## What
Fixes the 422 error returned by the proxy when Claude Code v2.1.128+
sends PDF context as Anthropic `document` blocks, plus two related
DeepSeek-only issues uncovered while debugging.
Closes#357.
## Why
Claude Code now attaches PDFs/files as `document` content blocks. The
`Message.content` union didn't include that variant, so every follow-up
turn after a PDF read returned `422 Unprocessable Content` from the
proxy itself (before the request ever reached DeepSeek).
## Changes
- `api/models/anthropic.py`: new `ContentBlockDocument`, added to
`Message.content` union.
- `providers/deepseek/request.py`:
- `_strip_unsupported_attachment_blocks` — silently drops
`image`/`document` blocks for DeepSeek.
- `_serialize_tool_result_content` + `_normalize_tool_result_content` —
coerces `tool_result.content` to a string per DeepSeek's API contract.
- Hooked into `build_request_body` (strip before validation, normalize
before send).
- `tests/providers/test_deepseek.py`: +4 tests, 1 legacy test updated.
## Verification
- `uv run ruff format` ✅
- `uv run ruff check` ✅
- `uv run ty check` ✅
- `uv run pytest` ✅ (1194 passed)
- Manual: `claude-deepseek` against a PDF no longer 422s.
## Scope / non-goals
- No README change (per CONTRIBUTING).
- Image/document blocks for DeepSeek are stripped, not converted to text
— Claude Code already ships the extracted text in the paired
tool_result.
- No changes to other providers.
---------
Co-authored-by: Alishahryar1 <alishahryar2@gmail.com>
- Only use provider completion_tokens when it is an int; otherwise estimate
- Coerce message_start/message_delta usage fields to safe integers in SSEBuilder
- Add regression tests for null upstream completion_tokens and builder edge cases
Claude Code could crash (e.g. undefined access on usage) when NIM/GLM or
similar sent usage with null token fields in streamed message_delta.
Pass parent_session_id into get_or_create_session so reply nodes align with
the fork/resume path instead of always allocating a fresh pending session.
Add unit coverage and update integration expectations.
- OpenAI-compat: emit minimal text block when only reasoning_content streams
(e.g. NIM) so clients get a text segment.
- Provider prereq: pass if text or thinking content is non-empty after strip.
- Add unit test for reasoning-only stream placeholder text.
- Make AnthropicToOpenAIConverter stateful: assistant text after tool_use is
deferred until matching tool_result, then replayed as a follow-up assistant
turn.
- After native streamed tool_use, emit top-level SSE error on transport
failure instead of assistant text_delta (avoids bad transcript shape).
- Add NIM preflight, streaming, converter, and product smoke regressions.
- Point DeepSeek at api.deepseek.com/anthropic with x-api-key headers
- Native request builder, DeepSeek-specific thinking/block sanitization
- Drop deepseek from OpenAI-chat server-tool preflight; update tests and docs
- Default smoke model deepseek-v4-pro; re-export dump_raw_messages_request
- Add ReasoningReplayMode and top-level reasoning replay in OpenAI conversion
- DeepSeek/NIM request bodies use reasoning_content when thinking is enabled
- NIM retries without reasoning_content on 400 from upstream
- Per-provider smoke models (FCC_SMOKE_MODEL_*) independent of MODEL mapping
- Fix smoke model override parsing for owner/model names with slashes
- Live smoke: reasoning tool continuation uses synthetic thinking+tool history
- Tests and docs updated
Consolidates the incremental refactor work into a single change set: modular web tools (api/web_tools), native Anthropic request building and SSE block policy, OpenAI conversion and error handling, provider transports and rate limiting, messaging handler and tree queue, safe logging, smoke tests, and broad test coverage.
Expand is_title_generation_request to match sentence-case/JSON title prompts
in addition to legacy new-conversation-topic copy. Add unit test for the
current session-title system text shape.
- Updated DEFAULT_TARGETS in config.py to include new targets: clients, llamacpp, and lmstudio, while removing contract and optimizations.
- Introduced TARGET_ALIASES for better target management.
- Added TARGET_REQUIRED_ENV to specify environment variables needed for each target.
- Enhanced SmokeOutcome in report.py to include classification of outcomes for better reporting.
- Implemented classify_outcome function to categorize smoke test results.
- Added new test for stop endpoint in test_api_live.py to ensure proper error handling.
- Updated test_auth_live.py to enforce auth token requirements and utilize environment files.
