deps: bump ruff from 0.15.22 to 0.16.2 in the pip-minor-patch group across 1 directory (#2962)

Bumps the pip-minor-patch group with 1 update in the / directory: [ruff](https://github.com/astral-sh/ruff). Updates `ruff` from 0.15.22 to 0.16.2 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/astral-sh/ruff/releases">ruff's releases</a>.</em></p> <blockquote> <h2>0.16.2</h2> <h2>Release Notes</h2> <p>Released on 2026-08-06.</p> <h3>Bug fixes</h3> <ul> <li>[<code>flake8-pyi</code>] Avoid false positives on <code>singledispatch</code> functions (<code>PYI041</code>) (<a href="https://redirect.github.com/astral-sh/ruff/pull/27335">#27335</a>)</li> </ul> <h3>Server</h3> <ul> <li>Register formatting capabilities dynamically to exclude TOML files (<a href="https://redirect.github.com/astral-sh/ruff/pull/27332">#27332</a>)</li> </ul> <h3>Contributors</h3> <ul> <li><a href="https://github.com/MeGaGiGaGon"><code>@MeGaGiGaGon</code></a></li> <li><a href="https://github.com/charliermarsh"><code>@charliermarsh</code></a></li> <li><a href="https://github.com/epage"><code>@epage</code></a></li> <li><a href="https://github.com/sharkdp"><code>@sharkdp</code></a></li> <li><a href="https://github.com/ntBre"><code>@ntBre</code></a></li> </ul> <h2>Install ruff 0.16.2</h2> <h3>Install prebuilt binaries via shell script</h3> <pre lang="sh"><code>curl --proto '=https' --tlsv1.2 -LsSf https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-installer.sh | sh </code></pre> <h3>Install prebuilt binaries via powershell script</h3> <pre lang="sh"><code>powershell -ExecutionPolicy Bypass -c "irm https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-installer.ps1 | iex" </code></pre> <h2>Download ruff 0.16.2</h2> <table> <thead> <tr> <th>File</th> <th>Platform</th> <th>Checksum</th> </tr> </thead> <tbody> <tr> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-aarch64-apple-darwin.tar.gz">ruff-aarch64-apple-darwin.tar.gz</a></td> <td>Apple Silicon macOS</td> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-aarch64-apple-darwin.tar.gz.sha256">checksum</a></td> </tr> <tr> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-x86_64-apple-darwin.tar.gz">ruff-x86_64-apple-darwin.tar.gz</a></td> <td>Intel macOS</td> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-x86_64-apple-darwin.tar.gz.sha256">checksum</a></td> </tr> <tr> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-aarch64-pc-windows-msvc.zip">ruff-aarch64-pc-windows-msvc.zip</a></td> <td>ARM64 Windows</td> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-aarch64-pc-windows-msvc.zip.sha256">checksum</a></td> </tr> <tr> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-i686-pc-windows-msvc.zip">ruff-i686-pc-windows-msvc.zip</a></td> <td>x86 Windows</td> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-i686-pc-windows-msvc.zip.sha256">checksum</a></td> </tr> <tr> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-x86_64-pc-windows-msvc.zip">ruff-x86_64-pc-windows-msvc.zip</a></td> <td>x64 Windows</td> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-x86_64-pc-windows-msvc.zip.sha256">checksum</a></td> </tr> <tr> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-aarch64-unknown-linux-gnu.tar.gz">ruff-aarch64-unknown-linux-gnu.tar.gz</a></td> <td>ARM64 Linux</td> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-aarch64-unknown-linux-gnu.tar.gz.sha256">checksum</a></td> </tr> <tr> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-i686-unknown-linux-gnu.tar.gz">ruff-i686-unknown-linux-gnu.tar.gz</a></td> <td>x86 Linux</td> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-i686-unknown-linux-gnu.tar.gz.sha256">checksum</a></td> </tr> <tr> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-powerpc64-unknown-linux-gnu.tar.gz">ruff-powerpc64-unknown-linux-gnu.tar.gz</a></td> <td>PPC64 Linux</td> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-powerpc64-unknown-linux-gnu.tar.gz.sha256">checksum</a></td> </tr> <tr> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-powerpc64le-unknown-linux-gnu.tar.gz">ruff-powerpc64le-unknown-linux-gnu.tar.gz</a></td> <td>PPC64LE Linux</td> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-powerpc64le-unknown-linux-gnu.tar.gz.sha256">checksum</a></td> </tr> <tr> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-riscv64gc-unknown-linux-gnu.tar.gz">ruff-riscv64gc-unknown-linux-gnu.tar.gz</a></td> <td>RISCV Linux</td> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-riscv64gc-unknown-linux-gnu.tar.gz.sha256">checksum</a></td> </tr> <tr> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-s390x-unknown-linux-gnu.tar.gz">ruff-s390x-unknown-linux-gnu.tar.gz</a></td> <td>S390x Linux</td> <td><a href="https://releases.astral.sh/github/ruff/releases/download/0.16.2/ruff-s390x-unknown-linux-gnu.tar.gz.sha256">checksum</a></td> </tr> </tbody> </table>  </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/astral-sh/ruff/blob/main/CHANGELOG.md">ruff's changelog</a>.</em></p> <blockquote> <h2>0.16.2</h2> <p>Released on 2026-08-06.</p> <h3>Bug fixes</h3> <ul> <li>[<code>flake8-pyi</code>] Avoid false positives on <code>singledispatch</code> functions (<code>PYI041</code>) (<a href="https://redirect.github.com/astral-sh/ruff/pull/27335">#27335</a>)</li> </ul> <h3>Server</h3> <ul> <li>Register formatting capabilities dynamically to exclude TOML files (<a href="https://redirect.github.com/astral-sh/ruff/pull/27332">#27332</a>)</li> </ul> <h3>Contributors</h3> <ul> <li><a href="https://github.com/MeGaGiGaGon"><code>@MeGaGiGaGon</code></a></li> <li><a href="https://github.com/charliermarsh"><code>@charliermarsh</code></a></li> <li><a href="https://github.com/epage"><code>@epage</code></a></li> <li><a href="https://github.com/sharkdp"><code>@sharkdp</code></a></li> <li><a href="https://github.com/ntBre"><code>@ntBre</code></a></li> </ul> <h2>0.16.1</h2> <p>Released on 2026-07-30.</p> <h3>Preview features</h3> <ul> <li>Add an option to opt out of human-readable names (<a href="https://redirect.github.com/astral-sh/ruff/pull/27160">#27160</a>)</li> <li>[<code>flake8-pytest-style</code>] Make fixes safe by default and unsafe only when comments are present (<code>PT018</code>) (<a href="https://redirect.github.com/astral-sh/ruff/pull/27201">#27201</a>)</li> <li>[<code>pyupgrade</code>] Skip fix when a defaulted <code>TypeVar</code> precedes a non-defaulted one (<code>UP040</code>, <code>UP046</code>, <code>UP047</code>) (<a href="https://redirect.github.com/astral-sh/ruff/pull/27133">#27133</a>)</li> <li>[<code>ruff</code>] Fix false positive with unpacked arguments (<code>RUF065</code>) (<a href="https://redirect.github.com/astral-sh/ruff/pull/26959">#26959</a>)</li> </ul> <h3>Bug fixes</h3> <ul> <li>Bump <code>gen-lsp-types</code> to gracefully handle unknown enumeration values in LSP messages (<a href="https://redirect.github.com/astral-sh/ruff/pull/27230">#27230</a>)</li> <li>[<code>flake8-bugbear</code>] Mark <code>range</code> as immutable (<code>B008</code>) (<a href="https://redirect.github.com/astral-sh/ruff/pull/27247">#27247</a>)</li> <li>[<code>flake8-comprehensions</code>] NFKC-normalize keyword names in <code>C408</code> fix (<a href="https://redirect.github.com/astral-sh/ruff/pull/26813">#26813</a>)</li> <li>[<code>flake8-return</code>] Fix false positive when variable is read in <code>finally</code> clause (<code>RET504</code>) (<a href="https://redirect.github.com/astral-sh/ruff/pull/25441">#25441</a>)</li> <li>[<code>pydocstyle</code>] Skip section detection inside RST directive bodies (<code>D214</code>, <code>D405</code>, <code>D413</code>) (<a href="https://redirect.github.com/astral-sh/ruff/pull/23635">#23635</a>)</li> <li>[<code>refurb</code>] Parenthesize <code>yield</code> arguments in the <code>FURB192</code> fix (<a href="https://redirect.github.com/astral-sh/ruff/pull/27192">#27192</a>)</li> </ul> <h3>Rule changes</h3> <ul> <li>[<code>flake8-pytest-style</code>] Mark <code>PT022</code> fixes as unsafe (<a href="https://redirect.github.com/astral-sh/ruff/pull/26440">#26440</a>)</li> <li>[<code>refurb</code>] Mark fixes that remove unknown separators as unsafe (<code>FURB105</code>) (<a href="https://redirect.github.com/astral-sh/ruff/pull/27200">#27200</a>)</li> </ul> <h3>Server</h3> <ul> <li>Fix indexing of excluded nested Ruff workspaces (<a href="https://redirect.github.com/astral-sh/ruff/pull/27303">#27303</a>)</li> <li>Lint TOML files in the LSP (<a href="https://redirect.github.com/astral-sh/ruff/pull/26862">#26862</a>)</li> </ul>  </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="5b48a04097"><code>5b48a04</code></a> Bump 0.16.2 (<a href="https://redirect.github.com/astral-sh/ruff/issues/27555">#27555</a>)</li> <li><a href="1b9e5fc483"><code>1b9e5fc</code></a> Update Swatinem/rust-cache action to v2.9.2 (<a href="https://redirect.github.com/astral-sh/ruff/issues/27568">#27568</a>)</li> <li><a href="c4e86fc039"><code>c4e86fc</code></a> [ty] Add helper extension methods for half-range and equality constraints (<a href="https://redirect.github.com/astral-sh/ruff/issues/2">#2</a>...</li> <li><a href="17a00de2e2"><code>17a00de</code></a> [ty] Reuse primer commands in memory reports (<a href="https://redirect.github.com/astral-sh/ruff/issues/27553">#27553</a>)</li> <li><a href="6ea296b969"><code>6ea296b</code></a> [ty] Normalize type labels in structured docstrings (<a href="https://redirect.github.com/astral-sh/ruff/issues/26923">#26923</a>)</li> <li><a href="2fc445f005"><code>2fc445f</code></a> [ty] Diagnose invalid <strong>getattr</strong> calls (<a href="https://redirect.github.com/astral-sh/ruff/issues/27502">#27502</a>)</li> <li><a href="22c7823c4e"><code>22c7823</code></a> [ty] Enable (but downrank) auto-import completion suggestions from stub-only ...</li> <li><a href="05160d507f"><code>05160d5</code></a> [ty] Diagnose invalid descriptor <code>__get__</code> calls (<a href="https://redirect.github.com/astral-sh/ruff/issues/27400">#27400</a>)</li> <li><a href="baea3d0dce"><code>baea3d0</code></a> [ty] Expose strict analysis options in the playground (<a href="https://redirect.github.com/astral-sh/ruff/issues/27543">#27543</a>)</li> <li><a href="c88946ebeb"><code>c88946e</code></a> [ty] Bump ecosystem-analyzer for strict project settings (<a href="https://redirect.github.com/astral-sh/ruff/issues/27542">#27542</a>)</li> <li>Additional commits viewable in <a href="https://github.com/astral-sh/ruff/compare/0.15.22...0.16.2">compare view</a></li> </ul> </details> <br /> --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
2026-08-27 14:17:10 -04:00 · 2026-08-14 16:38:08 -05:00 · 2026-08-14 16:38:08 -05:00 · ff17961cd7
commit ff17961cd7
parent bbe901319d
24 changed files with 526 additions and 519 deletions
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@ -27,7 +27,7 @@ repos:
