## Summary
- Refactors the admin interface into focused views and simplifies the
header (removes noisy status labels; hides managed-source labels where
appropriate).
- Fixes Claude runtime settings handling, reduces Z.ai base URL leakage
in the admin UI, and streamlines API startup logging.
- Updates configuration and catalog behavior (including `.env.example` /
README), and expands automated tests around admin, app lifespan, and
config/registry behavior.
## Test plan
- [ ] `uv run ruff format`, `uv run ruff check`, `uv run ty check`, `uv
run pytest`
- [ ] Smoke the admin UI: navigation between views, settings save/load,
no sensitive URL leakage in the UI
- [ ] Confirm API startup logs are readable and not overly verbose in
normal operation
## 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
- Default LOG_FILE to logs/server.log in settings and admin config
- Create log parent directories in configure_logging
- Gitignore /logs/, /server.*.log; keep server.log for root override
- Add test for nested log path mkdir
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.
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.
Safal Karki