Use resolved targets for client routing

docs/integrations/openai-compatible-chat.md

@@ -16,14 +16,13 @@ Generation sends an HTTP `POST` with `Content-Type: application/json`.
 Before the client is called, the engine resolves framework, backend, profile,
 and request values into one execution target. Endpoint configuration is trimmed
 and must be an absolute HTTP or HTTPS URL with a host and without user
-information, a query, or a fragment. A non-empty endpoint from the target
-overrides the client's configured base URL. The final selected endpoint is
-validated again before transport.
+information, a query, or a fragment. The target's endpoint is validated again
+before transport.
 
 The completion URL is composed through parsed URL path operations. Nested base
 paths are retained, repeated trailing slashes are normalized, and the result
 has exactly one appended `/chat/completions` suffix. Generation fails before
-sending when neither source supplies a valid endpoint.
+sending when the target does not supply a valid endpoint.
 
 The target's backend ID is routing metadata for prepared values, results, and
 injected clients. The built-in client does not derive the URL from that ID and
@@ -89,8 +88,7 @@ transport for HTTP-only diagnostics.
 ## Request Body
 
 The request body always contains `model` and `messages`. The execution
-target's model takes precedence over the client's configured model, and one
-must be available.
+target's model must be available.
 
 Each ordinary message contains its `role` and string `content`. A
 cache-controlled message instead uses a text content block containing `type`,

docs/internal/llm.md

@@ -26,10 +26,9 @@ client uses its endpoint, credential metadata, generation fields, and extra
 parameters. `BackendID` remains routing metadata
 for the generation boundary and is not mapped into the provider payload.
 
-Construction trims and validates a nonempty configured base URL and clones any
-supplied `http.Client` so Promptkit can apply its timeout default without
-mutating the caller's client. An empty configured base remains valid because a
-resolved request target may supply the endpoint. Generation preparation then:
+Construction clones any supplied `http.Client` so Promptkit can apply its
+timeout default without mutating the caller's client. Generation preparation
+then:
 
 1. validates shared execution-setting invariants and the final selected base
    endpoint;
@@ -106,14 +105,13 @@ public ownership and redaction semantics belong to the
 
 ## Failure Categories
 
-The package preserves distinct error identities for invalid client
-configuration, invalid generation requests, request execution failures,
-non-success provider statuses, and malformed successful responses. Provider
-response bodies are never exposed in raw form through non-success errors.
+The package preserves distinct error identities for invalid generation
+requests, request execution failures, non-success provider statuses, and
+malformed successful responses. Provider response bodies are never exposed in
+raw form through non-success errors.
 
-Invalid nonempty configured endpoints are configuration failures. A missing or
-invalid final selected endpoint is an invalid generation request and is
-rejected before transport.
+A missing or invalid final selected endpoint is an invalid generation request
+and is rejected before transport.
 
 Authentication resolves a trimmed direct key before a trimmed configured
 environment value. Optional missing, empty, or whitespace-only sources do not

docs/roadmap/implementation.md

@@ -71,6 +71,11 @@ introduce a new ownership subsystem.
 
 ## Stage 1: Remove Client-Level Routing Fallbacks
 
+**Completed:** Client routing now uses the resolved target; constructor fixtures
+and integration guidance were migrated. With Go 1.27.3, `go test ./internal/llm
+./internal/generation ./internal/configuration ./internal/usecase ./internal/engine`
+passed, including loaded-target coverage.
+
 **Finding:** 1. **Files:** `internal/llm/openai_compatible_client.go`, client
 fixtures/tests, `internal/engine/engine.go` caller verification, `docs/internal/llm.md`.