        # unconditionally, so installing hooks is not required for enforcement.
        args: [--assume-in-merge]
  - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.15.22
+    rev: v0.16.2
    hooks:
      - id: ruff
        args: [--fix]
--- a/headroom/testing/README.md
+++ b/headroom/testing/README.md
@ -33,7 +33,11 @@ assert report.passed
 suite = (
    Headroom.Suite("phase-1")
    .Add(Headroom.WithOpenAI().named("openai-cache").WithCompression(mode="cache"))
-    .Add(Headroom.WithBedrock(region="us-east-1").named("bedrock-token").WithCompression(mode="token"))
+    .Add(
        Headroom.WithBedrock(region="us-east-1")
        .named("bedrock-token")
        .WithCompression(mode="token")
    )
 )
 suite.write_manifest_bundle("headroom-testing-bundle.json", provider="openai", port_start=19000)
--- a/pyproject.toml
+++ b/pyproject.toml
@ -277,7 +277,7 @@ dev = [
    "pytest>=7.0.0",
    "pytest-cov>=4.0.0",
    "pytest-asyncio>=0.21.0",
-    "ruff==0.15.22",
+    "ruff==0.16.2",
    "mypy>=1.0.0",
    "pre-commit>=3.0.0",
    "openai>=1.0.0",
--- a/uv.lock
+++ b/uv.lock
@ -280,12 +280,12 @@ name = "any-llm-sdk"
 version = "1.12.1"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "httpx" },
+    { name = "httpx", marker = "python_full_version >= '3.11'" },
-    { name = "openai" },
+    { name = "openai", marker = "python_full_version >= '3.11'" },
-    { name = "openresponses-types" },
+    { name = "openresponses-types", marker = "python_full_version >= '3.11'" },
-    { name = "pydantic" },
+    { name = "pydantic", marker = "python_full_version >= '3.11'" },
-    { name = "rich" },
+    { name = "rich", marker = "python_full_version >= '3.11'" },
-    { name = "typing-extensions" },
+    { name = "typing-extensions", marker = "python_full_version >= '3.11'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/21/d5/21ef27d031b72f0054ba0015a66cc1f10cda9410e4a3acb6e795d848ad0d/any_llm_sdk-1.12.1.tar.gz", hash = "sha256:76e043fcaa56fccfb375a908511869dc7dbf393dd97a82d06bb764d8201724e8", size = 152078, upload-time = "2026-03-18T13:13:01.735Z" }
 wheels = [
@ -811,7 +811,7 @@ name = "coloredlogs"
 version = "15.0.1"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "humanfriendly" },
+    { name = "humanfriendly", marker = "python_full_version < '3.11'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/cc/c7/eed8f27100517e8c0e6b923d5f0845d0cb99763da6fdee00478f91db7325/coloredlogs-15.0.1.tar.gz", hash = "sha256:7c991aa71a4577af2f82600d8f8f3a89f936baeaf9b50a9c197da014e5bf16b0", size = 278520, upload-time = "2021-06-11T10:22:45.202Z" }
 wheels = [
@ -823,7 +823,7 @@ name = "colorlog"
 version = "6.10.1"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "colorama", marker = "python_full_version >= '3.13' and sys_platform == 'win32'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/a2/61/f083b5ac52e505dfc1c624eafbf8c7589a0d7f32daa398d2e7590efa5fda/colorlog-6.10.1.tar.gz", hash = "sha256:eb4ae5cb65fe7fec7773c2306061a8e63e02efc2c72eba9d27b0fa23c94f1321", size = 17162, upload-time = "2025-10-16T16:14:11.978Z" }
 wheels = [
@ -1045,7 +1045,7 @@ name = "cuda-bindings"
 version = "13.3.1"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "cuda-pathfinder" },
+    { name = "cuda-pathfinder", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/a9/21/8464d133752951c154feafb3b65c297e7d80f301183d220bec4c830f1441/cuda_bindings-13.3.1-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:120fcc53d57903df529c3486962c56528cba5b7d6c57c99537320ed9922c8b86", size = 6073403, upload-time = "2026-05-29T23:11:36.22Z" },
@ -1080,43 +1080,43 @@ wheels = [
 [package.optional-dependencies]
 cublas = [
-    { name = "nvidia-cublas", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-cublas", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
-    { name = "nvidia-cuda-nvrtc", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-cuda-nvrtc", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
 ]
 cudart = [
-    { name = "nvidia-cuda-runtime", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-cuda-runtime", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
 ]
 cufft = [
-    { name = "nvidia-cufft", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-cufft", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
-    { name = "nvidia-nvjitlink", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
 ]
 cufile = [
-    { name = "nvidia-cufile", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-cufile", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
 ]
 cupti = [
-    { name = "nvidia-cuda-cupti", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-cuda-cupti", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
 ]
 curand = [
-    { name = "nvidia-curand", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-curand", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
 ]
 cusolver = [
-    { name = "nvidia-cublas", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-cublas", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
-    { name = "nvidia-cusolver", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-cusolver", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
-    { name = "nvidia-cusparse", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-cusparse", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
-    { name = "nvidia-nvjitlink", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
 ]
 cusparse = [
-    { name = "nvidia-cusparse", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-cusparse", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
-    { name = "nvidia-nvjitlink", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
 ]
 nvjitlink = [
-    { name = "nvidia-nvjitlink", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
 ]
 nvrtc = [
-    { name = "nvidia-cuda-nvrtc", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-cuda-nvrtc", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
 ]
 nvtx = [
-    { name = "nvidia-nvtx", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
+    { name = "nvidia-nvtx", marker = "(python_full_version < '3.11' and platform_machine == 'AMD64' and sys_platform == 'win32') or (platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
 ]
 [[package]]
@ -1220,7 +1220,7 @@ name = "exceptiongroup"
 version = "1.3.1"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "typing-extensions" },
+    { name = "typing-extensions", marker = "python_full_version < '3.11'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/50/79/66800aadf48771f6b62f7eb014e352e5d06856655206165d775e675a02c9/exceptiongroup-1.3.1.tar.gz", hash = "sha256:8b412432c6055b0b7d14c310000ae93352ed6754f70fa8f7c34141f91c4e3219", size = 30371, upload-time = "2025-11-21T23:01:54.787Z" }
 wheels = [
@ -1637,7 +1637,7 @@ name = "gunicorn"
 version = "26.0.0"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "packaging" },
+    { name = "packaging", marker = "python_full_version < '3.11' or sys_platform != 'win32'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/6d/b7/a4a3f632f823e432ce6bc65f62961b7980c898c77f075a2f7118cb3846fe/gunicorn-26.0.0.tar.gz", hash = "sha256:ca9346f85e3a4aeeb64d491045c16b9a35647abd37ea15efe53080eb8b090baf", size = 727286, upload-time = "2026-05-05T06:38:25.529Z" }
 wheels = [
@ -1988,7 +1988,7 @@ requires-dist = [
    { name = "rapidocr-onnxruntime", marker = "python_full_version < '3.13' and extra == 'image'", specifier = ">=1.4.0,<2" },
    { name = "respx", marker = "extra == 'dev'", specifier = ">=0.20.0" },
    { name = "rich", specifier = ">=13.0.0" },
-    { name = "ruff", marker = "extra == 'dev'", specifier = "==0.15.22" },
+    { name = "ruff", marker = "extra == 'dev'", specifier = "==0.16.2" },
    { name = "scikit-learn", marker = "extra == 'evals'", specifier = ">=1.3.0" },
    { name = "sentence-transformers", marker = "sys_platform == 'darwin' and extra == 'pytorch-mps'", specifier = ">=2.2.0" },
    { name = "sentence-transformers", marker = "(platform_machine != 'x86_64' and extra == 'evals') or (sys_platform != 'darwin' and extra == 'evals')", specifier = ">=2.2.0,<6.0" },
@ -2207,7 +2207,7 @@ name = "humanfriendly"
 version = "10.0"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "pyreadline3", marker = "sys_platform == 'win32'" },
+    { name = "pyreadline3", marker = "python_full_version < '3.11' and sys_platform == 'win32'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/cc/3f/2c29224acb2e2df4d2046e4c73ee2662023c58ff5b113c4c1adac0886c43/humanfriendly-10.0.tar.gz", hash = "sha256:6b0b831ce8f15f7300721aa49829fc4e83921a9a301cc7f606be6686a2288ddc", size = 360702, upload-time = "2021-09-17T21:40:43.31Z" }
 wheels = [
@ -2690,18 +2690,18 @@ name = "litellm"
 version = "1.88.1"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "aiohttp" },
+    { name = "aiohttp", marker = "python_full_version < '3.14'" },
-    { name = "click" },
+    { name = "click", marker = "python_full_version < '3.14'" },
-    { name = "fastuuid" },
+    { name = "fastuuid", marker = "python_full_version < '3.14'" },
-    { name = "httpx" },
+    { name = "httpx", marker = "python_full_version < '3.14'" },
-    { name = "importlib-metadata" },
+    { name = "importlib-metadata", marker = "python_full_version < '3.14'" },
-    { name = "jinja2" },
+    { name = "jinja2", marker = "python_full_version < '3.14'" },
-    { name = "jsonschema" },
+    { name = "jsonschema", marker = "python_full_version < '3.14'" },
-    { name = "openai" },
+    { name = "openai", marker = "python_full_version < '3.14'" },
-    { name = "pydantic" },
+    { name = "pydantic", marker = "python_full_version < '3.14'" },
-    { name = "python-dotenv" },
+    { name = "python-dotenv", marker = "python_full_version < '3.14'" },
-    { name = "tiktoken" },
+    { name = "tiktoken", marker = "python_full_version < '3.14'" },
-    { name = "tokenizers" },
+    { name = "tokenizers", marker = "python_full_version < '3.14'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/16/ea/f99ececb7f22703fe120f1d8be9ffb749ec9453fbbbbbebc0d6a6b4d7864/litellm-1.88.1.tar.gz", hash = "sha256:89c6b74cc7912d6365793006ff951c0450fe847625008dfe49de8a7dc4529aa5", size = 13885969, upload-time = "2026-06-09T01:06:25.192Z" }
 wheels = [
@ -3583,7 +3583,7 @@ name = "nvidia-cublas"
 version = "13.1.1.3"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "nvidia-cuda-nvrtc" },
+    { name = "nvidia-cuda-nvrtc", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/a7/a1/0bd24ee8c8d03adac032fd2909426a00c88f8c57961b1277ded97f91119f/nvidia_cublas-13.1.1.3-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:b7a210458267ac818974c53038fbec2e969d5c99f305ab15c72522fa9f001dd5", size = 542848918, upload-time = "2026-04-08T18:46:22.985Z" },
@ -3622,7 +3622,7 @@ name = "nvidia-cudnn-cu13"
 version = "9.20.0.48"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "nvidia-cublas" },
+    { name = "nvidia-cublas", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/56/c5/83384d846b2fd17c44bd499b36c75a45ed4f095fbbb2252294e89cea5c5c/nvidia_cudnn_cu13-9.20.0.48-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:e31454ae00094b0c55319d9d15b6fa2fc50a9e1c0f5c8c80fb75258234e731e1", size = 444574296, upload-time = "2026-03-09T19:28:27.751Z" },
@ -3634,7 +3634,7 @@ name = "nvidia-cufft"
 version = "12.0.0.61"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "nvidia-nvjitlink" },
+    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/8b/ae/f417a75c0259e85c1d2f83ca4e960289a5f814ed0cea74d18c353d3e989d/nvidia_cufft-12.0.0.61-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2708c852ef8cd89d1d2068bdbece0aa188813a0c934db3779b9b1faa8442e5f5", size = 214053554, upload-time = "2025-09-04T08:31:38.196Z" },
@ -3664,9 +3664,9 @@ name = "nvidia-cusolver"
 version = "12.0.4.66"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "nvidia-cublas" },
+    { name = "nvidia-cublas", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
-    { name = "nvidia-cusparse" },
+    { name = "nvidia-cusparse", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
-    { name = "nvidia-nvjitlink" },
+    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/c8/c3/b30c9e935fc01e3da443ec0116ed1b2a009bb867f5324d3f2d7e533e776b/nvidia_cusolver-12.0.4.66-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:02c2457eaa9e39de20f880f4bd8820e6a1cfb9f9a34f820eb12a155aa5bc92d2", size = 223467760, upload-time = "2025-09-04T08:33:04.222Z" },
@ -3678,7 +3678,7 @@ name = "nvidia-cusparse"
 version = "12.6.3.3"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "nvidia-nvjitlink" },
+    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.11' and sys_platform == 'emscripten') or (python_full_version < '3.11' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/f8/94/5c26f33738ae35276672f12615a64bd008ed5be6d1ebcb23579285d960a9/nvidia_cusparse-12.6.3.3-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:80bcc4662f23f1054ee334a15c72b8940402975e0eab63178fc7e670aa59472c", size = 162155568, upload-time = "2025-09-04T08:33:42.864Z" },
@ -3757,8 +3757,8 @@ name = "omegaconf"
 version = "2.3.0"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "antlr4-python3-runtime" },
+    { name = "antlr4-python3-runtime", marker = "python_full_version >= '3.13'" },
-    { name = "pyyaml" },
+    { name = "pyyaml", marker = "python_full_version >= '3.13'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/09/48/6388f1bb9da707110532cb70ec4d2822858ddfb44f1cdf1233c20a80ea4b/omegaconf-2.3.0.tar.gz", hash = "sha256:d5d4b6d29955cc50ad50c46dc269bcd92c6e00f5f90d23ab5fee7bfca4ba4cc7", size = 3298120, upload-time = "2022-12-08T20:59:22.753Z" }
 wheels = [
@ -3773,12 +3773,12 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "coloredlogs" },
+    { name = "coloredlogs", marker = "python_full_version < '3.11'" },
-    { name = "flatbuffers" },
+    { name = "flatbuffers", marker = "python_full_version < '3.11'" },
-    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple/" } },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version < '3.11'" },
-    { name = "packaging" },
+    { name = "packaging", marker = "python_full_version < '3.11'" },
-    { name = "protobuf" },
+    { name = "protobuf", marker = "python_full_version < '3.11'" },
-    { name = "sympy" },
