05273ac06b
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>
150 lines
5.5 KiB
TOML
150 lines
5.5 KiB
TOML
# Lakehouse-Go config — G0 dev defaults. Overrides via env are a
|
||
# G1+ concern; for G0 edit this file and restart the affected service.
|
||
|
||
# G0 dev ports — shifted to 3110+ so the Go services run alongside
|
||
# the live Rust lakehouse on 3100/3201-3204 without colliding. G5
|
||
# (demo cutover) flips gateway back to 3100 when Rust retires.
|
||
[gateway]
|
||
bind = "127.0.0.1:3110"
|
||
storaged_url = "http://127.0.0.1:3211"
|
||
catalogd_url = "http://127.0.0.1:3212"
|
||
ingestd_url = "http://127.0.0.1:3213"
|
||
queryd_url = "http://127.0.0.1:3214"
|
||
vectord_url = "http://127.0.0.1:3215"
|
||
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"
|
||
|
||
[catalogd]
|
||
bind = "127.0.0.1:3212"
|
||
storaged_url = "http://127.0.0.1:3211"
|
||
|
||
[ingestd]
|
||
bind = "127.0.0.1:3213"
|
||
storaged_url = "http://127.0.0.1:3211"
|
||
catalogd_url = "http://127.0.0.1:3212"
|
||
# CSV uploads are ~4-6× the resulting Parquet. 256 MiB cap keeps the in-memory
|
||
# parse + Arrow + Parquet output footprint bounded. Bump for known large
|
||
# datasets (e.g. workers_500k → 344 MiB CSV needs 512 MiB).
|
||
max_ingest_bytes = 268435456
|
||
|
||
[vectord]
|
||
bind = "127.0.0.1:3215"
|
||
# Optional — set to empty string to disable persistence (dev/test).
|
||
storaged_url = "http://127.0.0.1:3211"
|
||
|
||
[embedd]
|
||
bind = "127.0.0.1:3216"
|
||
# G2: Ollama local. G3+ may swap in OpenAI/Voyage by changing
|
||
# this URL + the wire format inside the provider.
|
||
provider_url = "http://localhost:11434"
|
||
default_model = "nomic-embed-text"
|
||
|
||
[queryd]
|
||
bind = "127.0.0.1:3214"
|
||
catalogd_url = "http://127.0.0.1:3212"
|
||
secrets_path = "/etc/lakehouse/secrets-go.toml"
|
||
refresh_every = "30s"
|
||
|
||
[pathwayd]
|
||
bind = "127.0.0.1:3217"
|
||
# Empty = in-memory only (dev/test). Production sets a path under
|
||
# /var/lib/lakehouse/pathway/state.jsonl so traces survive restart.
|
||
persist_path = ""
|
||
|
||
[matrixd]
|
||
bind = "127.0.0.1:3218"
|
||
# matrixd calls embedd (query-text → vector) and vectord (per-corpus
|
||
# search) directly. Localhost defaults; in distributed deployments
|
||
# these point at the gateway's upstream addresses.
|
||
embedd_url = "http://127.0.0.1:3216"
|
||
vectord_url = "http://127.0.0.1:3215"
|
||
|
||
[observerd]
|
||
bind = "127.0.0.1:3219"
|
||
# Empty = in-memory only (dev/test). Production sets a path under
|
||
# /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"
|
||
bucket = "lakehouse-go-primary" # G0 dedicated bucket so Rust + Go coexist
|
||
access_key_id = "" # populated by SecretsProvider from /etc/lakehouse/secrets-go.toml
|
||
secret_access_key = "" # ditto
|
||
use_path_style = true
|
||
|
||
[log]
|
||
level = "info"
|
||
|
||
# Model tier registry — names map to actual model IDs per the small-
|
||
# model pipeline architecture (project_small_model_pipeline_vision.md).
|
||
# Bumping a model means editing one line here, not hunting through code.
|
||
#
|
||
# Tier philosophy:
|
||
# - local_* : on-box Ollama. Inner-loop hot path. Repeated calls.
|
||
# - cloud_* : Ollama Cloud (Pro plan). Larger context, fail-up tier.
|
||
# - frontier_* : OpenRouter / OpenCode. Rate-limited, billed per call.
|
||
# Reserved for blockers and full-scope reviews.
|
||
#
|
||
# weak_models is the codified "local-hot-path eligible" list that the
|
||
# matrix.downgrade gate reads. A model in this list bypasses the
|
||
# strong-model downgrade rule (it's already weak — no need to downgrade
|
||
# corpora further).
|
||
[models]
|
||
# Tier 1 — local hot path
|
||
local_fast = "qwen3.5:latest"
|
||
local_embed = "nomic-embed-text"
|
||
local_judge = "qwen3.5:latest"
|
||
local_review = "qwen3.5:latest"
|
||
|
||
# Tier 2 — Ollama Cloud (Pro). kimi-k2:1t still upstream-broken;
|
||
# deepseek/kimi-k2.6/qwen3-coder are the working primaries.
|
||
cloud_judge = "kimi-k2.6:cloud"
|
||
cloud_review = "qwen3-coder:480b"
|
||
cloud_strong = "deepseek-v3.2"
|
||
|
||
# Tier 3 — frontier. Use sparingly; rate-limited + per-call billing.
|
||
frontier_review = "openrouter/anthropic/claude-opus-4-7"
|
||
frontier_arch = "openrouter/moonshotai/kimi-k2-0905"
|
||
frontier_strong = "openrouter/openai/gpt-5"
|
||
frontier_free = "opencode/claude-opus-4-7"
|
||
|
||
# Local-hot-path eligible — matrix.downgrade bypass list.
|
||
weak_models = ["qwen3.5:latest", "qwen3:latest"]
|