root 05273ac06b phase 4: chatd — multi-provider LLM dispatcher (ollama / cloud / openrouter / opencode / kimi)
new cmd/chatd on :3220 routes /v1/chat to the right provider based
on model-name prefix or :cloud suffix. closes the architectural gap
named in lakehouse.toml [models]: tiers map to model IDs, but until
phase 4 there was no service that could actually CALL those models
from go.

routing rules (registry.Resolve):
  ollama/<m>          → local Ollama (prefix stripped)
  ollama_cloud/<m>    → Ollama Cloud
  <m>:cloud           → Ollama Cloud (suffix variant — kimi-k2.6:cloud)
  openrouter/<v>/<m>  → OpenRouter (prefix stripped, OpenAI-compat)
  opencode/<m>        → OpenCode unified Zen+Go
  kimi/<m>            → Kimi For Coding (api.kimi.com/coding/v1)
  bare names          → local Ollama (default)

provider implementations:
- internal/chat/types.go      Provider interface, Request/Response, errors
- internal/chat/registry.go   prefix + :cloud suffix dispatch
- internal/chat/ollama.go     local Ollama via /api/chat (think=false default)
- internal/chat/ollama_cloud.go  Ollama Cloud via /api/generate (Bearer auth)
- internal/chat/openai_compat.go shared OpenAI Chat Completions for the
                                 OpenRouter/OpenCode/Kimi family
- internal/chat/builder.go    BuildRegistry from BuilderInput;
                              ResolveKey reads env then .env file fallback

config:
- ChatdConfig in internal/shared/config.go with bind, ollama_url,
  per-provider key env names + .env fallback paths, timeout
- Gateway gains chatd_url + /v1/chat + /v1/chat/* routes
- lakehouse.toml [chatd] block with /etc/lakehouse/<provider>.env defaults

tests (19 in internal/chat):
- registry: prefix + :cloud + errors + telemetry + provider listing
- ollama: happy path + prefix strip + format=json + 500 mapping +
  flatten_messages
- openai_compat: happy path + format=json + 429 mapping + zero-choices

think=false default in ollama + ollama_cloud — local hot path skips
reasoning, low-budget callers (the playbook_lift judge at max_tokens=10)
get direct answers instead of empty content + done_reason=length.
proven via chatd_smoke acceptance.

acceptance gate: scripts/chatd_smoke.sh — 6/6 PASS:
1. /v1/chat/providers lists exactly registered providers (1 in dev mode)
2. bare model → ollama default with content + token counts + latency
3. explicit ollama/<m> → prefix stripped at upstream
4. <m>:cloud without ollama_cloud registered → 404 (no silent fall-through)
5. unknown/<m> → falls through to default → upstream 502 (no prefix rewrite)
6. missing model field → 400

just verify: PASS (vet + 30 packages × short tests + 9 smokes).
chatd_smoke is a domain smoke (not in just verify, mirrors matrix /
observer / pathway pattern).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-30 00:08:29 -05:00