+    { name = "sympy", marker = "python_full_version < '3.11'" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/35/d6/311b1afea060015b56c742f3531168c1644650767f27ef40062569960587/onnxruntime-1.23.2-cp310-cp310-macosx_13_0_arm64.whl", hash = "sha256:a7730122afe186a784660f6ec5807138bf9d792fa1df76556b27307ea9ebcbe3", size = 17195934, upload-time = "2025-10-27T23:06:14.143Z" },
@ -3824,10 +3824,10 @@ resolution-markers = [
    "python_full_version == '3.11.*' and sys_platform != 'emscripten' and sys_platform != 'win32'",
 ]
 dependencies = [
-    { name = "flatbuffers" },
+    { name = "flatbuffers", marker = "python_full_version >= '3.11'" },
-    { name = "numpy", version = "2.4.1", source = { registry = "https://pypi.org/simple/" } },
+    { name = "numpy", version = "2.4.1", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version >= '3.11'" },
-    { name = "packaging" },
+    { name = "packaging", marker = "python_full_version >= '3.11'" },
-    { name = "protobuf" },
+    { name = "protobuf", marker = "python_full_version >= '3.11'" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/d4/81/29a9eb470994a75eb7b3ccf32be314d7c66675a00ac7b50294816cc2db27/onnxruntime-1.26.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:ee1109ef4ef27cad90e823399e61e03b3c6c7bfe0fb820b4baf3678c15be8b3c", size = 18005108, upload-time = "2026-05-08T19:08:11.728Z" },
@ -3911,7 +3911,7 @@ name = "openresponses-types"
 version = "2.3.0.post1"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "pydantic" },
+    { name = "pydantic", marker = "python_full_version >= '3.11'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/d9/26/b612c3215f5599714fa94d63eb5ee59b4eb66dbdeeaf86bb4d848359484d/openresponses_types-2.3.0.post1.tar.gz", hash = "sha256:11b8896d3621d2ac2439f6ff106f34ddcb1bbd517c317a6c852a9df2e98a0753", size = 19254, upload-time = "2026-01-22T20:02:03.933Z" }
 wheels = [
@ -4154,10 +4154,10 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple/" } },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version < '3.11'" },
-    { name = "python-dateutil" },
+    { name = "python-dateutil", marker = "python_full_version < '3.11'" },
-    { name = "pytz" },
+    { name = "pytz", marker = "python_full_version < '3.11'" },
-    { name = "tzdata" },
+    { name = "tzdata", marker = "python_full_version < '3.11'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/33/01/d40b85317f86cf08d853a4f495195c73815fdf205eef3993821720274518/pandas-2.3.3.tar.gz", hash = "sha256:e05e1af93b977f7eafa636d043f9f94c7ee3ac81af99c13508215942e64c993b", size = 4495223, upload-time = "2025-09-29T23:34:51.853Z" }
 wheels = [
@ -4229,9 +4229,9 @@ resolution-markers = [
    "python_full_version == '3.11.*' and sys_platform != 'emscripten' and sys_platform != 'win32'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.4.1", source = { registry = "https://pypi.org/simple/" } },
+    { name = "numpy", version = "2.4.1", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version >= '3.11'" },
-    { name = "python-dateutil" },
+    { name = "python-dateutil", marker = "python_full_version >= '3.11'" },
-    { name = "tzdata", marker = "sys_platform == 'emscripten' or sys_platform == 'win32'" },
+    { name = "tzdata", marker = "(python_full_version >= '3.11' and sys_platform == 'emscripten') or (python_full_version >= '3.11' and sys_platform == 'win32')" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/de/da/b1dc0481ab8d55d0f46e343cfe67d4551a0e14fcee52bd38ca1bd73258d8/pandas-3.0.0.tar.gz", hash = "sha256:0facf7e87d38f721f0af46fe70d97373a37701b1c09f7ed7aeeb292ade5c050f", size = 4633005, upload-time = "2026-01-21T15:52:04.726Z" }
 wheels = [
@ -5393,17 +5393,17 @@ name = "rapidocr"
 version = "3.8.1"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "colorlog" },
+    { name = "colorlog", marker = "python_full_version >= '3.13'" },
-    { name = "numpy", version = "2.4.1", source = { registry = "https://pypi.org/simple/" } },
+    { name = "numpy", version = "2.4.1", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version >= '3.13'" },
-    { name = "omegaconf" },
+    { name = "omegaconf", marker = "python_full_version >= '3.13'" },
-    { name = "opencv-python" },
+    { name = "opencv-python", marker = "python_full_version >= '3.13'" },
-    { name = "pillow" },
+    { name = "pillow", marker = "python_full_version >= '3.13'" },
-    { name = "pyclipper" },
+    { name = "pyclipper", marker = "python_full_version >= '3.13'" },
-    { name = "pyyaml" },
+    { name = "pyyaml", marker = "python_full_version >= '3.13'" },
-    { name = "requests" },
+    { name = "requests", marker = "python_full_version >= '3.13'" },
-    { name = "shapely" },
+    { name = "shapely", marker = "python_full_version >= '3.13'" },
-    { name = "six" },
+    { name = "six", marker = "python_full_version >= '3.13'" },
-    { name = "tqdm" },
+    { name = "tqdm", marker = "python_full_version >= '3.13'" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/ea/4a/fa521d947f0fc7bb304bf11bec4cb66266bd81494588b4cb48dc01001719/rapidocr-3.8.1-py3-none-any.whl", hash = "sha256:650044b1fbce9e6bae5cae462dcf8be754cde11e2f23fc51f65dcc08deae2c46", size = 15080319, upload-time = "2026-04-11T07:13:22.56Z" },
@ -5414,17 +5414,17 @@ name = "rapidocr-onnxruntime"
 version = "1.4.4"
 source = { registry = "https://pypi.org/simple/" }
 dependencies = [
-    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version < '3.11' or python_full_version >= '3.13'" },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version < '3.11'" },
    { name = "numpy", version = "2.4.1", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version >= '3.11' and python_full_version < '3.13'" },
-    { name = "onnxruntime", version = "1.23.2", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version < '3.11' or python_full_version >= '3.13'" },
+    { name = "onnxruntime", version = "1.23.2", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version < '3.11'" },
    { name = "onnxruntime", version = "1.26.0", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version >= '3.11' and python_full_version < '3.13'" },
-    { name = "opencv-python" },
+    { name = "opencv-python", marker = "python_full_version < '3.13'" },
-    { name = "pillow" },
+    { name = "pillow", marker = "python_full_version < '3.13'" },
-    { name = "pyclipper" },
+    { name = "pyclipper", marker = "python_full_version < '3.13'" },
-    { name = "pyyaml" },
+    { name = "pyyaml", marker = "python_full_version < '3.13'" },
-    { name = "shapely" },
+    { name = "shapely", marker = "python_full_version < '3.13'" },
-    { name = "six" },
+    { name = "six", marker = "python_full_version < '3.13'" },
-    { name = "tqdm" },
+    { name = "tqdm", marker = "python_full_version < '3.13'" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/ba/12/1e5497183bdbe782dbb91bad1d0d2297dba4d2831b2652657f7517bfc6df/rapidocr_onnxruntime-1.4.4-py3-none-any.whl", hash = "sha256:971d7d5f223a7a808662229df1ef69893809d8457d834e6373d3854bc1782cbf", size = 14915192, upload-time = "2025-01-17T01:48:25.104Z" },
@ -5754,27 +5754,27 @@ wheels = [
 [[package]]
 name = "ruff"
-version = "0.15.22"
+version = "0.16.2"
 source = { registry = "https://pypi.org/simple/" }
-sdist = { url = "https://files.pythonhosted.org/packages/3a/06/ae069393fc66e8ff33036d4b368003833bf6e88ccf182e17e7a2f1c754fd/ruff-0.15.22.tar.gz", hash = "sha256:3f15175b1fb580126f58285a5dae6b2ea89000136d980c64499211f116b54809", size = 4785063, upload-time = "2026-07-16T15:14:13.244Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/73/e1/4508a569211b35599016e84ba65c1a992b7a4004b4b6c4bea02a851cba1b/ruff-0.16.2.tar.gz", hash = "sha256:c3d7828d12e8927a6fc65fe38e2c2541b9e762d360a1786d752cb1b8883b3c9c", size = 4885811, upload-time = "2026-08-07T13:31:01.432Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/23/18/ee54b7ae1e121be7a28ea6da4b67564ebb0530e183a54415ab7e3bcd2c4e/ruff-0.15.22-py3-none-linux_armv6l.whl", hash = "sha256:44423e73493737f5e7c5b41d475483898ff37afcdae38bc3da5085e29af1c2d8", size = 10781258, upload-time = "2026-07-16T15:13:19.452Z" },
+    { url = "https://files.pythonhosted.org/packages/14/57/db19951540f98859c956b50bdb4d31089b4d91e9f15e2968e7d5193806d5/ruff-0.16.2-py3-none-linux_armv6l.whl", hash = "sha256:3c8de4cf2181f01d57946d87d777aa52916976fc09942aed89938fab5e013318", size = 10847925, upload-time = "2026-08-07T13:30:14.468Z" },
-    { url = "https://files.pythonhosted.org/packages/2f/d2/2520cb14761ddbeaf57642a76942fc36adcbdbe53b4532241995f6fc485c/ruff-0.15.22-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:b82c6482946e9eda7ff2e091d25b8bad3f718684e1916d41bd56873cee05b697", size = 10999477, upload-time = "2026-07-16T15:13:23.318Z" },
+    { url = "https://files.pythonhosted.org/packages/13/5a/995fe85a8470d3e391ac0f7fa8054bb454eaf33ee138196d6172ed1079c0/ruff-0.16.2-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:9a48cc05c6fbc811ca81b5d7ba95375affea6582d1b8024e455e41afbbf55344", size = 11072662, upload-time = "2026-08-07T13:30:18.143Z" },
-    { url = "https://files.pythonhosted.org/packages/c9/10/74e53572aa758dfaa678c2a2646b5c5515d884b7ca56be4d2ce03ca4b560/ruff-0.15.22-py3-none-macosx_11_0_arm64.whl", hash = "sha256:11c1c715af53a09f714e011106bffc419751ec8232fcb5da42173284ea3fec6f", size = 10466716, upload-time = "2026-07-16T15:13:26.162Z" },
+    { url = "https://files.pythonhosted.org/packages/32/53/370d767c61c71a971a4ace36703a7ecd8c393956349a7325d7fab2b56827/ruff-0.16.2-py3-none-macosx_11_0_arm64.whl", hash = "sha256:a2c0d14fcbb26c91f0f867a6dc9bd71bbc30b1b6151829c884f23faeab2e5700", size = 10566771, upload-time = "2026-08-07T13:30:20.899Z" },
-    { url = "https://files.pythonhosted.org/packages/1e/cc/44eaaf0844e028182f2d0a8f2190d0f359159aed0a9e5ab861d892f1ae2a/ruff-0.15.22-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:742a29cf29bddb7c8327895d6a10e0e6c5b38a96dd407af9b5d0857f809c0576", size = 10892644, upload-time = "2026-07-16T15:13:29.229Z" },
+    { url = "https://files.pythonhosted.org/packages/85/d6/9d96948caf5a632be62d62202d5ec914d6856f204fd79eb036e5915e79ea/ruff-0.16.2-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:335c621622c4650330be50842561c6586ac6971bb8ab5407fe34dcc9efb16bbe", size = 10975825, upload-time = "2026-08-07T13:30:23.517Z" },
-    { url = "https://files.pythonhosted.org/packages/9f/21/8edf559014d2b0f82beea19cfb713993ad802ccda16868769979c6090a84/ruff-0.15.22-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:72af58b951b0ae395935ae79763dc349bc0eb706319d28f7a33ad2cfb3cfc178", size = 10576719, upload-time = "2026-07-16T15:13:32.35Z" },
+    { url = "https://files.pythonhosted.org/packages/3b/92/ea87129b3414acb0b5770563779c51804d37ac67675c7ba35447ddb14773/ruff-0.16.2-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:20e66910f2c37cc753f9ef6580c914a621b80c4fa3549d3e3521e29d0f5bfc3f", size = 10649437, upload-time = "2026-08-07T13:30:26.097Z" },
-    { url = "https://files.pythonhosted.org/packages/bf/1e/3a13abd392a3b50b62e5938a831f9ab6e588358cacad5c18545b716d2182/ruff-0.15.22-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:62d425005c1835eb24e2ee4161cb90e8db263415f4a71c8c72c33abaa6c0c224", size = 11376494, upload-time = "2026-07-16T15:13:35.958Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/43/f8f291dcd4af5bb7872b74fdfa41a7cd7c856ca1d4069670971cf1b9f5cb/ruff-0.16.2-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c7e36fbfba65510548156902bcf1350a979a958ce0347ce0f90d73894036b39f", size = 11446761, upload-time = "2026-08-07T13:30:28.752Z" },
-    { url = "https://files.pythonhosted.org/packages/bf/3e/422d3d95bcf04dd78e1aeac22184d4f9a8fb2c01865d39d44618484a0317/ruff-0.15.22-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e8b9b3f8779a4f08c969defc3c8c35abffaa757e601ed5ae66d6d1db6519969a", size = 12208370, upload-time = "2026-07-16T15:13:39.185Z" },
+    { url = "https://files.pythonhosted.org/packages/71/4a/ef991fb2fcf516ab71f0808adcdd8da5e18c8cde447f4ceaf5f47a5132a5/ruff-0.16.2-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f0eab35f80df8f134aae5d1630e751901321d317cc8e50dc39e36fa3ed34cd12", size = 12336364, upload-time = "2026-08-07T13:30:31.468Z" },
-    { url = "https://files.pythonhosted.org/packages/1e/91/5d065a0e0a02bf4813f5119ad278462eed081d2b832eb7c021ade0ec9e65/ruff-0.15.22-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1e0dd1b2e4d3d585f897a0d137cbf4eaf6223bef4e8ce34d6bb12556c5f9249e", size = 11581098, upload-time = "2026-07-16T15:13:42.132Z" },
+    { url = "https://files.pythonhosted.org/packages/f3/24/f615e74f307e6ca0e56a482872477b856c70d530aa356abfb6dfe5ca8a80/ruff-0.16.2-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:40ea8c0594feb894e89c8c61ab9c103d38b0ea72dfde6c594107147ca31b1140", size = 11630720, upload-time = "2026-08-07T13:30:34.426Z" },
-    { url = "https://files.pythonhosted.org/packages/f6/f9/a0d4871d12fae702eb1f41b686caf05f1f8b124dc6db6f784f53d74918fa/ruff-0.15.22-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:365523eb91d9224e1bcb03b022fbf0facb8f9e23792a2c53d9d4b3924bdbdebb", size = 11399422, upload-time = "2026-07-16T15:13:45.2Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/d3/8ef50149e8412a77f7ab409efdef0e2b23803707a3863da4fc64cb23d459/ruff-0.16.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ab3d62dde0b19facdd632008cc4827fc28ada7736c6bd35ab6f1050f0bfed53f", size = 11466130, upload-time = "2026-08-07T13:30:36.958Z" },
-    { url = "https://files.pythonhosted.org/packages/18/80/c843a5176cddbceb0b7e8dd41cf9993490796c1c469348d384f5a5c13c56/ruff-0.15.22-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:fabfd168afdf29fee5be98b831efa9683c94d7c5a3b58b9ce5a2e38444589a74", size = 11381683, upload-time = "2026-07-16T15:13:48.46Z" },
+    { url = "https://files.pythonhosted.org/packages/dd/a7/a19334985c4dea8c381981fa252cd854c7ee52dc4b1686dc16f4a911c702/ruff-0.16.2-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:e43e1f5b8388da9eca1b9e88328d47a5cec794633ccf6f7484ac2dd15eee92c0", size = 11523634, upload-time = "2026-08-07T13:30:39.822Z" },
