Route these providers through POST /messages with vendor headers and bases (including Kimi model list on OpenAI /v1/models). Remove Z.ai from OpenAI-chat server-tool rejection; extend tests and README.
## Summary
Adds support for the **OpenCode Go** subscription gateway at
`opencode.ai/zen/go/v1`, as requested in #504.
OpenCode Go exposes the same OpenAI-compatible Chat Completions API as
OpenCode Zen, so the implementation reuses `OpenCodeProvider` with a
configurable `provider_name` parameter — avoiding code duplication.
### Changes
- **Provider**: `OpenCodeProvider` now accepts `provider_name` (defaults
to `"OPENCODE"` for backward compatibility)
- **Catalog**: New `opencode_go` descriptor with correct base URL,
credential, and capabilities
- **Registry**: `_create_opencode_go` factory that passes
`provider_name="OPENCODE_GO"`
- **Settings**: `opencode_go_api_key` and `opencode_go_proxy` fields
- **Admin UI**: OpenCode Go API key, proxy, and smoke model config
fields
- **API services**: `opencode_go` added to OpenAI Chat Completions
upstream IDs
- **Smoke config**: Default smoke model `opencode_go/gpt-5.3-codex`
- **Tests**: New test for base URL, provider name, and API key; existing
tests updated
## Test plan
- [x] `test_opencode_go_provider_config_uses_correct_base_url_and_name`
— passes
- [x] `test_create_provider_instantiates_each_builtin` — covers
opencode_go
- [x]
`test_provider_and_platform_registries_include_advertised_builtins` —
covers opencode_go
- [x] `uv run ruff format`, `ruff check`, `ty check`, `pytest` — pass
locally on Python 3.14
Closes#504.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: Alishahryar1 <alishahryar2@gmail.com>
## Summary
- split the admin UI into Providers, Model Config, and Messaging views
- remove generated env, diagnostics, smoke, managed-label, and fixed
cloud/runtime settings from the visible admin UX
- make Z.ai base URL, Claude workspace, and Claude CLI binary fixed
app-level behavior instead of managed env fields
## Verification
- uv run ruff format
- uv run ruff check
- uv run ty check
- uv run pytest
Generalize retryable_upstream_status to HTTP 500-599 plus 429.
Improve execute_with_retry log label with actual status.
Preserve OpenAI InternalServerError 5xx in map_error after overload check.
Unify native stream send: log via _raise_for_status then optional async aclose.
Add _maybe_await_aclose for httpx doubles in tests.
Rename openai compat retry tests to 5xx; parameterize native/limiter/mapping tests.
Extend execute_with_retry with retryable_upstream_status for 429/503
shared backoff, reactive block, and TRACE provider.retry.scheduled.
Map InternalServerError(503) to APIError with preserved status.
Native transport closes-and-raises on 503 like 429 for clean retries.
Add NIM/OpenAI-compat and rate limiter tests.
## 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.
- 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.
## 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>
## 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.
Alishahryar1