Ali Khokhar ffa8237220 Refactor native Anthropic messages providers (#147) ...

## Summary
- add a shared `AnthropicMessagesProvider` for native Anthropic
`/messages` providers
- migrate OpenRouter, LM Studio, and llama.cpp onto the shared
transport/streaming base
- preserve provider-specific stream chunking, request headers, thinking
filtering, and error shapes

## Verification
- `uv run ruff format`
- `uv run ruff check`
- `uv run ty check`
- `uv run pytest` (902 passed)

2026-04-24 17:25:49 -07:00

..

test_anthropic_compat.py

Refactor native Anthropic messages providers (#147)

2026-04-24 17:25:49 -07:00

test_converter.py

Add local live smoke test suite (#148)

2026-04-23 19:06:09 -07:00

test_deepseek.py

Revert "Add per-model thinking toggles"

2026-04-24 00:26:15 -07:00

test_error_mapping.py

Improve deterministic error surfacing across stream and API

2026-03-01 01:32:52 -08:00

test_llamacpp.py

Refactor native Anthropic messages providers (#147)

2026-04-24 17:25:49 -07:00

test_lmstudio.py

Refactor native Anthropic messages providers (#147)

2026-04-24 17:25:49 -07:00

test_nvidia_nim_request.py

Fix: Exclude chat_template for Mistral tokenizers in NVIDIA NIM (#130) (#131)

2026-04-22 17:16:45 -07:00

test_nvidia_nim.py

Revert "Add per-model thinking toggles"

2026-04-24 00:26:15 -07:00

test_open_router.py

Refactor native Anthropic messages providers (#147)

2026-04-24 17:25:49 -07:00

test_parsers.py

new linter rules and fixes

2026-02-18 04:13:41 -08:00

test_provider_rate_limit.py

Make PROVIDER_MAX_CONCURRENCY required with default of 5

2026-02-19 14:39:42 +00:00

test_sse_builder.py

Major cleanup with GLM-5

2026-02-28 09:10:21 -08:00

test_streaming_errors.py

Revert "Add per-model thinking toggles"

2026-04-24 00:26:15 -07:00

test_subagent_interception.py

new linter rules and fixes

2026-02-18 04:13:41 -08:00