-    { url = "https://files.pythonhosted.org/packages/d4/00/8485de0ae92239438a36cfc51350db9b9e85c9ebdfaea91b18e422706662/ruff-0.15.22-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:225dbf095a87f1d9f90f5fd7924d2613ee452a75a4308c63a8f50f761787aa7c", size = 10850295, upload-time = "2026-07-16T15:13:51.655Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/6c/96d192b0e742412ceda08c0a50f9669b253dde9fd6a60ea1a10c9fa79a63/ruff-0.16.2-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:c24788a980581e1d7ea3a0cbe4344c4fbeb0a6a9b1f4713aa46bb104f8294690", size = 10949807, upload-time = "2026-08-07T13:30:42.745Z" },
-    { url = "https://files.pythonhosted.org/packages/fa/91/24977ec2ec72eaf15e4394ace2959fdff2dd1e14f03e005e838023407169/ruff-0.15.22-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:1877d63b9d24ed278744f1523fd11b85540566d54641f97c566d7d9dc5ca5296", size = 10579640, upload-time = "2026-07-16T15:13:54.79Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/51/e26599ceca11e79ee255c7df515995561edf87e9ca1893284e44d98f5a86/ruff-0.16.2-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:81806b08329130005dd4a8a8394a0c9da8c6f4cafb16ba438d2a2ee6a18bedf1", size = 10646891, upload-time = "2026-08-07T13:30:45.522Z" },
-    { url = "https://files.pythonhosted.org/packages/9c/47/9b51216951974df1f263ac19da550d34252e0ed7218c25f10c5ef9ed7517/ruff-0.15.22-py3-none-musllinux_1_2_i686.whl", hash = "sha256:a1606c510bd7215680d32efab38965f7cdec3ef69f5170a3f4791404ffdd5262", size = 11105077, upload-time = "2026-07-16T15:13:57.915Z" },
+    { url = "https://files.pythonhosted.org/packages/68/01/800c4b1f97bc8d7c6029e06b1f20473a3cf1e13c4933d8f3342add83fc55/ruff-0.16.2-py3-none-musllinux_1_2_i686.whl", hash = "sha256:4ce4e02bad779bef557f541a1b31f20d6abeae1cc05ed1b1ac019d4ffd1044c8", size = 11162063, upload-time = "2026-08-07T13:30:48.131Z" },
-    { url = "https://files.pythonhosted.org/packages/c2/47/20e9d4a3b8016778acea5fc32bb50d35d207500a17ddb529ffa6996feef8/ruff-0.15.22-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:630479b18625f5ffc373f77603a22a9f8ac0acd7ff0501178b5db28ec71e9c64", size = 11490980, upload-time = "2026-07-16T15:14:01.032Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/d0/1477ea50fc5a0d4b0b71d1d63d50770bdd794d90b43e37a7618e63ec9894/ruff-0.16.2-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:e0422abdf70070255fc4073ce9dfc814cc03db577013761ddd09bc1e4a9a4fbd", size = 11556038, upload-time = "2026-08-07T13:30:50.686Z" },
-    { url = "https://files.pythonhosted.org/packages/4d/76/3f72d8fc38c1cb77b38c56a70da9d0c17700cc1cc50f9649c9d3c8f5ba71/ruff-0.15.22-py3-none-win32.whl", hash = "sha256:e5ba0e4a13fd14abbed2a77b517a3911290c6c6c59ef67784328d1668fab76cf", size = 10789165, upload-time = "2026-07-16T15:14:04.16Z" },
+    { url = "https://files.pythonhosted.org/packages/b8/76/a7776f32048d991e16d4fa8ff91790b877342d3596cc3ed04acdbf1aaedc/ruff-0.16.2-py3-none-win32.whl", hash = "sha256:bf3a63d78fb39f4bf5ac8ae52051c5520505301abe19ba4e204c453b3f09bb0b", size = 10872850, upload-time = "2026-08-07T13:30:53.471Z" },
-    { url = "https://files.pythonhosted.org/packages/cb/46/4965251734c2b6fcdca1b1b187d20bcac3af0ee5b083b89c910bb961ce3a/ruff-0.15.22-py3-none-win_amd64.whl", hash = "sha256:9be63ba1eb936acd2d1342fb8337c356353706fce233b2a15a09a97037e6acde", size = 11938297, upload-time = "2026-07-16T15:14:07.316Z" },
+    { url = "https://files.pythonhosted.org/packages/00/0d/929c800d920e61397d82a01b60bffc68da3052c17d31de59efaad2e4ed75/ruff-0.16.2-py3-none-win_amd64.whl", hash = "sha256:bcabe2f6d0fc7819f1431793005af4e4de7371927d037345bf941252b195b9fa", size = 12023338, upload-time = "2026-08-07T13:30:56.193Z" },
-    { url = "https://files.pythonhosted.org/packages/57/c9/e69b1ff4c8b69093ef08b8919ab767af0569666865b39c30a8795d88d3c6/ruff-0.15.22-py3-none-win_arm64.whl", hash = "sha256:e1168075b72158510839f250027659cdd78476f40507dd517892304c41318661", size = 11298172, upload-time = "2026-07-16T15:14:10.51Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/6c/93e26c22c5f78ff87363e07da49c84955affbeb1098bd1936bf3b3f293bf/ruff-0.16.2-py3-none-win_arm64.whl", hash = "sha256:d614e95cedf38a2053fd351c55b103ba30d017d61688fdbfd40ee0412852a99f", size = 11374065, upload-time = "2026-08-07T13:30:58.775Z" },
 ]
 [[package]]
@ -5821,10 +5821,10 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "joblib" },
+    { name = "joblib", marker = "python_full_version < '3.11'" },
-    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple/" } },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version < '3.11'" },
-    { name = "scipy", version = "1.15.3", source = { registry = "https://pypi.org/simple/" } },
+    { name = "scipy", version = "1.15.3", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version < '3.11'" },
-    { name = "threadpoolctl" },
+    { name = "threadpoolctl", marker = "python_full_version < '3.11'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/98/c2/a7855e41c9d285dfe86dc50b250978105dce513d6e459ea66a6aeb0e1e0c/scikit_learn-1.7.2.tar.gz", hash = "sha256:20e9e49ecd130598f1ca38a1d85090e1a600147b9c02fa6f15d69cb53d968fda", size = 7193136, upload-time = "2025-09-09T08:21:29.075Z" }
 wheels = [
@ -5879,10 +5879,10 @@ resolution-markers = [
    "python_full_version == '3.11.*' and sys_platform != 'emscripten' and sys_platform != 'win32'",
 ]
 dependencies = [
-    { name = "joblib" },
+    { name = "joblib", marker = "python_full_version >= '3.11'" },
-    { name = "numpy", version = "2.4.1", source = { registry = "https://pypi.org/simple/" } },
+    { name = "numpy", version = "2.4.1", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version >= '3.11'" },
-    { name = "scipy", version = "1.17.0", source = { registry = "https://pypi.org/simple/" } },
+    { name = "scipy", version = "1.17.0", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version >= '3.11'" },
-    { name = "threadpoolctl" },
+    { name = "threadpoolctl", marker = "python_full_version >= '3.11'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/0e/d4/40988bf3b8e34feec1d0e6a051446b1f66225f8529b9309becaeef62b6c4/scikit_learn-1.8.0.tar.gz", hash = "sha256:9bccbb3b40e3de10351f8f5068e105d0f4083b1a65fa07b6634fbc401a6287fd", size = 7335585, upload-time = "2025-12-10T07:08:53.618Z" }
 wheels = [
@ -5932,7 +5932,7 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple/" } },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version < '3.11'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/0f/37/6964b830433e654ec7485e45a00fc9a27cf868d622838f6b6d9c5ec0d532/scipy-1.15.3.tar.gz", hash = "sha256:eae3cf522bc7df64b42cad3925c876e1b0b6c35c1337c93e12c0f366f55b0eaf", size = 59419214, upload-time = "2025-05-08T16:13:05.955Z" }
 wheels = [
@ -6002,7 +6002,7 @@ resolution-markers = [
    "python_full_version == '3.11.*' and sys_platform != 'emscripten' and sys_platform != 'win32'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.4.1", source = { registry = "https://pypi.org/simple/" } },
+    { name = "numpy", version = "2.4.1", source = { registry = "https://pypi.org/simple/" }, marker = "python_full_version >= '3.11'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/56/3e/9cca699f3486ce6bc12ff46dc2031f1ec8eb9ccc9a320fdaf925f1417426/scipy-1.17.0.tar.gz", hash = "sha256:2591060c8e648d8b96439e111ac41fd8342fdeff1876be2e19dea3fe8930454e", size = 30396830, upload-time = "2026-01-10T21:34:23.009Z" }
 wheels = [
--- a/wiki/ARCHITECTURE.md
+++ b/wiki/ARCHITECTURE.md
@ -226,8 +226,8 @@ analysis = {
    "data": [
        {"ts": 45, "cpu": 92},  # Keep the spike!
        {"ts": 46, "cpu": 95},
-        ...
+        ...,
-    ]
+    ],
 }
 ```
@ -397,11 +397,9 @@ def analyze_field(key, items):
        "unique_ratio": len(set(values)) / len(values),
        # 0.0 = all same (constant)
        # 1.0 = all different (unique IDs)
        "variance": statistics.variance(values),  # For numbers
        # Low = stable
        # High = changing
        "change_points": detect_spikes(values),
        # Indices where value jumps significantly
    }
@ -502,14 +500,14 @@ When SmartCrusher compresses, the original content is stored for on-demand retri
 ```python
@dataclass
 class CompressionEntry:
-    hash: str                    # 16-char SHA256 for retrieval
+    hash: str  # 16-char SHA256 for retrieval
-    original_content: str        # Full JSON before compression
+    original_content: str  # Full JSON before compression
-    compressed_content: str      # Compressed JSON
+    compressed_content: str  # Compressed JSON
    original_item_count: int
    compressed_item_count: int
-    tool_name: str | None        # For feedback tracking
+    tool_name: str | None  # For feedback tracking
    created_at: float
-    ttl: int = 300               # 5 minute default
+    ttl: int = 300  # 5 minute default
 ```
 **Features:**
@ -625,12 +623,12 @@ The feedback system learns from retrieval patterns to improve future compression
@dataclass
 class ToolPattern:
    tool_name: str
-    total_compressions: int      # Times we compressed this tool
+    total_compressions: int  # Times we compressed this tool
-    total_retrievals: int        # Times LLM asked for more
+    total_retrievals: int  # Times LLM asked for more
-    full_retrievals: int         # Retrieved everything (all retrievals — hash-only)
+    full_retrievals: int  # Retrieved everything (all retrievals — hash-only)
-    search_retrievals: int       # Legacy; always 0 (retrieval is hash-only, no search)
+    search_retrievals: int  # Legacy; always 0 (retrieval is hash-only, no search)
-    common_queries: dict[str, int]   # Legacy query-pattern frequency (no longer populated)
+    common_queries: dict[str, int]  # Legacy query-pattern frequency (no longer populated)
-    queried_fields: dict[str, int]   # Legacy queried-field frequency (no longer populated)
+    queried_fields: dict[str, int]  # Legacy queried-field frequency (no longer populated)
 ```
 **Key Metrics:**
@ -644,12 +642,12 @@ class ToolPattern:
 ```python
@dataclass
 class CompressionHints:
-    max_items: int = 15          # Target item count
+    max_items: int = 15  # Target item count
    suggested_items: int | None  # Calculated optimal
-    skip_compression: bool       # Don't compress at all
+    skip_compression: bool  # Don't compress at all
-    preserve_fields: list[str]   # Always keep these fields
+    preserve_fields: list[str]  # Always keep these fields
-    aggressiveness: float        # 0.0 = aggressive, 1.0 = conservative
+    aggressiveness: float  # 0.0 = aggressive, 1.0 = conservative
-    reason: str                  # Explanation
+    reason: str  # Explanation
 ```
 **Feedback-Driven Adjustment:**
@ -733,24 +731,26 @@ if self.config.use_feedback_hints and tool_name:
 ```python
@dataclass
 class CCRToolCall:
-    tool_call_id: str      # For matching response
+    tool_call_id: str  # For matching response
-    hash_key: str          # CCR hash to retrieve
+    hash_key: str  # CCR hash to retrieve
@dataclass
 class CCRToolResult:
    tool_call_id: str
-    content: str           # Retrieved data as JSON
+    content: str  # Retrieved data as JSON
    success: bool
    items_retrieved: int
 class CCRResponseHandler:
    async def handle_response(
        self,
-        response: dict,           # Initial LLM response
+        response: dict,  # Initial LLM response
-        messages: list,           # Conversation history
+        messages: list,  # Conversation history
-        tools: list,              # Tool definitions
+        tools: list,  # Tool definitions
-        api_call_fn: Callable,    # Function to make API calls
+        api_call_fn: Callable,  # Function to make API calls
-        provider: str,            # "anthropic" or "openai"
+        provider: str,  # "anthropic" or "openai"
    ) -> dict:
        """Handle CCR tool calls until final response."""
 ```
@ -762,11 +762,14 @@ The handler also supports streaming responses via `StreamingCCRHandler`:
 ```python
 class StreamingCCRBuffer:
    """Buffers streaming chunks to detect CCR tool calls."""
    chunks: list[bytes]
    detected_ccr: bool
 class StreamingCCRHandler:
    """Handles CCR in streaming responses."""
    async def process_stream(self, stream, messages, tools, api_call_fn):
        """Yields chunks, switching to buffered mode if CCR detected."""
 ```
@ -848,11 +851,11 @@ The tracker uses simple but effective heuristics:
@dataclass
 class ContextTrackerConfig:
    enabled: bool = True
-    max_tracked_contexts: int = 100      # LRU eviction
+    max_tracked_contexts: int = 100  # LRU eviction
-    relevance_threshold: float = 0.3     # Min score to recommend
+    relevance_threshold: float = 0.3  # Min score to recommend
-    max_context_age_seconds: float = 300 # 5 minutes
+    max_context_age_seconds: float = 300  # 5 minutes
    proactive_expansion: bool = True
-    max_proactive_expansions: int = 2    # Per query
+    max_proactive_expansions: int = 2  # Per query
 ```
 ---
--- a/wiki/agno.md
+++ b/wiki/agno.md
@ -167,6 +167,7 @@ Full async support for high-throughput applications:
 import asyncio
 from headroom.integrations.agno import HeadroomAgnoModel
 async def process_async():
    model = HeadroomAgnoModel(OpenAIChat(id="gpt-4o"))
@ -179,6 +180,7 @@ async def process_async():
    print(f"\nTokens saved: {model.total_tokens_saved}")
 asyncio.run(process_async())
 ```
--- a/wiki/api.md
+++ b/wiki/api.md
@ -101,9 +101,9 @@ config = CacheAlignerConfig(
 from headroom import RelevanceScorerConfig
 config = RelevanceScorerConfig(
-    scorer_type="bm25",      # "bm25", "embedding", or "hybrid"
+    scorer_type="bm25",  # "bm25", "embedding", or "hybrid"
-    embedding_model=None,    # Model name for embedding scorer
+    embedding_model=None,  # Model name for embedding scorer
-    hybrid_alpha=0.5,        # Weight for hybrid scoring
+    hybrid_alpha=0.5,  # Weight for hybrid scoring
 )
 ```
@ -286,10 +286,12 @@ result = aligner.align(messages)
 ```python
 from headroom import TransformPipeline
-pipeline = TransformPipeline([
+pipeline = TransformPipeline(
-    SmartCrusher(),
+    [
-    CacheAligner(),
+        SmartCrusher(),
-])
+        CacheAligner(),
    ]
 )
 result = pipeline.transform(messages)
 ```
--- a/wiki/compression.md
+++ b/wiki/compression.md
@ -79,21 +79,18 @@ from headroom.compression import UniversalCompressorConfig
 config = UniversalCompressorConfig(
    # Detection
-    use_magika=True,               # Use ML-based detection (requires magika)
+    use_magika=True,  # Use ML-based detection (requires magika)
