Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / openenv /pr_1321 /en /environments /thinkingbox.html
HuggingFaceDocBuilder's picture
HuggingFaceDocBuilder
download
raw
29 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;ThinkingBox&quot;,&quot;local&quot;:&quot;thinkingbox&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Introduction&quot;,&quot;local&quot;:&quot;introduction&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Quick Start&quot;,&quot;local&quot;:&quot;quick-start&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Examples&quot;,&quot;local&quot;:&quot;examples&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Environment Details&quot;,&quot;local&quot;:&quot;environment-details&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Configuration&quot;,&quot;local&quot;:&quot;configuration&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Deployment Boundary&quot;,&quot;local&quot;:&quot;deployment-boundary&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Citation&quot;,&quot;local&quot;:&quot;citation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
<link href="/docs/openenv/main/en/_app/immutable/entry/start.DV-RUl-a.js" rel="modulepreload">
<link href="/docs/openenv/main/en/_app/immutable/chunks/vYvlmaea.js" rel="modulepreload">
<link href="/docs/openenv/main/en/_app/immutable/chunks/BSuxAqoA.js" rel="modulepreload">
<link href="/docs/openenv/main/en/_app/immutable/entry/app.DV37A4P_.js" rel="modulepreload">
<link href="/docs/openenv/main/en/_app/immutable/chunks/Ds_1Ru_R.js" rel="modulepreload">
<link href="/docs/openenv/main/en/_app/immutable/chunks/Cs50_Xpk.js" rel="modulepreload">
<link href="/docs/openenv/main/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
<link href="/docs/openenv/main/en/_app/immutable/chunks/BAUKCucN.js" rel="modulepreload">
<link href="/docs/openenv/main/en/_app/immutable/nodes/0.0hnUFZHb.js" rel="modulepreload">
<link href="/docs/openenv/main/en/_app/immutable/chunks/CR5HsSXT.js" rel="modulepreload">
<link href="/docs/openenv/main/en/_app/immutable/nodes/40.D2OgAHwh.js" rel="modulepreload">
<link href="/docs/openenv/main/en/_app/immutable/chunks/C07d6Hje.js" rel="modulepreload">
<!--90qlm5--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;ThinkingBox&quot;,&quot;local&quot;:&quot;thinkingbox&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Introduction&quot;,&quot;local&quot;:&quot;introduction&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Quick Start&quot;,&quot;local&quot;:&quot;quick-start&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Examples&quot;,&quot;local&quot;:&quot;examples&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Environment Details&quot;,&quot;local&quot;:&quot;environment-details&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Configuration&quot;,&quot;local&quot;:&quot;configuration&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Deployment Boundary&quot;,&quot;local&quot;:&quot;deployment-boundary&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Citation&quot;,&quot;local&quot;:&quot;citation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
<link href="/docs/openenv/main/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg><!----></button></div> <!--[-1--><!--]--></div><!----> <!--[0--><h1 class="relative group"><a id="thinkingbox" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#thinkingbox"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span>ThinkingBox</span></h1><!--]--><!----> <!--[1--><h2 class="relative group"><a id="introduction" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#introduction"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span>Introduction</span></h2><!--]--><!----> <p><a href="https://github.com/microsoft/thinkingbox" rel="nofollow">ThinkingBox</a> is an agentic harness for
defining isolated MCP tool environments, creating stateful scenarios and test
cases, running an LLM agent with simulated-user interaction, and evaluating
the resulting backend state, side effects, and response requirements. It can
support offline evaluation or conversation generation and agentic training
workflows.</p> <p>This OpenEnv adapter exposes the public <a href="https://arxiv.org/abs/2608.19741" rel="nofollow">ThinkingBox-Bench</a> through the standard
WebSocket reset/step interface. The adapter is currently designed for
evaluation only. Canonical coverage uses the pinned public benchmark release;
user-supplied ThinkingBox scenarios can also be evaluated when their executable
data and external services are provided, but those runs are not canonical
ThinkingBox-Bench results.</p> <!--[1--><h2 class="relative group"><a id="quick-start" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#quick-start"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span>Quick Start</span></h2><!--]--><!----> <p>Start the externally managed ThinkingBox services described under <a href="#deployment-boundary">Deployment Boundary</a>, then run the OpenEnv server:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-bash "><!---->OPENENV_TB_CONFIG=/path/to/thinkingbox.yaml \
