feat: operator-defined model aliases

Spec §5 (v0.2): Config.ModelAliases map[string]string, alias-first
resolution precedence ahead of provider-prefix splitting, alias-OR-target
authorization, lazy target resolution with a 404 naming both ids,
/v1/models listing, admin overview alias table (JSON + dashboard), and
construction-time validation (shape, prefix-shadow, explicit-model
collision, chain, empty target).

routes_unified.go/routes_media.go needed no resolution-call-site changes
- both already pass the client's raw requested id through to
registry.resolve, so aliases inherit the __alias echo and multipart
rewrite machinery for free. cache.go needed no changes either - cacheKey
already hashes requestedModel, so two aliases resolving to the same
target already produce distinct cache entries.

Adds registry_test.go validation table + precedence/authz/lazy-404/
listing coverage, a dedicated cache-key split test, chat/embeddings/
images/audio-transcriptions end-to-end tests, an extended admin overview
test, and an integration test covering the openai-type vs anthropic-type
echo asymmetry under real Traefik+Yaegi.
This commit is contained in:
2026-08-20 20:56:01 +01:00
parent f49c51b341
commit 2090b31ae2
12 changed files with 1221 additions and 15 deletions
+9
View File
@@ -27,6 +27,15 @@ type Config struct {
// all — ServeHTTP falls through to its existing 404/passthroughUnknown
// handling for those paths, preserving v0.1 behavior exactly.
Admin *AdminConfig `json:"admin,omitempty"`
// ModelAliases maps an operator-defined alias id to a target model id
// (spec §5, v0.2) — e.g. {"aliased/coding": "anthropic/claude-sonnet-4-5"}.
// An exact alias match wins resolution before any other rule
// (modelRegistry.resolve, registry.go); the target then resolves
// through the normal rules. nil/omitted preserves v0.1 behavior
// exactly: resolve never consults an empty alias map, so no existing
// model id's resolution changes. Validated at construction
// (validateModelAliases, registry.go).
ModelAliases map[string]string `json:"modelAliases,omitempty"`
// Retry is a struct value, not a pointer, because its own Enabled
// field is the on/off signal (unlike Redis/Users, where the block's
// mere presence is the signal) — so its tag omits "omitempty":