    # Compression
    # (Note: the legacy `use_llmlingua` flag was retired with the
    # LLMLingua-2 integration. The optional ML compressor is now Kompress,
    # installed via `headroom-ai[ml]` and configured separately.)
    compression_ratio_target=0.3,  # Keep 30% of content (70% reduction)
-    min_content_length=100,        # Skip content shorter than this
+    min_content_length=100,  # Skip content shorter than this
    # Structure preservation
-    use_entropy_preservation=True, # Preserve high-entropy tokens
+    use_entropy_preservation=True,  # Preserve high-entropy tokens
-    entropy_threshold=0.85,        # Entropy threshold for preservation
+    entropy_threshold=0.85,  # Entropy threshold for preservation
    # CCR
-    ccr_enabled=True,              # Store originals for retrieval
+    ccr_enabled=True,  # Store originals for retrieval
 )
 ```
@ -121,12 +118,12 @@ Preserves JSON structure while compressing values:
 from headroom.compression.handlers.json_handler import JSONStructureHandler
 handler = JSONStructureHandler(
-    preserve_short_values=True,     # Keep values < 20 chars
+    preserve_short_values=True,  # Keep values < 20 chars
-    short_value_threshold=20,       # Threshold for "short"
+    short_value_threshold=20,  # Threshold for "short"
-    preserve_high_entropy=True,     # Keep UUIDs, hashes
+    preserve_high_entropy=True,  # Keep UUIDs, hashes
-    entropy_threshold=0.85,         # Entropy threshold
+    entropy_threshold=0.85,  # Entropy threshold
-    max_array_items_full=3,         # Keep first N array items full
+    max_array_items_full=3,  # Keep first N array items full
-    max_number_digits=10,           # Preserve numbers up to N digits
+    max_number_digits=10,  # Preserve numbers up to N digits
 )
 ```
@ -141,18 +138,10 @@ handler = JSONStructureHandler(
 ```python
 # Before
-{
+{"id": "usr_abc123", "name": "Alice Johnson", "bio": "A long description that goes on and on..."}
    "id": "usr_abc123",
    "name": "Alice Johnson",
    "bio": "A long description that goes on and on..."
 }
 # After (structure preserved, long values compressed)
-{
+{"id": "usr_abc123", "name": "Alice Johnson", "bio": "A long...[compressed]..."}
    "id": "usr_abc123",
    "name": "Alice Johnson",
    "bio": "A long...[compressed]..."
 }
 ```
 ### Code Handler
@ -163,9 +152,9 @@ Preserves code structure using AST parsing (tree-sitter) or regex fallback:
 from headroom.compression.handlers.code_handler import CodeStructureHandler
 handler = CodeStructureHandler(
-    preserve_comments=False,        # Preserve comments as structural
+    preserve_comments=False,  # Preserve comments as structural
-    use_tree_sitter=True,           # Use tree-sitter for parsing
+    use_tree_sitter=True,  # Use tree-sitter for parsing
-    default_language="python",      # Default when detection fails
+    default_language="python",  # Default when detection fails
 )
 ```
@ -226,24 +215,24 @@ from headroom.compression import compress
 result = compress(content)
 # Access result fields
-print(result.compressed)           # Compressed content
+print(result.compressed)  # Compressed content
-print(result.original)             # Original content
+print(result.original)  # Original content
-print(result.compression_ratio)    # e.g., 0.35 (35% of original size)
+print(result.compression_ratio)  # e.g., 0.35 (35% of original size)
-print(result.tokens_before)        # Estimated tokens before
+print(result.tokens_before)  # Estimated tokens before
-print(result.tokens_after)         # Estimated tokens after
+print(result.tokens_after)  # Estimated tokens after
-print(result.tokens_saved)         # tokens_before - tokens_after
+print(result.tokens_saved)  # tokens_before - tokens_after
-print(result.savings_percentage)   # e.g., 65.0 (65% savings)
+print(result.savings_percentage)  # e.g., 65.0 (65% savings)
 # Detection info
-print(result.content_type)         # ContentType.JSON, CODE, etc.
+print(result.content_type)  # ContentType.JSON, CODE, etc.
-print(result.detection_confidence) # 0.0-1.0
+print(result.detection_confidence)  # 0.0-1.0
 # Structure info
-print(result.handler_used)         # "json", "code", etc.
+print(result.handler_used)  # "json", "code", etc.
-print(result.preservation_ratio)   # Fraction preserved as structure
+print(result.preservation_ratio)  # Fraction preserved as structure
 # CCR info
-print(result.ccr_key)              # Key for retrieval (if CCR enabled)
+print(result.ccr_key)  # Key for retrieval (if CCR enabled)
 ```
 ---
@ -259,8 +248,8 @@ compressor = UniversalCompressor()
 contents = [
    '{"users": [...]}',
-    'def hello(): pass',
+    "def hello(): pass",
-    'Plain text content',
+    "Plain text content",
 ]
 results = compressor.compress_batch(contents)
@ -393,11 +382,11 @@ json_content = """
 result = compressor.compress(json_content)
-print(f"Type: {result.content_type}")          # ContentType.JSON
+print(f"Type: {result.content_type}")  # ContentType.JSON
-print(f"Handler: {result.handler_used}")        # json
+print(f"Handler: {result.handler_used}")  # json
 print(f"Saved: {result.savings_percentage:.0f}%")  # ~60%
 print(f"Structure: {result.preservation_ratio:.0%} preserved")  # ~40%
-print(f"CCR Key: {result.ccr_key}")             # For retrieval
+print(f"CCR Key: {result.ccr_key}")  # For retrieval
 ```
 ---
--- a/wiki/configuration.md
+++ b/wiki/configuration.md
@ -31,22 +31,17 @@ from openai import OpenAI
 client = HeadroomClient(
    original_client=OpenAI(),
    provider=OpenAIProvider(),
    # Mode: "audit" (observe only) or "optimize" (apply transforms)
    default_mode="optimize",
    # Enable provider-specific cache optimization
    enable_cache_optimizer=True,
    # Enable query-level semantic caching
    enable_semantic_cache=False,
    # Override default context limits per model
    model_context_limits={
        "gpt-4o": 128000,
        "gpt-4o-mini": 128000,
    },
    # Database location (defaults to temp directory)
    # store_url="sqlite:////absolute/path/to/headroom.db",
 )
@ -136,20 +131,14 @@ Override configuration for specific requests:
 response = client.chat.completions.create(
    model="gpt-4o",
    messages=[...],
    # Override mode for this request
    headroom_mode="audit",
    # Reserve more tokens for output
    headroom_output_buffer_tokens=8000,
    # Keep last N turns (don't compress)
    headroom_keep_turns=5,
    # Skip compression for specific tools
-    headroom_tool_profiles={
+    headroom_tool_profiles={"important_tool": {"skip_compression": True}},
        "important_tool": {"skip_compression": True}
    }
 )
 ```
@ -186,13 +175,10 @@ from headroom.transforms import SmartCrusherConfig
 config = SmartCrusherConfig(
    # Maximum items to keep after compression
    max_items_after_crush=15,
    # Minimum tokens before applying compression
    min_tokens_to_crush=200,
    # Relevance scoring tier: "bm25" (fast) or "embedding" (accurate)
    relevance_tier="bm25",
    # Always keep items with these field values
    preserve_fields=["error", "warning", "failure"],
 )
@ -208,7 +194,6 @@ from headroom.transforms import CacheAlignerConfig
 config = CacheAlignerConfig(
    # Enable/disable cache alignment
    enabled=True,
    # Patterns to extract from system prompt
    dynamic_patterns=[
        r"Today is \w+ \d+, \d{4}",
--- a/wiki/errors.md
+++ b/wiki/errors.md
@ -6,12 +6,12 @@ Headroom provides explicit exceptions for debugging, with a safety guarantee tha
 ```python
 from headroom import (
-    HeadroomError,        # Base class - catch all Headroom errors
+    HeadroomError,  # Base class - catch all Headroom errors
-    ConfigurationError,   # Invalid configuration
+    ConfigurationError,  # Invalid configuration
-    ProviderError,        # Provider issues (unknown model, etc.)
+    ProviderError,  # Provider issues (unknown model, etc.)
-    StorageError,         # Database/storage failures
+    StorageError,  # Database/storage failures
-    CompressionError,     # Compression failures (rare)
+    CompressionError,  # Compression failures (rare)
-    ValidationError,      # Setup validation failures
+    ValidationError,  # Setup validation failures
 )
 ```
@ -75,10 +75,7 @@ Raised for provider-specific issues.
 # - Token counting failure
 try:
-    response = client.chat.completions.create(
+    response = client.chat.completions.create(model="unknown-model-xyz", messages=[...])
        model="unknown-model-xyz",
        messages=[...]
    )
 except ProviderError as e:
    print(f"Provider error: {e}")
    print(f"Provider: {e.details.get('provider')}")
@ -122,10 +119,7 @@ Raised when setup validation fails.
 ```python
 result = client.validate_setup()
 if not result["valid"]:
-    raise ValidationError(
+    raise ValidationError("Setup validation failed", details={"issues": result["issues"]})
        "Setup validation failed",
        details={"issues": result["issues"]}
    )
 ```
 ## Safety Guarantee
@ -136,16 +130,11 @@ This is a core design principle. Your LLM calls never fail due to Headroom:
 ```python
 # Even if SmartCrusher encounters unexpected data:
-messages = [
+messages = [{"role": "tool", "content": "malformed json {{{"}]
    {"role": "tool", "content": "malformed json {{{"}
 ]
 # This will NOT raise an exception
 # Instead, the malformed content passes through unchanged
-response = client.chat.completions.create(
+response = client.chat.completions.create(model="gpt-4o", messages=messages)
    model="gpt-4o",
    messages=messages
 )
 ```
 ## Logging Errors
@ -154,6 +143,7 @@ Enable logging to see error details:
 ```python
 import logging
 logging.basicConfig(level=logging.WARNING)
 # Now you'll see warnings when compression is skipped:
@ -232,6 +222,7 @@ response = client.chat.completions.create(...)
 ```python
 import logging
 logging.basicConfig(level=logging.DEBUG)
 # Shows detailed transform decisions
--- a/wiki/image-compression.md
+++ b/wiki/image-compression.md
@ -61,13 +61,15 @@ client = HeadroomClient(provider="openai")
 response = client.chat.completions.create(
    model="gpt-4o",
-    messages=[{
+    messages=[
-        "role": "user",
+        {
-        "content": [
+            "role": "user",
-            {"type": "text", "text": "What animal is this?"},
+            "content": [
-            {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,..."}}
+                {"type": "text", "text": "What animal is this?"},
-        ]
+                {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,..."}},
-    }]
+            ],
        }
    ],
 )
 # Image automatically compressed with detail="low" (87% savings)
 ```
@ -106,8 +108,8 @@ from headroom.image import ImageCompressor
 compressor = ImageCompressor(
    model_id="chopratejas/technique-router",  # HuggingFace model
-    use_siglip=True,   # Enable image analysis
+    use_siglip=True,  # Enable image analysis
-    device="cuda",     # Use GPU if available
+    device="cuda",  # Use GPU if available
 )
 ```
@ -229,9 +231,11 @@ The HuggingFace model downloads on first use:
 ```python
 # Force a specific cache directory
 import os
 os.environ["HF_HOME"] = "/path/to/cache"
 from headroom.image import ImageCompressor
 compressor = ImageCompressor()
 ```
@ -290,10 +294,10 @@ class ImageCompressor:
 ```python
@dataclass
 class CompressionResult:
-    technique: Technique      # full_low, preserve, crop, transcode
+    technique: Technique  # full_low, preserve, crop, transcode
-    original_tokens: int      # Estimated tokens before
+    original_tokens: int  # Estimated tokens before
-    compressed_tokens: int    # Estimated tokens after
+    compressed_tokens: int  # Estimated tokens after
-    confidence: float         # Router confidence (0-1)
+    confidence: float  # Router confidence (0-1)
    @property
    def savings_percent(self) -> float:
@ -304,10 +308,10 @@ class CompressionResult:
 ```python
 class Technique(Enum):
-    FULL_LOW = "full_low"     # 87% savings
+    FULL_LOW = "full_low"  # 87% savings
-    PRESERVE = "preserve"     # 0% savings
+    PRESERVE = "preserve"  # 0% savings
-    CROP = "crop"             # 50-90% savings
+    CROP = "crop"  # 50-90% savings
-    TRANSCODE = "transcode"   # 99% savings
+    TRANSCODE = "transcode"  # 99% savings
 ```
 ## See Also
--- a/wiki/integration-guide.md
+++ b/wiki/integration-guide.md
@ -92,22 +92,26 @@ import httpx
 from headroom import compress
 compressed = compress(messages, model="claude-sonnet-4-5-20250929")
-httpx.post("https://api.anthropic.com/v1/messages", json={
+httpx.post(
-    "model": "claude-sonnet-4-5-20250929",
+    "https://api.anthropic.com/v1/messages",
-    "messages": compressed.messages,
+    json={
-}, headers={"X-Api-Key": api_key, "anthropic-version": "2023-06-01"})
+        "model": "claude-sonnet-4-5-20250929",
        "messages": compressed.messages,
    },
    headers={"X-Api-Key": api_key, "anthropic-version": "2023-06-01"},
 )
 ```
 ### What compress() returns
 ```python
 result = compress(messages, model="gpt-4o")
-result.messages           # list[dict] — compressed messages, same format as input
+result.messages  # list[dict] — compressed messages, same format as input
-result.tokens_before      # int — original token count
+result.tokens_before  # int — original token count
-result.tokens_after       # int — compressed token count
+result.tokens_after  # int — compressed token count
-result.tokens_saved       # int — tokens removed
+result.tokens_saved  # int — tokens removed
 result.compression_ratio  # float — 0.0 (no savings) to 1.0 (100% removed)
-result.transforms_applied # list[str] — what ran (e.g., ["router:smart_crusher:0.35"])
+result.transforms_applied  # list[str] — what ran (e.g., ["router:smart_crusher:0.35"])
 ```
 ---
@ -169,6 +173,7 @@ app.add_middleware(CompressionMiddleware)
 # LiteLLM proxy
 from litellm.proxy.proxy_server import app
 app.add_middleware(CompressionMiddleware)
 ```
@ -309,6 +314,7 @@ Customize compression behavior without modifying Headroom's code:
 ```python
 from headroom import compress, CompressionHooks, CompressContext
 class MyHooks(CompressionHooks):
    def pre_compress(self, messages, ctx):
        # Modify messages before compression (dedup, filter, inject)
@ -323,6 +329,7 @@ class MyHooks(CompressionHooks):
        # Observe results (logging, analytics, learning)
        print(f"Saved {event.tokens_saved} tokens")
 result = compress(messages, model="gpt-4o", hooks=MyHooks())
 ```
--- a/wiki/langchain.md
+++ b/wiki/langchain.md
@ -91,11 +91,13 @@ Works seamlessly with LangChain tool calling:
 ```python
 from langchain_core.tools import tool
@tool
 def search(query: str) -> str:
    """Search the web."""
