Session infrastructure: OpenRouter + tree-split reducer + observer→LLM Team + scrum_applier #11
@ -95,8 +95,35 @@ async fn main() {
|
||||
tracing::warn!("workspace rebuild: {e}");
|
||||
}
|
||||
|
||||
// AI sidecar client
|
||||
let ai_client = aibridge::client::AiClient::new(&config.sidecar.url);
|
||||
// AI sidecar clients — Phase 44 part 3 (2026-04-27).
|
||||
//
|
||||
// Two flavors of the same client:
|
||||
// - `ai_client_direct` posts directly to ${sidecar}/generate. Used
|
||||
// inside the gateway by V1State + the legacy /ai proxy. These
|
||||
// call sites are themselves the implementation of /v1/chat
|
||||
// (or its sidecar shim), so routing them through /v1/chat
|
||||
// would self-loop.
|
||||
// - `ai_client_observable` posts via ${gateway}/v1/chat with
|
||||
// provider="ollama". Used by vectord modules (autotune agent,
|
||||
// /vectors service) so their LLM calls land in /v1/usage and
|
||||
// Langfuse traces. Adds one localhost HTTP hop per call (~ms);
|
||||
// accepted for the observability gain.
|
||||
//
|
||||
// The gateway can call its own /v1/chat over localhost during
|
||||
// boot's transient period because we don't fire any LLM calls
|
||||
// until the listener is up — the observable client is just
|
||||
// configured here, not exercised.
|
||||
let ai_client_direct = aibridge::client::AiClient::new(&config.sidecar.url);
|
||||
let gateway_self_url = format!("http://{}:{}", config.gateway.host, config.gateway.port);
|
||||
let ai_client_observable = aibridge::client::AiClient::new_with_gateway(
|
||||
&config.sidecar.url,
|
||||
&gateway_self_url,
|
||||
);
|
||||
// Backwards-compat alias for the (many) existing references in this file.
|
||||
// Defaults to direct so the existing wiring (V1State, /ai proxy)
|
||||
// keeps its non-self-loop transport. New vectord wiring below
|
||||
// explicitly uses ai_client_observable.
|
||||
let ai_client = ai_client_direct.clone();
|
||||
|
||||
// Vector service components — built before the router because both the
|
||||
// /vectors service AND ingestd need the agent handle to enqueue triggers.
|
||||
@ -134,7 +161,9 @@ async fn main() {
|
||||
agent_cfg,
|
||||
vectord::agent::AgentDeps {
|
||||
store: store.clone(),
|
||||
ai_client: ai_client.clone(),
|
||||
// Observable: autotune agent's LLM calls go through
|
||||
// /v1/chat for /v1/usage + Langfuse visibility.
|
||||
ai_client: ai_client_observable.clone(),
|
||||
catalog: registry.clone(),
|
||||
index_registry: index_reg.clone(),
|
||||
hnsw_store: hnsw.clone(),
|
||||
@ -189,7 +218,9 @@ async fn main() {
|
||||
}))
|
||||
.nest("/vectors", vectord::service::router(vectord::service::VectorState {
|
||||
store: store.clone(),
|
||||
ai_client: ai_client.clone(),
|
||||
// Observable: /vectors service's LLM calls (RAG, summary,
|
||||
// playbook synthesis, etc.) flow through /v1/chat.
|
||||
ai_client: ai_client_observable.clone(),
|
||||
job_tracker: vectord::jobs::JobTracker::new(),
|
||||
index_registry: index_reg.clone(),
|
||||
hnsw_store: hnsw,
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user