Ed Zynda 10abb29e4f fix(models): route auto-discovered providers by wire protocol (#41) ...

- replace npmToLLMProvider map with npmToWireProtocol (openai/anthropic/google)
- add createAutoRoutedGoogleProvider so @ai-sdk/google proxies work
  (fixes opencode/gemini-* failing with "no LLM provider mapping")
- strip the genai-injected v1beta segment for proxies whose base URL
  already carries a version (e.g. opencode's /zen/v1)
- preserve openai-compat fallback and clearer error for unroutable providers
- document auto-routing in README and providers docs; update CreateProvider godoc
- add regression tests for wire routing and version-path rewriting

Fixes #41

2026-06-02 15:07:07 +03:00

..

autoroute_test.go

fix(models): route auto-discovered providers by wire protocol (#41)

2026-06-02 15:07:07 +03:00

cache_options_test.go

gofmt trailing-blank-line cleanup after dead-code removal

2026-05-07 12:34:29 +03:00

cache_options.go

gofmt trailing-blank-line cleanup after dead-code removal

2026-05-07 12:34:29 +03:00

cache.go

rename: fork mcphost to kit (github.com/mark3labs/kit)

2026-02-26 16:59:59 +03:00

custom_test.go

feat(models): add per-model system prompt support

2026-04-09 12:35:00 +03:00

custom.go

feat(kit): isolate viper config per Kit instance + add NewAgent (#42)

2026-06-02 14:41:35 +03:00

embedded_models.json

chore(models): refresh embedded models database from models.dev

2026-05-29 15:09:26 +03:00

modelsdb.go

fix(models): route auto-discovered providers by wire protocol (#41)

2026-06-02 15:07:07 +03:00

providers_test.go

fix(auth): support OAuth credentials in ACP mode and auto-refresh tokens

2026-03-15 12:38:23 +03:00

providers.go

fix(models): route auto-discovered providers by wire protocol (#41)

2026-06-02 15:07:07 +03:00

registry_test.go

feat(subagent): return early error for invalid model instead of silent fallback

2026-04-02 14:45:03 +03:00

registry.go

fix(models): route auto-discovered providers by wire protocol (#41)

2026-06-02 15:07:07 +03:00

rightsize_test.go

feat(models): surface and prevent silent max-tokens truncation

2026-04-16 23:12:10 +03:00