    return {"results": [...]}  # Large JSON response
 llm_with_tools = llm.bind_tools([search])
 response = llm_with_tools.invoke("Search for Python tutorials")
 # Tool outputs are automatically compressed in subsequent turns
@ -117,7 +119,7 @@ base_history = ChatMessageHistory()
 compressed_history = HeadroomChatMessageHistory(
    base_history,
    compress_threshold_tokens=4000,  # Compress when over 4K tokens
-    keep_recent_turns=5,             # Always keep last 5 turns
+    keep_recent_turns=5,  # Always keep last 5 turns
 )
 # Use with any memory class
@ -152,9 +154,9 @@ base_retriever = vectorstore.as_retriever(search_kwargs={"k": 50})
 # Wrap with Headroom compression (keep best for precision)
 compressor = HeadroomDocumentCompressor(
-    max_documents=10,      # Keep top 10
+    max_documents=10,  # Keep top 10
-    min_relevance=0.3,     # Minimum relevance score
+    min_relevance=0.3,  # Minimum relevance score
-    prefer_diverse=True,   # MMR-style diversity
+    prefer_diverse=True,  # MMR-style diversity
 )
 retriever = ContextualCompressionRetriever(
@ -179,18 +181,21 @@ from langchain.agents import create_openai_tools_agent, AgentExecutor
 from langchain_core.tools import tool
 from headroom.integrations import wrap_tools_with_headroom
@tool
 def search_database(query: str) -> str:
    """Search the database."""
    # Returns 1000 results as JSON
    return json.dumps({"results": [...], "total": 1000})
@tool
 def fetch_logs(service: str) -> str:
    """Fetch service logs."""
    # Returns 500 log entries
    return json.dumps({"logs": [...]})
 # Wrap tools with compression
 tools = [search_database, fetch_logs]
 wrapped_tools = wrap_tools_with_headroom(
@ -296,26 +301,33 @@ from langchain_core.tools import tool
 from langgraph.prebuilt import create_react_agent
 from headroom.integrations import HeadroomChatModel, wrap_tools_with_headroom
 # Define tools that return large outputs
@tool
 def search_web(query: str) -> str:
    """Search the web for information."""
    # Simulating large search results
-    return json.dumps({
+    return json.dumps(
-        "results": [
+        {
-            {"title": f"Result {i}", "snippet": "..." * 100, "url": f"https://..."}
+            "results": [
-            for i in range(100)
+                {"title": f"Result {i}", "snippet": "..." * 100, "url": f"https://..."}
-        ],
+                for i in range(100)
-        "total": 1000,
+            ],
-    })
+            "total": 1000,
        }
    )
@tool
 def query_database(sql: str) -> str:
    """Execute SQL query."""
-    return json.dumps({
+    return json.dumps(
-        "rows": [{"id": i, "data": "..." * 50} for i in range(500)],
+        {
-        "total": 500,
+            "rows": [{"id": i, "data": "..." * 50} for i in range(500)],
-    })
+            "total": 500,
        }
    )
 # Wrap model with Headroom
 llm = HeadroomChatModel(ChatOpenAI(model="gpt-4o"))
@ -327,9 +339,9 @@ tools = wrap_tools_with_headroom([search_web, query_database])
 agent = create_react_agent(llm, tools)
 # Run - tool outputs are automatically compressed between iterations
-result = agent.invoke({
+result = agent.invoke(
-    "messages": [("user", "Find all users who signed up last week and their activity")]
+    {"messages": [("user", "Find all users who signed up last week and their activity")]}
-})
+)
 # Check savings
 print(f"Tokens saved: {llm.get_metrics()['tokens_saved']}")
@ -352,23 +364,29 @@ from langchain_core.messages import HumanMessage
 from langgraph.graph import StateGraph, MessagesState, START, END
 from headroom.integrations.langchain import create_compress_tool_messages_node
 # Define your agent and tools nodes
 def agent_node(state: MessagesState):
    llm = ChatOpenAI(model="gpt-4o")
    response = llm.invoke(state["messages"])
    return {"messages": [response]}
 def tools_node(state: MessagesState):
    # Your tool execution logic here
    ...
 # Build the graph with a compression step
 graph = StateGraph(MessagesState)
 graph.add_node("agent", agent_node)
 graph.add_node("tools", tools_node)
-graph.add_node("compress", create_compress_tool_messages_node(
+graph.add_node(
-    min_tokens_to_compress=100,  # Only compress outputs > ~100 tokens
+    "compress",
-))
+    create_compress_tool_messages_node(
        min_tokens_to_compress=100,  # Only compress outputs > ~100 tokens
    ),
 )
 # Wire: tools -> compress -> agent (instead of tools -> agent directly)
 graph.add_edge(START, "agent")
@ -411,9 +429,9 @@ base_retriever = vectorstore.as_retriever(search_kwargs={"k": 50})
 # Headroom compressor for precision
 compressor = HeadroomDocumentCompressor(
-    max_documents=5,       # Keep only top 5
+    max_documents=5,  # Keep only top 5
-    min_relevance=0.4,     # Must be 40%+ relevant
+    min_relevance=0.4,  # Must be 40%+ relevant
-    prefer_diverse=True,   # Avoid redundant docs
+    prefer_diverse=True,  # Avoid redundant docs
 )
 # Combine into compression retriever
@ -461,7 +479,7 @@ base_history = ChatMessageHistory()
 compressed_history = HeadroomChatMessageHistory(
    base_history,
    compress_threshold_tokens=8000,  # Compress when over 8K
-    keep_recent_turns=10,            # Always keep last 10 turns
+    keep_recent_turns=10,  # Always keep last 10 turns
 )
 memory = ConversationBufferMemory(
@ -500,30 +518,45 @@ from headroom.integrations import (
    reset_tool_metrics,
 )
@tool
 def search_arxiv(query: str) -> str:
    """Search arXiv for papers."""
-    return json.dumps({"papers": [{"title": f"Paper {i}", "abstract": "..." * 200} for i in range(50)]})
+    return json.dumps(
        {"papers": [{"title": f"Paper {i}", "abstract": "..." * 200} for i in range(50)]}
    )
@tool
 def search_github(query: str) -> str:
    """Search GitHub repositories."""
-    return json.dumps({"repos": [{"name": f"repo-{i}", "description": "..." * 100, "stars": i * 100} for i in range(100)]})
+    return json.dumps(
        {
            "repos": [
                {"name": f"repo-{i}", "description": "..." * 100, "stars": i * 100}
                for i in range(100)
            ]
        }
    )
@tool
 def fetch_documentation(url: str) -> str:
    """Fetch documentation from URL."""
    return "..." * 5000  # Large doc content
 # Wrap everything
 llm = HeadroomChatModel(ChatOpenAI(model="gpt-4o"))
 tools = wrap_tools_with_headroom([search_arxiv, search_github, fetch_documentation])
-prompt = ChatPromptTemplate.from_messages([
+prompt = ChatPromptTemplate.from_messages(
-    ("system", "You are a research assistant. Use tools to gather information."),
+    [
-    ("human", "{input}"),
+        ("system", "You are a research assistant. Use tools to gather information."),
-    ("placeholder", "{agent_scratchpad}"),
+        ("human", "{input}"),
-])
+        ("placeholder", "{agent_scratchpad}"),
    ]
 )
 agent = create_openai_tools_agent(llm, tools, prompt)
 executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
@ -532,9 +565,11 @@ executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
 reset_tool_metrics()
 # Run complex research task
-result = executor.invoke({
+result = executor.invoke(
-    "input": "Research the latest advances in LLM context compression and find relevant GitHub projects"
+    {
-})
+        "input": "Research the latest advances in LLM context compression and find relevant GitHub projects"
    }
 )
 # Check per-tool metrics
 metrics = get_tool_metrics().get_summary()
@ -550,9 +585,9 @@ print(f"Per-tool breakdown: {metrics['by_tool']}")
 ```python
 HeadroomChatModel(
-    wrapped_model,                     # Any LangChain BaseChatModel
+    wrapped_model,  # Any LangChain BaseChatModel
    headroom_config=HeadroomConfig(),  # Headroom configuration
-    auto_detect_provider=True,         # Auto-detect from wrapped model
+    auto_detect_provider=True,  # Auto-detect from wrapped model
 )
 ```
@ -560,10 +595,10 @@ HeadroomChatModel(
 ```python
 HeadroomChatMessageHistory(
-    base_history,                      # Any BaseChatMessageHistory
+    base_history,  # Any BaseChatMessageHistory
-    compress_threshold_tokens=4000,    # Token threshold for compression
+    compress_threshold_tokens=4000,  # Token threshold for compression
-    keep_recent_turns=5,               # Minimum turns to preserve
+    keep_recent_turns=5,  # Minimum turns to preserve
-    model="gpt-4o",                    # Model for token counting
+    model="gpt-4o",  # Model for token counting
 )
 ```
@ -571,9 +606,9 @@ HeadroomChatMessageHistory(
 ```python
 HeadroomDocumentCompressor(
-    max_documents=10,                  # Maximum docs to return
+    max_documents=10,  # Maximum docs to return
-    min_relevance=0.0,                 # Minimum relevance score (0-1)
+    min_relevance=0.0,  # Minimum relevance score (0-1)
-    prefer_diverse=False,              # Use MMR for diversity
+    prefer_diverse=False,  # Use MMR for diversity
 )
 ```
@ -581,9 +616,9 @@ HeadroomDocumentCompressor(
 ```python
 wrap_tools_with_headroom(
-    tools,                             # List of LangChain tools
+    tools,  # List of LangChain tools
-    min_chars_to_compress=1000,        # Minimum output size
+    min_chars_to_compress=1000,  # Minimum output size
-    smart_crusher_config=None,         # SmartCrusher configuration
+    smart_crusher_config=None,  # SmartCrusher configuration
 )
 ```
@ -595,27 +630,21 @@ wrap_tools_with_headroom(
 from headroom.integrations import (
    # Chat Model
    HeadroomChatModel,
    # Memory
    HeadroomChatMessageHistory,
    # Retrievers
    HeadroomDocumentCompressor,
    # Agents
    HeadroomToolWrapper,
    wrap_tools_with_headroom,
    get_tool_metrics,
    reset_tool_metrics,
    # Streaming
    StreamingMetricsTracker,
    StreamingMetricsCallback,
    track_streaming_response,
    # LangSmith
    HeadroomLangSmithCallbackHandler,
    # Provider Detection
    detect_provider,
    get_headroom_provider,
@ -660,7 +689,7 @@ Check that your message count exceeds the threshold:
 history = HeadroomChatMessageHistory(
    base_history,
    compress_threshold_tokens=1000,  # Lower threshold
-    keep_recent_turns=2,             # Fewer preserved turns
+    keep_recent_turns=2,  # Fewer preserved turns
 )
 ```
--- a/wiki/memory.md
+++ b/wiki/memory.md
@ -159,15 +159,13 @@ client = with_memory(OpenAI(), user_id="alice")
 # Use exactly like normal
 response = client.chat.completions.create(
-    model="gpt-4o",
+    model="gpt-4o", messages=[{"role": "user", "content": "I prefer Python for backend work"}]
    messages=[{"role": "user", "content": "I prefer Python for backend work"}]
 )
 # Memory extracted INLINE - zero extra latency
 # Later, in a new conversation...
 response = client.chat.completions.create(
-    model="gpt-4o",
+    model="gpt-4o", messages=[{"role": "user", "content": "What language should I use?"}]
    messages=[{"role": "user", "content": "What language should I use?"}]
 )
 # → Response uses the Python preference from memory
 ```
@ -228,7 +226,7 @@ client1 = with_memory(
 )
 response = client1.chat.completions.create(
    model="gpt-4o",
-    messages=[{"role": "user", "content": "I prefer Go for performance-critical code"}]
+    messages=[{"role": "user", "content": "I prefer Go for performance-critical code"}],
 )
 # Memory stored at USER level (persists across sessions)
@ -239,8 +237,7 @@ client2 = with_memory(
    session_id="afternoon-session",  # Different session
 )
 response = client2.chat.completions.create(
-    model="gpt-4o",
+    model="gpt-4o", messages=[{"role": "user", "content": "What language for my new microservice?"}]
    messages=[{"role": "user", "content": "What language for my new microservice?"}]
 )
