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>

lakehouse.toml

@@ -15,6 +15,7 @@ embedd_url   = "http://127.0.0.1:3216"
 pathwayd_url = "http://127.0.0.1:3217"
 matrixd_url  = "http://127.0.0.1:3218"
 observerd_url = "http://127.0.0.1:3219"
+chatd_url    = "http://127.0.0.1:3220"
 
 [storaged]
 bind = "127.0.0.1:3211"
@@ -70,6 +71,36 @@ bind = "127.0.0.1:3219"
 # /var/lib/lakehouse/observer/ops.jsonl so ops survive restart.
 persist_path = ""
 
+[chatd]
+# LLM chat dispatcher (Phase 4). Routes /v1/chat to the right provider
+# based on model name prefix or :cloud suffix:
+#   ollama/<model>            → local Ollama (no auth)
+#   ollama_cloud/<model>      → Ollama Cloud
+#   <model>:cloud             → Ollama Cloud (suffix variant)
+#   openrouter/<vendor>/<m>   → OpenRouter
+#   opencode/<model>          → OpenCode (Zen+Go unified)
+#   kimi/<model>              → Kimi For Coding
+#   bare names (e.g. qwen3.5:latest) → local Ollama (default)
+bind       = "127.0.0.1:3220"
+ollama_url = "http://localhost:11434"
+
+# Per-provider key resolution: env var first, then .env file fallback.
+# Empty file path skips the file lookup. systemd EnvironmentFile=
+# loads these natively, so service runtime sees the env vars.
+ollama_cloud_key_env  = "OLLAMA_CLOUD_KEY"
+openrouter_key_env    = "OPENROUTER_API_KEY"
+opencode_key_env      = "OPENCODE_API_KEY"
+kimi_key_env          = "KIMI_API_KEY"
+
+ollama_cloud_key_file = "/etc/lakehouse/ollama_cloud.env"
+openrouter_key_file   = "/etc/lakehouse/openrouter.env"
+opencode_key_file     = "/etc/lakehouse/opencode.env"
+kimi_key_file         = "/etc/lakehouse/kimi.env"
+
+# Per-call timeout (seconds). Cloud reasoning models can take >60s
+# for long prompts, so 180 is the default.
+timeout_secs = 180
+
 [s3]
 endpoint        = "http://localhost:9000"
 region          = "us-east-1"