL)
}
srv := mcp.NewServer(reg, cfg.MCPAuthToken, validator)
mux := http.NewServeMux()
mux.Handle("/mcp", srv)
mux.HandleFunc("/healthz", func(w http.ResponseWriter, _ *http.Request) {
w.WriteHeader(http.StatusOK)
})
if dexURL := os.Getenv("DEX_ISSUER_URL"); dexURL != "" {
resourceURL := os.Getenv("MCP_RESOURCE_URL")
mux.HandleFunc("GET /.well-known/oauth-protected-resource",
auth.ProtectedResourceHandler(resourceURL, dexURL))
}
addr := ":" + cfg.Port
logger.Info("routing pod starting", "addr", addr,
"fast", cfg.FastModel, "thinking", cfg.ThinkingModel,
"floor", cfg.RouteLocalFloor, "ceil", cfg.RouteLocalCeil)
if err := http.ListenAndServe(addr, mux); err != nil { //nolint:gosec
logger.Error("server stopped", "err", err)
os.Exit(1)
}
}
func envOr(key, def string) string {
if v := os.Getenv(key); v != "" {
return v
}
return def
}