 # → Recalls Go preference from morning session!
 ```
@ -270,17 +267,21 @@ new = await memory.supersede(
 )
 # Query current state (excludes superseded)
-current = await memory.query(MemoryFilter(
+current = await memory.query(
-    user_id="alice",
+    MemoryFilter(
-    include_superseded=False,  # Default
+        user_id="alice",
-))
+        include_superseded=False,  # Default
    )
 )
 # → Returns only "User now works at Anthropic"
 # Query full history (includes superseded)
-history = await memory.query(MemoryFilter(
+history = await memory.query(
-    user_id="alice",
+    MemoryFilter(
-    include_superseded=True,
+        user_id="alice",
-))
+        include_superseded=True,
    )
 )
 # → Returns both memories with validity timestamps
 # Get the chain
@ -362,6 +363,7 @@ from headroom.memory import (
 )
 from headroom.memory.ports import MemoryFilter, VectorFilter
 async def main():
    # Create with custom configuration
    config = MemoryConfig(
@ -402,17 +404,20 @@ async def main():
    )
    # Query with filters
-    memories = await memory.query(MemoryFilter(
+    memories = await memory.query(
-        user_id="alice",
+        MemoryFilter(
-        categories=[MemoryCategory.PREFERENCE, MemoryCategory.FACT],
+            user_id="alice",
-        min_importance=0.7,
+            categories=[MemoryCategory.PREFERENCE, MemoryCategory.FACT],
-        limit=10,
+            min_importance=0.7,
-    ))
+            limit=10,
        )
    )
    # Convenience methods
    await memory.remember("Likes coffee", user_id="alice", importance=0.6)
    relevant = await memory.recall("beverage preferences", user_id="alice")
 asyncio.run(main())
 ```
@ -482,13 +487,13 @@ Apple GPU instead of the default ONNX CPU embedder. Notes:
 ```python
 config = MemoryConfig(
-    db_path="memory.db",          # SQLite database path
+    db_path="memory.db",  # SQLite database path
-    vector_dimension=384,          # Must match embedder output
+    vector_dimension=384,  # Must match embedder output
-    hnsw_ef_construction=200,      # HNSW index quality (higher = better, slower)
+    hnsw_ef_construction=200,  # HNSW index quality (higher = better, slower)
-    hnsw_m=16,                     # HNSW connections per node
+    hnsw_m=16,  # HNSW connections per node
-    hnsw_ef_search=50,             # HNSW search quality
+    hnsw_ef_search=50,  # HNSW search quality
-    cache_enabled=True,            # Enable LRU cache
+    cache_enabled=True,  # Enable LRU cache
-    cache_max_size=1000,           # Max cached memories
+    cache_max_size=1000,  # Max cached memories
 )
 ```
@ -499,7 +504,7 @@ client = with_memory(
    OpenAI(),
    user_id="alice",
    db_path="memory.db",
-    top_k=5,                       # Memories to inject per request
+    top_k=5,  # Memories to inject per request
    session_id="optional-session",
    agent_id="optional-agent",
    embedder_backend=EmbedderBackend.LOCAL,
@ -659,6 +664,7 @@ client = with_memory(
 # Groq
 from groq import Groq
 client = with_memory(Groq(), user_id="alice")
 # Any OpenAI-compatible client
@ -678,10 +684,12 @@ client = with_memory(OpenAI(), user_id="developer_jane")
 # Conversation 1: User shares context
 response = client.chat.completions.create(
    model="gpt-4o",
-    messages=[{
+    messages=[
-        "role": "user",
+        {
-        "content": "I'm a Python developer at a fintech startup. We use PostgreSQL and FastAPI."
+            "role": "user",
-    }]
+            "content": "I'm a Python developer at a fintech startup. We use PostgreSQL and FastAPI.",
        }
    ],
 )
 # Memories extracted:
 #   - [FACT] Python developer at fintech startup
@ -691,10 +699,7 @@ response = client.chat.completions.create(
 # Conversation 2 (new session): User asks question
 response = client.chat.completions.create(
    model="gpt-4o",
-    messages=[{
+    messages=[{"role": "user", "content": "What database should I use for my new project?"}],
        "role": "user",
        "content": "What database should I use for my new project?"
    }]
 )
 # Response references PostgreSQL preference from memory:
 # → "Given your experience with PostgreSQL at your fintech company,
--- a/wiki/metrics.md
+++ b/wiki/metrics.md
@ -336,19 +336,19 @@ print(stats)
        "tokens_saved_total": 15000,
        "tokens_output_total": 8000,
        "cache_hits": 3,
-        "compression_ratio_avg": 0.70
+        "compression_ratio_avg": 0.70,
    },
    "config": {
        "mode": "optimize",
        "provider": "openai",
        "cache_optimizer_enabled": True,
-        "semantic_cache_enabled": False
+        "semantic_cache_enabled": False,
    },
    "transforms": {
        "smart_crusher_enabled": True,
        "cache_aligner_enabled": True,
-        "rolling_window_enabled": True
+        "rolling_window_enabled": True,
-    }
+    },
 }
 ```
--- a/wiki/plans/dynamic-smart-crusher.md
+++ b/wiki/plans/dynamic-smart-crusher.md
@ -72,17 +72,18 @@ Different data patterns need different position importance:
 ```python
 class AnchorStrategy(Enum):
-    FRONT_HEAVY = "front_heavy"     # Search results: top items matter most
+    FRONT_HEAVY = "front_heavy"  # Search results: top items matter most
-    BACK_HEAVY = "back_heavy"       # Logs: recent items matter most
+    BACK_HEAVY = "back_heavy"  # Logs: recent items matter most
-    BALANCED = "balanced"           # Time series: both ends matter
+    BALANCED = "balanced"  # Time series: both ends matter
-    MIDDLE_AWARE = "middle_aware"   # Database: order might be arbitrary
+    MIDDLE_AWARE = "middle_aware"  # Database: order might be arbitrary
 def get_anchor_strategy(pattern: DataPattern) -> AnchorStrategy:
    return {
        DataPattern.SEARCH_RESULTS: AnchorStrategy.FRONT_HEAVY,  # Top N by score
-        DataPattern.LOGS: AnchorStrategy.BACK_HEAVY,             # Recency matters
+        DataPattern.LOGS: AnchorStrategy.BACK_HEAVY,  # Recency matters
-        DataPattern.TIME_SERIES: AnchorStrategy.BALANCED,        # Both ends for trend
+        DataPattern.TIME_SERIES: AnchorStrategy.BALANCED,  # Both ends for trend
-        DataPattern.GENERIC: AnchorStrategy.MIDDLE_AWARE,        # Don't assume order
+        DataPattern.GENERIC: AnchorStrategy.MIDDLE_AWARE,  # Don't assume order
    }.get(pattern, AnchorStrategy.BALANCED)
 ```
@ -150,7 +151,7 @@ def select_informative_anchors(
    items: list[dict],
    region: str,  # "front", "back", "middle"
    slots: int,
-    all_items_hash: set[str]
+    all_items_hash: set[str],
 ) -> list[int]:
    """Select most informative items from a region."""
@ -195,7 +196,7 @@ def calculate_information_score(item: dict, all_items: list[dict]) -> float:
    for field, value in item.items():
        field_values = [i.get(field) for i in all_items if field in i]
        value_frequency = field_values.count(value) / len(field_values)
-        score += (1 - value_frequency)  # Rare values score higher
+        score += 1 - value_frequency  # Rare values score higher
    # 2. Structural uniqueness - different fields than typical
    typical_fields = get_typical_fields(all_items)
@ -221,6 +222,7 @@ Track which positions users actually retrieve and learn from it:
@dataclass
 class PositionRetrievalPattern:
    """Learned position importance from retrieval data."""
    tool_name: str
    total_compressions: int
    position_retrievals: dict[str, int]  # "front_10%", "middle", "back_10%"
@ -231,21 +233,13 @@ class PositionRetrievalPattern:
        if total == 0:
            return {"front": 0.5, "middle": 0.0, "back": 0.5}
-        return {
+        return {position: count / total for position, count in self.position_retrievals.items()}
            position: count / total
            for position, count in self.position_retrievals.items()
        }
 class TOINPositionLearning:
    """Learn position importance from retrieval patterns."""
-    def record_retrieval(
+    def record_retrieval(self, tool_name: str, original_size: int, retrieved_indices: list[int]):
        self,
        tool_name: str,
        original_size: int,
        retrieved_indices: list[int]
    ):
        """Record which positions were retrieved."""
        for idx in retrieved_indices:
            position = self._classify_position(idx, original_size)
@ -287,9 +281,7 @@ For large arrays, sample strategically from middle:
 ```python
 def stratified_middle_sample(
-    items: list[dict],
+    items: list[dict], num_samples: int, analysis: ArrayAnalysis
    num_samples: int,
    analysis: ArrayAnalysis
 ) -> list[int]:
    """Sample middle positions using stratified approach."""
@ -310,9 +302,7 @@ def stratified_middle_sample(
    if analysis.numeric_fields:
        variance_scores = calculate_position_variance(items, analysis.numeric_fields)
        sorted_by_variance = sorted(
-            middle_items,
+            middle_items, key=lambda i: variance_scores.get(i, 0), reverse=True
            key=lambda i: variance_scores.get(i, 0),
            reverse=True
        )
        return sorted(sorted_by_variance[:num_samples])
@ -383,11 +373,7 @@ class TestAdversarialPositions:
        items[42]["name"] = "target_item"
        items[42]["description"] = "This is what user asked about"
-        result = smart_crusher.crush(
+        result = smart_crusher.crush(items, max_items=10, query="find target_item")
            items,
            max_items=10,
            query="find target_item"
        )
        # Query-matched item MUST be preserved
        assert any("target_item" in item.get("name", "") for item in result)
@ -399,12 +385,15 @@ class TestAdversarialPositions:
 class TestSizeAdaptation:
    """Test that anchor allocation scales with array size."""
-    @pytest.mark.parametrize("size,expected_min_anchors", [
+    @pytest.mark.parametrize(
-        (20, 3),    # Small array: at least 3 anchors
+        "size,expected_min_anchors",
-        (100, 4),   # Medium array: at least 4 anchors
+        [
-        (500, 5),   # Large array: at least 5 anchors
+            (20, 3),  # Small array: at least 3 anchors
-        (2000, 6),  # Very large: at least 6 anchors
+            (100, 4),  # Medium array: at least 4 anchors
-    ])
+            (500, 5),  # Large array: at least 5 anchors
            (2000, 6),  # Very large: at least 6 anchors
        ],
    )
    def test_anchor_count_scales(self, size, expected_min_anchors):
        """Anchor count should increase with array size."""
        items = [{"id": i, "value": i * 10} for i in range(size)]
@ -413,8 +402,7 @@ class TestSizeAdaptation:
        # Count items from first 10% and last 10%
        anchor_count = sum(
-            1 for item in result
+            1 for item in result if item["id"] < size * 0.1 or item["id"] > size * 0.9
            if item["id"] < size * 0.1 or item["id"] > size * 0.9
        )
        assert anchor_count >= expected_min_anchors
@ -454,10 +442,7 @@ class TestPatternAwareAnchoring:
    def test_search_results_front_heavy(self):
        """Search results should preserve more from front."""
-        items = [
+        items = [{"title": f"Result {i}", "score": 1.0 - (i * 0.01)} for i in range(100)]
            {"title": f"Result {i}", "score": 1.0 - (i * 0.01)}
            for i in range(100)
        ]
        result = smart_crusher.crush(items, max_items=10)
@ -485,10 +470,7 @@ class TestPatternAwareAnchoring:
    def test_time_series_balanced(self):
        """Time series should have balanced front/back."""
-        items = [
+        items = [{"timestamp": f"2024-01-01T{i:02d}:00:00", "value": 100 + i} for i in range(24)]
            {"timestamp": f"2024-01-01T{i:02d}:00:00", "value": 100 + i}
            for i in range(24)
        ]
        result = smart_crusher.crush(items, max_items=8)
@ -510,11 +492,7 @@ class TestQueryAwareAnchoring:
        """'Latest' in query should preserve more recent items."""
        items = [{"id": i, "created": f"2024-01-{i:02d}"} for i in range(1, 31)]
-        result = smart_crusher.crush(
+        result = smart_crusher.crush(items, max_items=8, query="Show me the latest entries")
            items,
            max_items=8,
            query="Show me the latest entries"
        )
        ids = [item["id"] for item in result]
        recent_count = sum(1 for id in ids if id > 20)
@ -525,11 +503,7 @@ class TestQueryAwareAnchoring:
        """'First' in query should preserve earlier items."""
        items = [{"id": i, "created": f"2024-01-{i:02d}"} for i in range(1, 31)]
-        result = smart_crusher.crush(
+        result = smart_crusher.crush(items, max_items=8, query="Show me the first entries")
            items,
            max_items=8,
            query="Show me the first entries"
        )
        ids = [item["id"] for item in result]
        early_count = sum(1 for id in ids if id < 10)
@ -540,11 +514,7 @@ class TestQueryAwareAnchoring:
        """Query for specific ID should find it regardless of position."""
        items = [{"id": f"item_{i:04d}", "value": i} for i in range(1000)]
-        result = smart_crusher.crush(
+        result = smart_crusher.crush(items, max_items=10, query="Find item_0567")
            items,
            max_items=10,
            query="Find item_0567"
        )
        assert any(item["id"] == "item_0567" for item in result)
 ```
@ -574,8 +544,7 @@ class TestCoverageMetrics:
    def test_category_coverage(self):
        """Preserved items should represent all categories."""
        items = [
-            {"category": cat, "id": i}
+            {"category": cat, "id": i} for i, cat in enumerate(["A"] * 30 + ["B"] * 30 + ["C"] * 40)
            for i, cat in enumerate(["A"] * 30 + ["B"] * 30 + ["C"] * 40)
        ]
        result = smart_crusher.crush(items, max_items=10)
@ -608,10 +577,7 @@ class TestRetrievalSimulation:
    def test_retrieval_hit_rate_random_queries(self):
        """Measure how often preserved items satisfy random queries."""
