Conversation
…ardization, and utilities
Core infrastructure improvements:
- Smart 'latest' model alias resolution with cost-based tiebreaking
- Standardized error responses with proper HTTP status codes and error.code field
- ProxyExhaustionError for structured credential exhaustion reporting
- TerminalRequestError for non-rotatable errors (404, model not found)
- Per-provider retry count override via MAX_RETRIES_{PROVIDER} env var
- Retry 429 rate_limit errors with backoff instead of rotating
- Cached token pricing in streaming cost calculation
- Split quota stats into current_period and global/lifetime views
- Log rotation for proxy.log and proxy_debug.log (RotatingFileHandler)
- Include latest virtual models in /v1/models endpoint
- Resolve singleton cache pollution for dynamic providers
- Fork-specific README and .gitignore updates
…ased model filtering, and enhanced X-Initiator heuristic
Test suite designed to catch breakage from branch re-organization without sending queries to real LLM providers. Covers all critical integration points that previously broke silently during deployment. Coverage: - Anthropic↔OpenAI format translation & streaming - Error classification (determines retry/rotation behavior) - Request sanitization (prevents 400s from invalid params) - Provider-specific request transforms - Model alias & latest registry parsing - Usage tracking (windows, quota groups, custom caps) - Credential discovery, deduplication, env:// URI - Provider plugin registration & singleton pattern - Proxy endpoint routing & auth All tests use synthetic credentials and mocked HTTP. Runs in ~2.3s. Zero API cost.
…flow Replaces the old manifest-driven multi-branch replay system with a simpler linear commit stack. Changes are made via fixup!/autosquash. Upstream syncs are a single git rebase. Includes: - AGENTS.md: entry point for all AI coding agents - .agent/rules/claude.md: Claude-specific SSH/deployment notes - .agent/rules/llm-proxy.md: container layout and deployment pipeline - .agent/skills/upstream-sync/SKILL.md: sync workflow reference
Custom provider for Google Vertex AI Express Mode API keys that uses x-goog-api-key header authentication against the Vertex AI OpenAI-compatible endpoint. Supports non-streaming and streaming chat completions with automatic model discovery. Models are prefixed as vertex/ (e.g. vertex/gemini-3.1-flash-lite-preview). Env vars: VERTEX_PROJECT, VERTEX_LOCATION, VERTEX_API_KEY_N
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
There was a problem hiding this comment.
Code Review
This pull request introduces unit tests for provider configuration accessors in tests/test_provider_config.py. The review feedback suggests enhancing the test suite by explicitly verifying the merge priority when combining data sources and refactoring multi-scenario tests using pytest parametrization for better isolation and readability.
| def test_get_full_provider_config_known_provider(): | ||
| """Test get_full_provider_config with a known provider.""" | ||
| mock_scraped_providers = { | ||
| "test_provider": { | ||
| "api_base": "https://api.test.com", | ||
| "models": ["model-a"], | ||
| } | ||
| } | ||
| mock_litellm_providers = { | ||
| "test_provider": { | ||
| "category": "test_category", | ||
| "note": "Test note", | ||
| } | ||
| } | ||
| with patch("rotator_library.provider_config.SCRAPED_PROVIDERS", mock_scraped_providers): | ||
| with patch("rotator_library.provider_config.LITELLM_PROVIDERS", mock_litellm_providers): | ||
| config = get_full_provider_config("test_provider") | ||
|
|
||
| # Should have properties from both | ||
| assert config["api_base"] == "https://api.test.com" | ||
| assert config["models"] == ["model-a"] | ||
| assert config["category"] == "test_category" | ||
| assert config["note"] == "Test note" |
There was a problem hiding this comment.
The test verifies that data from both sources is merged, but it doesn't verify the merge priority (i.e., that UI configuration overrides scraped data). Given that get_full_provider_config uses {**scraped, **ui_config}, it's important to ensure that if a key exists in both, the UI config value is the one preserved. It's also recommended to assert the entire dictionary to ensure no unexpected keys are present.
def test_get_full_provider_config_known_provider():
"""Test get_full_provider_config with a known provider, verifying merge priority."""
