starred/anyllm-proxy
1
0
Fork 0
mirror of https://github.com/whit3rabbit/anyllm-proxy.git synced 2026-09-22 00:00:50 +00:00
Code Issues Packages Projects Releases Wiki Activity
423 Commits 14 Branches 21 Tags
codex/fix-vulnerability-causing-zero-cost-usage
Commit Graph
5 Commits
Author SHA1 Message Date
whit3rabbitandClaude Opus 4.6 486661e0a0 refactor: remove native Gemini API translation, use OpenAI-compatible endpoint 
Gemini's OpenAI-compatible endpoint (/openai) supports the same Chat
Completions format as the OpenAI backend, making the native Gemini
translation path redundant. This removes ~3400 lines of Gemini-specific
types, mapping, streaming, and client code, routing Gemini through the
existing OpenAI translation pipeline instead.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 06:34:03 -05:00
whit3rabbitandClaude Opus 4.6 9ed5be65c5 test: add error/edge case fixtures for OpenAI, Gemini, Anthropic (Phase 22) 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-22 13:04:35 -05:00
whit3rabbitandClaude Opus 4.6 76e9392656 Add native Gemini backend, library mode, and middleware (Phases 20d-20g, 21a-21c) 
Gemini native backend:
- Schema sanitizer strips unsupported JSON Schema keys for Gemini (20d)
- Anthropic-to-Gemini message mapping with role coercion and turn merging (20e)
- Streaming state machine for Gemini SSE and Vertex AI responses (20f)
- GeminiClient with retry/backoff, BackendClient enum dispatch (20g)
- Unified BackendError with per-backend error helpers
- Shared retry logic extracted to backend/mod.rs

Library mode (21a-21c):
- TranslationConfig with builder pattern, model mapping, lossy behavior control
- translate_request/translate_response convenience functions
- Public TranslateError enum, crate-level doc examples
- Axum middleware layer (AnthropicTranslationLayer) for embedding in existing services
- Feature-gated middleware deps (axum, reqwest, tokio)
- library_usage and middleware_integration test suites

Also: new Claude Code tool call fixtures, updated CLAUDE.md and TASKS.md.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-22 09:20:22 -05:00
whit3rabbitandClaude Opus 4.6 3b70d1c64e Add native Gemini API types (Phase 20c) 
Pure type definitions for Gemini generateContent API: request/response
structs, Content/Part union, tool declarations, error shapes, safety
settings, and citation metadata. 19 serde round-trip tests with golden
fixtures. No mapping logic or proxy changes.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-21 21:07:29 -05:00
whit3rabbitandClaude Opus 4.6 f2e3ed15f4 Initial commit: Anthropic-to-OpenAI API translation proxy 
Rust workspace with two crates:
- translator: pure, IO-free mapping between Anthropic Messages API and OpenAI Chat Completions
- proxy: axum HTTP server with auth, streaming SSE, retry/backoff, concurrency limits

169 tests passing (unit, golden fixture, integration).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-21 13:25:43 -05:00