-        items = [
+        items = [{"id": i, "name": f"Item {i}", "category": f"cat_{i % 5}"} for i in range(100)]
            {"id": i, "name": f"Item {i}", "category": f"cat_{i % 5}"}
            for i in range(100)
        ]
        compressed = smart_crusher.crush(items, max_items=15)
        compressed_ids = {item["id"] for item in compressed}
@ -636,9 +602,9 @@ class TestRetrievalSimulation:
        # Weight queries toward front (30%), back (30%), anomalies (40%)
        hits = 0
        queries = (
-            list(range(10)) * 3 +  # Front queries
+            list(range(10)) * 3  # Front queries
-            list(range(90, 100)) * 3 +  # Back queries
+            + list(range(90, 100)) * 3  # Back queries
-            [50] * 4  # Middle anomaly queries
+            + [50] * 4  # Middle anomaly queries
        )
        for target_id in queries:
@ -718,12 +684,12 @@ class AnchorConfig:
    time_series_balance: float = 0.5
    # Query keyword detection
-    recency_keywords: list[str] = field(default_factory=lambda: [
+    recency_keywords: list[str] = field(
-        "latest", "recent", "last", "newest", "current"
+        default_factory=lambda: ["latest", "recent", "last", "newest", "current"]
-    ])
+    )
-    historical_keywords: list[str] = field(default_factory=lambda: [
+    historical_keywords: list[str] = field(
-        "first", "oldest", "earliest", "original", "initial"
+        default_factory=lambda: ["first", "oldest", "earliest", "original", "initial"]
-    ])
+    )
    # Information density selection
    use_information_density: bool = True
--- a/wiki/proxy.md
+++ b/wiki/proxy.md
@ -323,13 +323,18 @@ The provider caches the bytes you *forwarded*, which compression already changed
 ```python
 forwarded = []
 def next_turn(new_messages):
-    r = requests.post(f"{proxy}/v1/compress", json={
+    r = requests.post(
-        "messages": forwarded + new_messages,
+        f"{proxy}/v1/compress",
-        "model": "claude-sonnet-4-6",
+        json={
-        "config": {"frozen_message_count": len(forwarded)},
+            "messages": forwarded + new_messages,
-    }).json()
+            "model": "claude-sonnet-4-6",
-    forwarded[:] = r["messages"]   # next turn's frozen prefix
+            "config": {"frozen_message_count": len(forwarded)},
        },
    ).json()
    forwarded[:] = r["messages"]  # next turn's frozen prefix
    return forwarded
 ```
--- a/wiki/quickstart.md
+++ b/wiki/quickstart.md
@ -149,19 +149,21 @@ messages = [
    {
        "role": "assistant",
        "content": None,
-        "tool_calls": [{
+        "tool_calls": [
-            "id": "call_1",
+            {
-            "type": "function",
+                "id": "call_1",
-            "function": {"name": "search", "arguments": '{"q": "python"}'},
+                "type": "function",
-        }],
+                "function": {"name": "search", "arguments": '{"q": "python"}'},
            }
        ],
    },
    {
        "role": "tool",
        "tool_call_id": "call_1",
        # This is where Headroom shines - compressing large outputs
-        "content": json.dumps({
+        "content": json.dumps(
-            "results": [{"title": f"Result {i}", "score": 100-i} for i in range(500)]
+            {"results": [{"title": f"Result {i}", "score": 100 - i} for i in range(500)]}
-        }),
+        ),
    },
    {"role": "user", "content": "What are the top 3 results?"},
 ]
@ -188,7 +190,9 @@ plan = client.chat.completions.simulate(
 print(f"Tokens before: {plan.tokens_before}")
 print(f"Tokens after: {plan.tokens_after}")
-print(f"Would save: {plan.tokens_saved} tokens ({plan.tokens_saved/plan.tokens_before*100:.0f}%)")
+print(
    f"Would save: {plan.tokens_saved} tokens ({plan.tokens_saved / plan.tokens_before * 100:.0f}%)"
 )
 print(f"Transforms: {plan.transforms}")
 print(f"Estimated savings: {plan.estimated_savings}")
 ```
@ -227,6 +231,7 @@ print(response.content[0].text)
 ```python
 import logging
 logging.basicConfig(level=logging.INFO)
 # Now you'll see:
@ -347,6 +352,7 @@ print(stats["config"]["mode"])  # Should be "optimize"
 # 2. Enable logging to see what's happening
 import logging
 logging.basicConfig(level=logging.DEBUG)
 ```
--- a/wiki/sdk.md
+++ b/wiki/sdk.md
@ -45,30 +45,26 @@ messages = [
    {
        "role": "assistant",
        "content": None,
-        "tool_calls": [{
+        "tool_calls": [
-            "id": "call_123",
+            {
-            "type": "function",
+                "id": "call_123",
-            "function": {"name": "search", "arguments": '{"q": "python"}'},
+                "type": "function",
-        }],
+                "function": {"name": "search", "arguments": '{"q": "python"}'},
            }
        ],
    },
    {
        "role": "tool",
        "tool_call_id": "call_123",
-        "content": json.dumps({
+        "content": json.dumps(
-            "results": [
+            {"results": [{"title": f"Tutorial {i}", "score": 100 - i} for i in range(500)]}
-                {"title": f"Tutorial {i}", "score": 100-i}
+        ),
                for i in range(500)
            ]
        }),
    },
    {"role": "user", "content": "What are the top 3?"},
 ]
 # Headroom compresses 500 results to ~15, keeping highest-scoring items
-response = client.chat.completions.create(
+response = client.chat.completions.create(model="gpt-4o-mini", messages=messages)
    model="gpt-4o-mini",
    messages=messages
 )
 # Check savings
 stats = client.get_stats()
@ -187,13 +183,10 @@ print(f"Transforms: {plan.transforms}")
 response = client.chat.completions.create(
    model="gpt-4o",
    messages=[...],
    # Override mode for this request
    headroom_mode="audit",
    # Reserve more tokens for output
    headroom_output_buffer_tokens=8000,
    # Keep last N turns
    headroom_keep_turns=5,
 )
@ -203,6 +196,7 @@ response = client.chat.completions.create(
 ```python
 import logging
 logging.basicConfig(level=logging.INFO)
 # Now you'll see:
--- a/wiki/shared-context.md
+++ b/wiki/shared-context.md
@ -28,10 +28,10 @@ Store content under a key. Compresses automatically using Headroom's full pipeli
 ```python
 entry = ctx.put("findings", big_json_output, agent="researcher")
-entry.original_tokens     # 20,000
+entry.original_tokens  # 20,000
-entry.compressed_tokens   # 4,000
+entry.compressed_tokens  # 4,000
-entry.savings_percent     # 80.0
+entry.savings_percent  # 80.0
-entry.transforms          # ["router:json:0.20"]
+entry.transforms  # ["router:json:0.20"]
 ```
 ### `get(key, *, full=False)`
@ -39,9 +39,9 @@ entry.transforms          # ["router:json:0.20"]
 Retrieve content. Returns compressed version by default, original with `full=True`.
 ```python
-compressed = ctx.get("findings")           # 4K tokens
+compressed = ctx.get("findings")  # 4K tokens
 original = ctx.get("findings", full=True)  # 20K tokens
-missing = ctx.get("nonexistent")           # None
+missing = ctx.get("nonexistent")  # None
 ```
 ### `get_entry(key)`
@ -50,13 +50,13 @@ Get the full `ContextEntry` with metadata.
 ```python
 entry = ctx.get_entry("findings")
-entry.key                # "findings"
+entry.key  # "findings"
-entry.agent              # "researcher"
+entry.agent  # "researcher"
-entry.original_tokens    # 20000
+entry.original_tokens  # 20000
 entry.compressed_tokens  # 4000
-entry.savings_percent    # 80.0
+entry.savings_percent  # 80.0
-entry.timestamp          # 1710000000.0
+entry.timestamp  # 1710000000.0
-entry.transforms         # ["router:json:0.20"]
+entry.transforms  # ["router:json:0.20"]
 ```
 ### `keys()`
@ -69,11 +69,11 @@ Aggregated stats across all entries.
 ```python
 stats = ctx.stats()
-stats.entries                  # 3
+stats.entries  # 3
-stats.total_original_tokens    # 60000
+stats.total_original_tokens  # 60000
 stats.total_compressed_tokens  # 12000
-stats.total_tokens_saved       # 48000
+stats.total_tokens_saved  # 48000
-stats.savings_percent          # 80.0
+stats.savings_percent  # 80.0
 ```
 ### `clear()`
@ -85,8 +85,8 @@ Remove all entries.
 ```python
 ctx = SharedContext(
    model="claude-sonnet-4-5-20250929",  # For token counting
-    ttl=3600,                             # 1 hour (default)
+    ttl=3600,  # 1 hour (default)
-    max_entries=100,                       # Evicts oldest when full
+    max_entries=100,  # Evicts oldest when full
 )
 ```
@ -113,11 +113,13 @@ from headroom import SharedContext
 ctx = SharedContext()
 def researcher_node(state):
    result = do_research()
    ctx.put("research", result)
    return {"research_summary": ctx.get("research")}
 def coder_node(state):
    # Compressed summary in state, full details on demand
    full = ctx.get("research", full=True)
@ -131,6 +133,7 @@ from headroom import SharedContext
 ctx = SharedContext()
 def compress_handoff(messages):
    for msg in messages:
        if len(msg.content) > 1000:
@ -138,6 +141,7 @@ def compress_handoff(messages):
            msg.content = ctx.get(msg.id)
    return messages
 handoff(agent=coder, input_filter=compress_handoff)
 ```
--- a/wiki/strands.md
+++ b/wiki/strands.md
@ -114,11 +114,13 @@ HeadroomStrandsModel supports Strands' structured output feature:
 ```python
 from pydantic import BaseModel
 class Analysis(BaseModel):
    severity: str
    root_cause: str
    recommendation: str
 result = optimized.structured_output(Analysis, messages)
 ```
--- a/wiki/text-compression.md
+++ b/wiki/text-compression.md
@ -136,10 +136,14 @@ elif detection.content_type == ContentType.PLAIN_TEXT:
 ```python
 from headroom.transforms import (
-    detect_content_type, ContentType,
+    detect_content_type,
-    SearchCompressor, LogCompressor, TextCompressor
+    ContentType,
    SearchCompressor,
    LogCompressor,
    TextCompressor,
 )
 def compress_tool_output(content: str, context: str = "") -> str:
    """Application-level compression with explicit control."""
    detection = detect_content_type(content)
@ -166,7 +170,7 @@ Each compressor accepts configuration options:
 from headroom.transforms import SearchCompressor, SearchCompressorConfig
 config = SearchCompressorConfig(
-    max_results=50,           # Keep up to 50 matches
+    max_results=50,  # Keep up to 50 matches
    preserve_file_diversity=True,  # Ensure different files represented
    relevance_threshold=0.3,  # Minimum relevance score to keep
 )
--- a/wiki/transforms.md
+++ b/wiki/transforms.md
@ -22,13 +22,13 @@ SmartCrusher analyzes JSON arrays and selectively keeps important items:
 from headroom import SmartCrusherConfig
 config = SmartCrusherConfig(
-    min_tokens_to_crush=200,      # Only compress if > 200 tokens
+    min_tokens_to_crush=200,  # Only compress if > 200 tokens
-    max_items_after_crush=50,     # Keep at most 50 items
+    max_items_after_crush=50,  # Keep at most 50 items
-    keep_first=3,                 # Always keep first 3 items
+    keep_first=3,  # Always keep first 3 items
-    keep_last=2,                  # Always keep last 2 items
+    keep_last=2,  # Always keep last 2 items
-    relevance_threshold=0.3,      # Keep items with relevance > 0.3
+    relevance_threshold=0.3,  # Keep items with relevance > 0.3
-    anomaly_std_threshold=2.0,    # Keep items > 2 std dev from mean
+    anomaly_std_threshold=2.0,  # Keep items > 2 std dev from mean
-    preserve_errors=True,         # Always keep error items
+    preserve_errors=True,  # Always keep error items
 )
 ```
@ -94,9 +94,9 @@ result = aligner.align(messages)
 from headroom import CacheAlignerConfig
 config = CacheAlignerConfig(
-    extract_dates=True,           # Move dates to dynamic section
+    extract_dates=True,  # Move dates to dynamic section
-    normalize_whitespace=True,    # Consistent spacing
+    normalize_whitespace=True,  # Consistent spacing
-    stable_prefix_min_tokens=100, # Min prefix size for alignment
+    stable_prefix_min_tokens=100,  # Min prefix size for alignment
 )
 ```
@ -170,16 +170,16 @@ pip install "headroom-ai[code]"  # Adds tree-sitter-language-pack
 from headroom.transforms import CodeAwareCompressor, CodeCompressorConfig, DocstringMode
 config = CodeCompressorConfig(
-    preserve_imports=True,              # Always keep imports
+    preserve_imports=True,  # Always keep imports
-    preserve_signatures=True,           # Always keep function signatures
+    preserve_signatures=True,  # Always keep function signatures
-    preserve_type_annotations=True,     # Keep type hints
+    preserve_type_annotations=True,  # Keep type hints
-    preserve_error_handlers=True,       # Keep try/except blocks
+    preserve_error_handlers=True,  # Keep try/except blocks
-    preserve_decorators=True,           # Keep decorators
+    preserve_decorators=True,  # Keep decorators
    docstring_mode=DocstringMode.FIRST_LINE,  # FULL, FIRST_LINE, REMOVE
-    target_compression_rate=0.2,        # Keep 20% of tokens
+    target_compression_rate=0.2,  # Keep 20% of tokens
-    max_body_lines=5,                   # Lines to keep per function body
+    max_body_lines=5,  # Lines to keep per function body
-    min_tokens_for_compression=100,     # Skip small content
+    min_tokens_for_compression=100,  # Skip small content
-    language_hint=None,                 # Auto-detect if None
+    language_hint=None,  # Auto-detect if None
 )
 compressor = CodeAwareCompressor(config)
@ -263,10 +263,10 @@ ContentRouter analyzes content and selects the best compression strategy:
 from headroom.transforms import ContentRouter, ContentRouterConfig, CompressionStrategy
 config = ContentRouterConfig(
-    min_section_tokens=100,             # Minimum tokens to compress
+    min_section_tokens=100,  # Minimum tokens to compress
-    enable_code_aware=True,             # Use CodeAwareCompressor for code
+    enable_code_aware=True,  # Use CodeAwareCompressor for code
-    enable_search_compression=True,     # Use SearchCompressor for grep output
+    enable_search_compression=True,  # Use SearchCompressor for grep output
-    enable_log_compression=True,        # Use LogCompressor for logs
+    enable_log_compression=True,  # Use LogCompressor for logs
    default_strategy=CompressionStrategy.TEXT,  # Fallback strategy
 )
@ -331,10 +331,12 @@ Combine transforms for optimal results.
 ```python
 from headroom import TransformPipeline, SmartCrusher, CacheAligner
-pipeline = TransformPipeline([
+pipeline = TransformPipeline(
-    SmartCrusher(),      # First: compress tool outputs
+    [
-    CacheAligner(),      # Then: stabilize prefix
+        SmartCrusher(),  # First: compress tool outputs
-])
+        CacheAligner(),  # Then: stabilize prefix
    ]
 )
 result = pipeline.transform(messages)
 print(f"Saved {result.tokens_saved} tokens")
--- a/wiki/troubleshooting.md
+++ b/wiki/troubleshooting.md
@ -224,6 +224,7 @@ client = HeadroomClient(
 # 2. For temp directory storage
 import tempfile
 import os
 db_path = os.path.join(tempfile.gettempdir(), "headroom.db")
 client = HeadroomClient(
    original_client=OpenAI(),
@ -287,6 +288,7 @@ pip install --upgrade headroom-ai
 ```python
 # Check available imports
 import headroom
 print(dir(headroom))
 # Common imports:
@ -397,6 +399,7 @@ print(f"Waste signals: {plan.waste_signals}")
 # See the actual optimized messages
 import json
 print(json.dumps(plan.messages_optimized, indent=2))
 ```