Updates the requirements on
[httpx[socks]](https://github.com/encode/httpx) to permit the latest
version.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/encode/httpx/releases">httpx[socks]'s
releases</a>.</em></p>
<blockquote>
<h2>Version 0.28.1</h2>
<h2>0.28.1 (6th December, 2024)</h2>
<ul>
<li>Fix SSL case where <code>verify=False</code> together with client
side certificates.</li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/encode/httpx/blob/master/CHANGELOG.md">httpx[socks]'s
changelog</a>.</em></p>
<blockquote>
<h2>0.28.1 (6th December, 2024)</h2>
<ul>
<li>Fix SSL case where <code>verify=False</code> together with client
side certificates.</li>
</ul>
<h2>0.28.0 (28th November, 2024)</h2>
<p>Be aware that the default <em>JSON request bodies now use a more
compact representation</em>. This is generally considered a prefered
style, tho may require updates to test suites.</p>
<p>The 0.28 release includes a limited set of deprecations...</p>
<p><strong>Deprecations</strong>:</p>
<p>We are working towards a simplified SSL configuration API.</p>
<p><em>For users of the standard <code>verify=True</code> or
<code>verify=False</code> cases, or
<code>verify=<ssl_context></code> case this should require no
changes. The following cases have been deprecated...</em></p>
<ul>
<li>The <code>verify</code> argument as a string argument is now
deprecated and will raise warnings.</li>
<li>The <code>cert</code> argument is now deprecated and will raise
warnings.</li>
</ul>
<p>Our revised <a
href="https://github.com/encode/httpx/blob/master/docs/advanced/ssl.md">SSL
documentation</a> covers how to implement the same behaviour with a more
constrained API.</p>
<p><strong>The following changes are also included</strong>:</p>
<ul>
<li>The deprecated <code>proxies</code> argument has now been
removed.</li>
<li>The deprecated <code>app</code> argument has now been removed.</li>
<li>JSON request bodies use a compact representation. (<a
href="https://redirect.github.com/encode/httpx/issues/3363">#3363</a>)</li>
<li>Review URL percent escape sets, based on WHATWG spec. (<a
href="https://redirect.github.com/encode/httpx/issues/3371">#3371</a>,
<a
href="https://redirect.github.com/encode/httpx/issues/3373">#3373</a>)</li>
<li>Ensure <code>certifi</code> and <code>httpcore</code> are only
imported if required. (<a
href="https://redirect.github.com/encode/httpx/issues/3377">#3377</a>)</li>
<li>Treat <code>socks5h</code> as a valid proxy scheme. (<a
href="https://redirect.github.com/encode/httpx/issues/3178">#3178</a>)</li>
<li>Cleanup <code>Request()</code> method signature in line with
<code>client.request()</code> and <code>httpx.request()</code>. (<a
href="https://redirect.github.com/encode/httpx/issues/3378">#3378</a>)</li>
<li>Bugfix: When passing <code>params={}</code>, always strictly update
rather than merge with an existing querystring. (<a
href="https://redirect.github.com/encode/httpx/issues/3364">#3364</a>)</li>
</ul>
<h2>0.27.2 (27th August, 2024)</h2>
<h3>Fixed</h3>
<ul>
<li>Reintroduced supposedly-private <code>URLTypes</code> shortcut. (<a
href="https://redirect.github.com/encode/httpx/issues/2673">#2673</a>)</li>
</ul>
<h2>0.27.1 (27th August, 2024)</h2>
<h3>Added</h3>
<ul>
<li>Support for <code>zstd</code> content decoding using the python
<code>zstandard</code> package is added. Installable using
<code>httpx[zstd]</code>. (<a
href="https://redirect.github.com/encode/httpx/issues/3139">#3139</a>)</li>
</ul>
<h3>Fixed</h3>
<ul>
<li>Improved error messaging for <code>InvalidURL</code> exceptions. (<a
href="https://redirect.github.com/encode/httpx/issues/3250">#3250</a>)</li>
<li>Fix <code>app</code> type signature in <code>ASGITransport</code>.
(<a
href="https://redirect.github.com/encode/httpx/issues/3109">#3109</a>)</li>
</ul>
<h2>0.27.0 (21st February, 2024)</h2>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="26d48e0634"><code>26d48e0</code></a>
Version 0.28.1 (<a
href="https://redirect.github.com/encode/httpx/issues/3445">#3445</a>)</li>
<li><a
href="89599a9541"><code>89599a9</code></a>
Fix <code>verify=False</code>, <code>cert=...</code> case. (<a
href="https://redirect.github.com/encode/httpx/issues/3442">#3442</a>)</li>
<li><a
href="8ecb86f0d7"><code>8ecb86f</code></a>
Add test for request params behavior changes (<a
href="https://redirect.github.com/encode/httpx/issues/3364">#3364</a>)
(<a
href="https://redirect.github.com/encode/httpx/issues/3440">#3440</a>)</li>
<li><a
href="0cb7e5a2e7"><code>0cb7e5a</code></a>
Bump the python-packages group with 11 updates (<a
href="https://redirect.github.com/encode/httpx/issues/3434">#3434</a>)</li>
<li><a
href="15e21e9ea3"><code>15e21e9</code></a>
Updating deprecated docstring Client() class (<a
href="https://redirect.github.com/encode/httpx/issues/3426">#3426</a>)</li>
<li><a
href="80960fa319"><code>80960fa</code></a>
Version 0.28.0. (<a
href="https://redirect.github.com/encode/httpx/issues/3419">#3419</a>)</li>
<li><a
href="a33c87852b"><code>a33c878</code></a>
Fix <code>extensions</code> type annotation. (<a
href="https://redirect.github.com/encode/httpx/issues/3380">#3380</a>)</li>
<li><a
href="ce7e14da27"><code>ce7e14d</code></a>
Error on verify as str. (<a
href="https://redirect.github.com/encode/httpx/issues/3418">#3418</a>)</li>
<li><a
href="47f4a96ffa"><code>47f4a96</code></a>
Handle empty zstd responses (<a
href="https://redirect.github.com/encode/httpx/issues/3412">#3412</a>)</li>
<li><a
href="189fc4bcbe"><code>189fc4b</code></a>
Update CHANGELOG.md, fix typo(s) (<a
href="https://redirect.github.com/encode/httpx/issues/3406">#3406</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/encode/httpx/compare/0.25.0...0.28.1">compare
view</a></li>
</ul>
</details>
<br />
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
## Summary
Adds a Dependabot configuration to automate weekly update PRs for:
- `uv`-managed Python dependencies
- GitHub Actions used in CI workflows
## Why
This repository already relies on pinned dependency state via `uv.lock`
and pinned GitHub Action revisions in CI. Adding Dependabot helps keep
both current with small, reviewable update PRs instead of larger manual
catch-up updates.
## What this changes
- Adds `.github/dependabot.yml`
- Configures weekly version update checks for the repo root
- Groups minor and patch dependency updates to reduce PR noise
- Enables automatic update PRs for GitHub Actions references in
workflows
## Used `uv` instead of `pip`
This project uses `uv` directly (`uv.lock`, `uv run`, and repo
instructions based on `uv`), so configuring Dependabot with the `uv`
ecosystem matches the repository’s actual package management workflow
more closely than a generic `pip` entry.
## Risk
Low. This is a configuration only change and does not affect application
runtime behavior .
## 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