mock_scraped_providers = {
"test_provider": {
"api_base": "https://api.test.com",
"models": ["model-a"],
"category": "scraped_category",
}
}
mock_litellm_providers = {
"test_provider": {
"category": "test_category",
"note": "Test note",
}
}
with patch("rotator_library.provider_config.SCRAPED_PROVIDERS", mock_scraped_providers):
with patch("rotator_library.provider_config.LITELLM_PROVIDERS", mock_litellm_providers):
config = get_full_provider_config("test_provider")
assert config == {
"api_base": "https://api.test.com",
"models": ["model-a"],
"category": "test_category",
"note": "Test note",
}| def test_get_full_provider_config_partial_data(): | ||
| """Test get_full_provider_config when provider is only in scraped or only in UI config.""" | ||
| # Only in UI config | ||
| mock_litellm_providers = {"test_ui_only": {"category": "ui_only_category"}} | ||
| mock_scraped_providers = {} | ||
|
|
||
| with patch("rotator_library.provider_config.SCRAPED_PROVIDERS", mock_scraped_providers): | ||
| with patch("rotator_library.provider_config.LITELLM_PROVIDERS", mock_litellm_providers): | ||
| config = get_full_provider_config("test_ui_only") | ||
| assert config == {"category": "ui_only_category"} | ||
|
|
||
| # Only in scraped config | ||
| mock_litellm_providers = {} | ||
| mock_scraped_providers = {"test_scraped_only": {"api_base": "https://test.com"}} | ||
|
|
||
| with patch("rotator_library.provider_config.SCRAPED_PROVIDERS", mock_scraped_providers): | ||
| with patch("rotator_library.provider_config.LITELLM_PROVIDERS", mock_litellm_providers): | ||
| config = get_full_provider_config("test_scraped_only") | ||
| assert config == {"api_base": "https://test.com", "category": "other"} |
There was a problem hiding this comment.
This test function covers two distinct scenarios. Using @pytest.mark.parametrize would make the test more concise, readable, and ensure that each case is executed independently.
| def test_get_full_provider_config_partial_data(): | |
| """Test get_full_provider_config when provider is only in scraped or only in UI config.""" | |
| # Only in UI config | |
| mock_litellm_providers = {"test_ui_only": {"category": "ui_only_category"}} | |
| mock_scraped_providers = {} | |
| with patch("rotator_library.provider_config.SCRAPED_PROVIDERS", mock_scraped_providers): | |
| with patch("rotator_library.provider_config.LITELLM_PROVIDERS", mock_litellm_providers): | |
| config = get_full_provider_config("test_ui_only") | |
| assert config == {"category": "ui_only_category"} | |
| # Only in scraped config | |
| mock_litellm_providers = {} | |
| mock_scraped_providers = {"test_scraped_only": {"api_base": "https://test.com"}} | |
| with patch("rotator_library.provider_config.SCRAPED_PROVIDERS", mock_scraped_providers): | |
| with patch("rotator_library.provider_config.LITELLM_PROVIDERS", mock_litellm_providers): | |
| config = get_full_provider_config("test_scraped_only") | |
| assert config == {"api_base": "https://test.com", "category": "other"} | |
| @pytest.mark.parametrize("provider_key, mock_scraped, mock_ui, expected", [ | |
| ( | |
| "test_ui_only", | |
| {}, | |
| {"test_ui_only": {"category": "ui_only_category"}}, | |
| {"category": "ui_only_category"} | |
| ), | |
| ( | |
| "test_scraped_only", | |
| {"test_scraped_only": {"api_base": "https://test.com"}}, | |
| {}, | |
| {"api_base": "https://test.com", "category": "other"} | |
| ), | |
| ]) | |
| def test_get_full_provider_config_partial_data(provider_key, mock_scraped, mock_ui, expected): | |
| """Test get_full_provider_config when provider is only in scraped or only in UI config.""" | |
| with patch("rotator_library.provider_config.SCRAPED_PROVIDERS", mock_scraped): | |
| with patch("rotator_library.provider_config.LITELLM_PROVIDERS", mock_ui): | |
| assert get_full_provider_config(provider_key) == expected |
|
[Gemini-CLI Review Skill] @jules Reviewing this PR against the checklist and Gemini Code Assist feedback:
|
I have implemented the requested changes: I added a test case to explicitly verify the merge priority when both |
Code Review SummaryStatus: No Issues Found | Recommendation: Merge Overview
Changes Reviewed
AssessmentThe code changes are correct:
Tests are comprehensive and test the actual changed behavior. Files Reviewed (2 files)
Reviewed by minimax-m2.7 · 124,269 tokens |
|
[Gemini-CLI Review Skill] Consolidated into the linear commit stack on dev. |
Acknowledged. |
🎯 What: The testing gap addressed is the missing unit tests for
get_full_provider_configandget_provider_ui_configfunctions insrc/rotator_library/provider_config.py.📊 Coverage: Test coverage is now complete for both known and unknown providers, verifying data merging and fallbacks.
✨ Result: Enhanced test coverage provides confidence against regressions and validates correct dictionary fallback behaviour.
PR created automatically by Jules for task 16947276259564390506 started by @b3nw