mirror of
https://github.com/Nezumi-2711/9router.git
synced 2026-09-22 13:38:31 +00:00
Phuong Lambert
783e271c16
Add gemini-3.6-flash tiered (high/medium/low) for Antigravity routing via upstreamModelId "gemini-3.6-flash-tiered(level)" + thinkingLevel, plus gemini-3.6-flash and gemini-3.5-flash-lite direct API models. - getModelUpstreamId: split (level) suffix before lookup, re-append after - Antigravity executor: preserve transformed body.model - MITM extractModel: parse thinkingLevel for tiered model (default medium) - Isolate Cloud Code endpoints: discovery (loadCodeAssist/onboardUser/ quota) on PROD cloudcode-pa, chat transport on daily-cloudcode-pa to bypass prod 429
25 lines
2.8 KiB
Plaintext
25 lines
2.8 KiB
Plaintext
tests/unit/claude-header-forwarding.test.js :: proxyAwareFetch — api.anthropic.com routing routes api.anthropic.com to gotScraping (non-streaming) and returns ok response
|
|
tests/unit/oauth-cursor-auto-import.test.js :: GET /api/oauth/cursor/auto-import extracts tokens using exact keys
|
|
tests/unit/oauth-cursor-auto-import.test.js :: GET /api/oauth/cursor/auto-import falls back to fuzzy key matching on macOS when exact keys are missing
|
|
tests/unit/oauth-cursor-auto-import.test.js :: GET /api/oauth/cursor/auto-import linux uses single hardcoded path and original error message
|
|
tests/unit/oauth-cursor-auto-import.test.js :: GET /api/oauth/cursor/auto-import returns descriptive error if macOS db file exists but cannot be opened
|
|
tests/unit/oauth-cursor-auto-import.test.js :: GET /api/oauth/cursor/auto-import returns login-prompt error when tokens are missing even after fallback
|
|
tests/unit/oauth-cursor-auto-import.test.js :: GET /api/oauth/cursor/auto-import returns not-found when no macOS cursor db paths are accessible
|
|
tests/unit/oauth-cursor-auto-import.test.js :: GET /api/oauth/cursor/auto-import unsupported platform returns 400
|
|
tests/unit/oauth-cursor-auto-import.test.js :: GET /api/oauth/cursor/auto-import unwraps JSON-encoded string values
|
|
tests/unit/openai-to-claude.test.js :: openaiToClaudeResponse omits empty Read pages tool argument before emitting Claude input deltas
|
|
tests/unit/rtk.test.js :: RTK flag default off, toggle works
|
|
tests/unit/rtk.test.js :: compressMessages (disabled) returns null when disabled
|
|
tests/unit/rtk.test.js :: compressMessages (enabled) compresses Claude array-form tool_result text parts
|
|
tests/unit/rtk.test.js :: compressMessages (enabled) compresses Claude string-form tool_result
|
|
tests/unit/rtk.test.js :: compressMessages (enabled) compresses OpenAI tool message (string content)
|
|
tests/unit/rtk.test.js :: compressMessages (enabled) handles mix of messages without crashing
|
|
tests/unit/rtk.test.js :: compressMessages (enabled) never produces empty content (R14 guard)
|
|
tests/unit/rtk.test.js :: compressMessages (enabled) skips below MIN_COMPRESS_SIZE (<500 bytes)
|
|
tests/unit/rtk.test.js :: compressMessages (enabled) skips is_error tool_result
|
|
tests/unit/rtk.test.js :: compressMessages (enabled) skips when body has no messages
|
|
tests/unit/translator-request-normalization.test.js :: request normalization claudeToOpenAIRequest flattens text-only content arrays into string
|
|
tests/unit/translator-request-normalization.test.js :: request normalization filterToOpenAIFormat flattens text-only arrays to string
|
|
tests/unit/translator-request-normalization.test.js :: request normalization parseSSELine supports provider raw NDJSON stream lines
|
|
tests/unit/translator-request-normalization.test.js :: request normalization translateRequest keeps /v1/messages Claude->OpenAI text payloads string-safe
|