- Changed target from vscode to clients in test_client_shapes_live.py.
- Removed obsolete test_feature_manifest.py and test_stream_contracts.py files.
- Added new skip helpers in skips.py to manage upstream unavailability scenarios.
- Created new tests for local provider endpoints in test_local_provider_endpoints_live.py.
- Added comprehensive feature inventory tests in tests/contracts/test_feature_manifest.py.
- Implemented stream contract tests in tests/contracts/test_stream_contracts.py.
## Summary
- add an opt-in local `smoke/` pytest suite for API, auth, providers,
CLI, IDE-shaped requests, messaging, voice, tools, and thinking stream
contracts
- keep smoke tests out of normal CI collection with `testpaths =
["tests"]`
- write sanitized smoke artifacts under `.smoke-results/`
## Verification
- `uv run ruff format`
- `uv run ruff check`
- `uv run ty check`
- `uv run ty check smoke`
- `FCC_LIVE_SMOKE=1 FCC_SMOKE_TARGETS=all FCC_SMOKE_RUN_VOICE=1 uv run
pytest smoke -n 0 -m live -s --tb=short` -> 17 passed, 9 skipped
- `uv run pytest` -> 904 passed
## Notes
- Skipped live checks require local credentials/tools/services, such as
provider models, Telegram/Discord targets, voice backend, or Claude CLI.
- `claude-pick` smoke was intentionally removed.
Fixes#130. This PR updates the NVIDIA NIM provider to omit
\chat_template_kwargs\ and \chat_template\ when using a Mistral
tokenizer model. This resolves the 400 Bad Request error returned by the
API.
Co-authored-by: Alishahryar1 <alishahryar2@gmail.com>
Add proxy support for providers based on
[doc](https://www.python-httpx.org/advanced/proxies/):
- Add per-provider proxy support (HTTP and SOCKS5) for all 4 providers:
nvidia_nim, open_router, lmstudio, llamacpp
- Each provider gets its own env var (NVIDIA_NIM_PROXY,
OPENROUTER_PROXY, LMSTUDIO_PROXY, LLAMACPP_PROXY) for independent proxy
configuration
---------
Co-authored-by: Alishahryar1 <alishahryar2@gmail.com>
## Summary
* add native DeepSeek provider support via the shared OpenAI-compatible
provider base
* allow `deepseek/...` model prefixes in config validation
* add `DEEPSEEK_API_KEY` and `DEEPSEEK_BASE_URL` settings
* add DeepSeek entries to `.env.example` and `config/env.example`
* implement `DeepSeekProvider` and register it in provider dependencies
* add a DeepSeek request builder with DeepSeek-specific thinking payload
handling
* preserve Anthropic thinking blocks as `reasoning_content` for
DeepSeek-compatible continuation flows
* update `claude-pick` to discover DeepSeek models from the DeepSeek API
* document DeepSeek usage in `README.md`
* add tests for config validation, provider dependency wiring, request
building, and streaming behavior
## Motivation
DeepSeek exposes an OpenAI-compatible API and can be used directly
without routing through OpenRouter. This lets users spend their existing
DeepSeek balance through the proxy while keeping the same Claude Code
workflow and per-model provider mapping.
## Example
```dotenv
DEEPSEEK_API_KEY="sk-..."
DEEPSEEK_BASE_URL="https://api.deepseek.com"
MODEL_OPUS="deepseek/deepseek-reasoner"
MODEL_SONNET="deepseek/deepseek-chat"
MODEL_HAIKU="deepseek/deepseek-chat"
MODEL="deepseek/deepseek-chat"
---------
Co-authored-by: Alishahryar1 <alishahryar2@gmail.com>
Mistral models reject chat_template_kwargs, causing 400 errors. Make
thinking params (chat_template_kwargs, reasoning_budget) opt-in via
NIM_ENABLE_THINKING env var (default false) so only models that need it
(kimi, nemotron) receive them.
Replace dropped params (thinking, reasoning_split, include_reasoning,
return_tokens_as_token_ids, reasoning_effort) with the new API format:
chat_template_kwargs.enable_thinking=True and reasoning_budget=max_tokens.
- Rewrites LMStudioProvider to inherit from BaseProvider
- Passes requests natively to /v1/messages using httpx instead of AsyncOpenAI
- Auto-translates internal ThinkingConfig to Anthropic schema
- Updates .env.example with model routing instructions
- Adjusts test suite for new native integration
Leung Ka Chun