134 lines
5.0 KiB
Go

// gateway is the Lakehouse-Go HTTP ingress. D6 promotes the D1
// stub endpoints into real reverse-proxies fronting all four backing
// services (storaged, catalogd, ingestd, queryd) on a single bind.
//
// Routes:
// /v1/storage/* → storaged
// /v1/catalog/* → catalogd
// /v1/ingest → ingestd
// /v1/sql → queryd
//
// The /v1 prefix lives at the edge — internal services route on
// /storage, /catalog, /ingest, /sql. Per Kimi K2 finding from the
// D1 plan review: httputil.NewSingleHostReverseProxy preserves the
// inbound path by default, so the proxy helper strips /v1 in its
// Director before forwarding.
package main
import (
"flag"
"log/slog"
"net/url"
"os"
"github.com/go-chi/chi/v5"
"git.agentview.dev/profit/golangLAKEHOUSE/internal/gateway"
"git.agentview.dev/profit/golangLAKEHOUSE/internal/shared"
)
func main() {
configPath := flag.String("config", "lakehouse.toml", "path to TOML config")
flag.Parse()
cfg, err := shared.LoadConfig(*configPath)
if err != nil {
slog.Error("config", "err", err)
os.Exit(1)
}
upstreams := map[string]string{
"storaged_url": cfg.Gateway.StoragedURL,
"catalogd_url": cfg.Gateway.CatalogdURL,
"ingestd_url": cfg.Gateway.IngestdURL,
"queryd_url": cfg.Gateway.QuerydURL,
"vectord_url": cfg.Gateway.VectordURL,
"embedd_url": cfg.Gateway.EmbeddURL,
"pathwayd_url": cfg.Gateway.PathwaydURL,
"matrixd_url": cfg.Gateway.MatrixdURL,
"observerd_url": cfg.Gateway.ObserverdURL,
"chatd_url": cfg.Gateway.ChatdURL,
}
for k, v := range upstreams {
if v == "" {
slog.Error("config", "err", "gateway."+k+" is required")
os.Exit(1)
}
}
// Per scrum O-WARN2 (Opus): url.Parse is permissive — a typo
// like "127.0.0.1:3211" (missing scheme) parses without error
// but produces empty Host, and every proxied request 502s. Fail
// fast at startup if scheme/host are missing so misconfigs
// surface in `systemctl status gateway` rather than at first traffic.
storagedURL := mustParseUpstream("storaged_url", cfg.Gateway.StoragedURL)
catalogdURL := mustParseUpstream("catalogd_url", cfg.Gateway.CatalogdURL)
ingestdURL := mustParseUpstream("ingestd_url", cfg.Gateway.IngestdURL)
querydURL := mustParseUpstream("queryd_url", cfg.Gateway.QuerydURL)
vectordURL := mustParseUpstream("vectord_url", cfg.Gateway.VectordURL)
embeddURL := mustParseUpstream("embedd_url", cfg.Gateway.EmbeddURL)
pathwaydURL := mustParseUpstream("pathwayd_url", cfg.Gateway.PathwaydURL)
matrixdURL := mustParseUpstream("matrixd_url", cfg.Gateway.MatrixdURL)
observerdURL := mustParseUpstream("observerd_url", cfg.Gateway.ObserverdURL)
chatdURL := mustParseUpstream("chatd_url", cfg.Gateway.ChatdURL)
storagedProxy := gateway.NewProxyHandler(storagedURL)
catalogdProxy := gateway.NewProxyHandler(catalogdURL)
ingestdProxy := gateway.NewProxyHandler(ingestdURL)
querydProxy := gateway.NewProxyHandler(querydURL)
vectordProxy := gateway.NewProxyHandler(vectordURL)
embeddProxy := gateway.NewProxyHandler(embeddURL)
pathwaydProxy := gateway.NewProxyHandler(pathwaydURL)
matrixdProxy := gateway.NewProxyHandler(matrixdURL)
observerdProxy := gateway.NewProxyHandler(observerdURL)
chatdProxy := gateway.NewProxyHandler(chatdURL)
if err := shared.Run("gateway", cfg.Gateway.Bind, func(r chi.Router) {
// Storage / catalog have multi-segment paths under their
// prefix (e.g. /v1/storage/get/<key>). chi's `*` wildcard
// captures the rest of the path.
r.Handle("/v1/storage/*", storagedProxy)
r.Handle("/v1/catalog/*", catalogdProxy)
// Ingest + sql are single endpoints. We accept any method
// (GET/POST/etc) and let the backing service decide. ingestd
// only accepts POST; queryd only accepts POST. Other methods
// will get the backend's 405.
r.Handle("/v1/ingest", ingestdProxy)
r.Handle("/v1/sql", querydProxy)
// Vector search routes — /v1/vectors/index, /v1/vectors/index/{name}/...
r.Handle("/v1/vectors/*", vectordProxy)
// Embedding service — /v1/embed
r.Handle("/v1/embed", embeddProxy)
// Pathway memory — /v1/pathway/*
r.Handle("/v1/pathway/*", pathwaydProxy)
// Matrix indexer — /v1/matrix/* (multi-corpus retrieve+merge per SPEC §3.4)
r.Handle("/v1/matrix/*", matrixdProxy)
// Observer — /v1/observer/* (autonomous-iteration witness loop)
r.Handle("/v1/observer/*", observerdProxy)
// Chat — /v1/chat (LLM dispatcher) + /v1/chat/providers
r.Handle("/v1/chat", chatdProxy)
r.Handle("/v1/chat/*", chatdProxy)
}, cfg.Auth); err != nil {
slog.Error("server", "err", err)
os.Exit(1)
}
}
// mustParseUpstream parses an upstream URL string and validates that
// scheme + host are non-empty. Exits the process on failure — gateway
// can't function without a valid upstream so failing fast is the
// right call. Per scrum O-WARN2.
func mustParseUpstream(name, raw string) *url.URL {
u, err := url.Parse(raw)
if err != nil {
slog.Error("config", "err", "parse "+name+": "+err.Error())
os.Exit(1)
}
if u.Scheme == "" || u.Host == "" {
slog.Error("config", "err", name+" must include scheme + host (got "+raw+")")
os.Exit(1)
}
return u
}