The R1-R3 refactors removed the per-provider handle*Error methods,
consolidated validators into validateNumberInRange, renamed Gemini's
buildGenerationConfig to buildConfig, and split OpenWebUI's message
conversion and response formatting into openwebui-strategies.ts.
44 of 91 existing tests broke as a result.
Changes:
claude.test.ts (8 -> 13 passing)
- Switch error mapping tests from handleAnthropicError to the base
normalizeError method.
- Update temperature error-message expectation to match the new
validateNumberInRange wording.
openai.test.ts (16 -> 22 passing)
- Same handleOpenAIError -> normalizeError switch.
- Add a regression test for the 429+"quota" path that goes through
mapProviderError instead of the base mapping.
gemini.test.ts (17 -> 27 passing)
- Update getInfo expectations to the new default model (gemini-2.5)
and provider version 2.0.0.
- Switch to normalizeError.
- Rename buildGenerationConfig -> buildConfig (renamed during R2).
- Update formatCompletionResponse mocks: the @google/genai SDK
exposes response.text as a getter rather than walking
candidates[0].content.parts.
openwebui.test.ts (4 -> 19 passing)
- Drop tests for convertMessages / convertMessagesToPrompt /
formatChatResponse / formatOllamaResponse / makeRequest: these
moved into openwebui-strategies.ts and openwebui-http.ts during R3
and warrant their own test files.
- Add error-mapping tests covering the new mapProviderError +
providerErrorMessages plumbing.
claude-code.test.ts (new, 18 tests)
- Constructor accepts subscription mode (empty config).
- getInfo advertises subscriptionAuth + requiresLocalCli.
- mapProviderError catches ENOENT and "not logged in".
- errorForSdkAssistantError covers each documented SDK error code.
- buildPrompt handles single-turn pass-through, multi-system
combination, multi-turn flattening with role labels, and rejects
empty turn lists.
Full suite: 100 pass / 0 fail across 5 files.
