## 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
- 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
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
This PR improves and tightens the Pydantic validation for `NimSettings`
in `config/nim.py`, ensuring that all field inputs are robustly coerced,
reject bad values early, and provide clear error messages for
misconfigurations.
### What was changed
- Added type coercion and safety to fields allowing environment/CLI
config values.
- Provided default values on empty strings and None where safe.
- Added detailed value checks for float fields and integer fields.
- Improved docstrings for field clarity.
---
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.
## Summary
Added NVIDIA NIM as a second transcription option ( alongside local
Whisper). This lets you transcribe voice notes using NVIDIA's cloud API
instead of running Whisper locally.
## What changed
- **Transcription**: Now supports the two backends
- Local Whisper: Free, runs on your GPU/CPU (existing)
- NVIDIA NIM: Cloud API via Riva gRPC (new)
- **Supported models**: 8 NVIDIA NIM models added (Parakeet variants for
different languages, Whisper Large V3)
---------
Co-authored-by: Alishahryar1 <alishahryar2@gmail.com>
- `max_concurrency` is now always an `int` (default 5) — `None`/unlimited
is no longer a valid state; omitting the env var uses the default
- `GlobalRateLimiter`: semaphore is always created; `concurrency_slot()`
no longer has None guards; log message always includes concurrency
- `ProviderConfig.max_concurrency`: `int = 5` (was `int | None = None`)
- `Settings.provider_max_concurrency`: `int = Field(default=5, ...)` —
setting env var to an invalid value (e.g. empty string) raises
- `.env.example`: uncommented `PROVIDER_MAX_CONCURRENCY=5`
- README: updated config table default from `—` to `5`
- Tests: removed `test_concurrency_slot_noop_when_not_configured`;
updated mock settings to use `5` instead of `None`
https://claude.ai/code/session_014mrF1WMNgmNjtPBuoQHsbg
The max_sessions cap in CLISessionManager was the only thing enforcing
a limit on concurrent CLI processes. Now that provider concurrency is
controlled at the streaming layer (PROVIDER_MAX_CONCURRENCY semaphore),
the CLI session pool cap is redundant and removed entirely.
Changes:
- cli/manager.py: remove max_sessions param, cap check, _cleanup_idle_sessions_unlocked, max_sessions from get_stats()
- config/settings.py: remove max_cli_sessions field
- api/app.py: remove max_sessions=settings.max_cli_sessions from CLISessionManager constructor
- messaging/handler.py: remove "Waiting for slot" status check; stats display no longer shows Max CLI
- .env.example: remove MAX_CLI_SESSIONS line
- tests/cli/test_cli.py: remove max_sessions args and assertion from manager tests
- tests/cli/test_cli_manager_edge_cases.py: remove two tests for cap/cleanup behavior
- tests/api/test_app_lifespan_and_errors.py: remove max_cli_sessions from all SimpleNamespace settings
- tests/config/test_config.py: remove max_cli_sessions isinstance assertion
- tests/conftest.py: remove max_sessions from mock stats
- tests/messaging/test_handler.py: merge slot/capacity tests into single new-conversation test; remove Max CLI assertion from stats test
- tests/messaging/test_handler_markdown_and_status_edges.py: remove "Waiting for slot" assertion; drop max_sessions from all stats mocks
https://claude.ai/code/session_014mrF1WMNgmNjtPBuoQHsbg
Adds max_concurrency cap to GlobalRateLimiter using asyncio.Semaphore.
A request now waits for a concurrency slot before the sliding window rate
limit check, so at most N streams are open to the provider simultaneously,
even when the rate window would allow more.
Changes:
- providers/rate_limit.py: max_concurrency param, _concurrency_sem, concurrency_slot() asynccontextmanager
- providers/openai_compat.py: pass max_concurrency to limiter; wrap execute_with_retry + stream iteration in concurrency_slot()
- providers/base.py: max_concurrency field on ProviderConfig
- config/settings.py: provider_max_concurrency setting (PROVIDER_MAX_CONCURRENCY env var, default None = unlimited)
- api/dependencies.py: pass provider_max_concurrency into all three provider ProviderConfig instantiations
- .env.example: document PROVIDER_MAX_CONCURRENCY (commented out)
- tests/providers/test_provider_rate_limit.py: 5 new tests covering concurrency limit enforcement, slot release on exception, noop when unconfigured
- tests/api/test_dependencies.py: add provider_max_concurrency=None to mock settings helper
https://claude.ai/code/session_014mrF1WMNgmNjtPBuoQHsbg
Safal Karki