uv run --project envs/thinkingbox_env --frozen server<!----></pre></div><!----> <p>Connect from a trusted harness:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-python "><!----><span class="hljs-keyword">from</span> thinkingbox_env <span class="hljs-keyword">import</span> ThinkingBoxEnv
<span class="hljs-keyword">async</span> <span class="hljs-keyword">with</span> ThinkingBoxEnv(base_url=<span class="hljs-string">&quot;http://127.0.0.1:8000&quot;</span>) <span class="hljs-keyword">as</span> env:
result = <span class="hljs-keyword">await</span> env.reset(<span class="hljs-string">&quot;file.py:test_name&quot;</span>)
tools = <span class="hljs-keyword">await</span> env.list_tools()
result = <span class="hljs-keyword">await</span> env.call_tool(<span class="hljs-string">&quot;tool_name&quot;</span>, {<span class="hljs-string">&quot;argument&quot;</span>: <span class="hljs-string">&quot;value&quot;</span>})
result = <span class="hljs-keyword">await</span> env.submit_message(<span class="hljs-string">&quot;Final response&quot;</span>)<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="examples" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#examples"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span>Examples</span></h2><!--]--><!----> <ul><li><a href="https://github.com/huggingface/OpenEnv/blob/main/examples/thinkingbox/example_usage.py" rel="nofollow">Public client example</a>:
reset a server-visible task and inspect its public task and tool observations
without loading benchmark implementation data on the client.</li> <li><a href="https://github.com/huggingface/OpenEnv/blob/main/examples/thinkingbox/eval_testlist.py" rel="nofollow">Evaluation wrapper</a>:
invoke the packaged <code>thinkingbox-eval</code> CLI for native model orchestration,
repetition IDs, privacy-reviewed canonical JSONL, and strict aggregation.</li></ul> <p>Run either script from the repository root:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-bash "><!---->uv run --project envs/thinkingbox_env \
python examples/thinkingbox/example_usage.py file.py:test_name
uv run --project envs/thinkingbox_env \
python examples/thinkingbox/eval_testlist.py \
--config /path/to/thinkingbox.yaml \
--output results.jsonl<!----></pre></div><!----> <p>The evaluator’s <code>--config</code> and <code>--dataset</code> paths are local to the trusted
evaluator. For a remote OpenEnv server, pass the corresponding server-visible
paths with <code>--env-config</code> and <code>--env-dataset</code>. Strict <code>canary</code> and <code>full</code> coverage profiles accept only the pinned public benchmark; custom scenario
bundles use ordinary non-profiled evaluation.</p> <!--[1--><h2 class="relative group"><a id="environment-details" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#environment-details"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span>Environment Details</span></h2><!--]--><!----> <p>The adapter preserves native ThinkingBox hydration, history replay, tool
overrides, parallel tool batches, direct responses, simulated users, effects,
fixtures, <code>TestContext</code>, <code>TestScript</code>, <code>Judge</code>, error latching, and teardown.
Final rewards are binary pass/fail; infrastructure failures are reported
separately and never converted into benchmark failures.</p> <p>The model-facing action surface contains tool discovery, tool calls, and
assistant messages. A trusted harness may call <code>finish()</code>, but finish is not
advertised in the public action schema. Private user context, initialization
state, assertion source, credentials, proxy session identifiers, effects, and
grading internals remain inside the environment.</p> <p><code>seed</code> is accepted for OpenEnv API compatibility but intentionally unused
because tasks are selected deterministically by UID. Concurrent sessions are
stacked independent environment instances, one trajectory per instance; they
are not multiplexed trajectories.</p> <p>Executable assets come from the pinned <code>thinkingbox-bench-v1.0</code> release in <a href="https://github.com/microsoft/thinkingbox-data" rel="nofollow"><code>microsoft/thinkingbox-data</code></a>.
The <a href="https://huggingface.co/datasets/microsoft/ThinkingBox-Bench" rel="nofollow">Hugging Face <code>microsoft/ThinkingBox-Bench</code> dataset</a> is a
viewer-friendly representation, while GitHub remains the executable source.</p> <!--[1--><h2 class="relative group"><a id="configuration" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#configuration"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span>Configuration</span></h2><!--]--><!----> <p>The server accepts an ordinary native ThinkingBox YAML configuration through <code>OPENENV_TB_CONFIG</code> or the reset <code>config=</code> argument. The file supplies <code>mcp_proxy</code>, <code>orchestrator.agent_model</code>, <code>user_model</code>, <code>judge_model</code>, <code>judge_type</code>, and user-completion behavior; see the <a href="https://github.com/microsoft/thinkingbox/blob/main/docs/llm_endpoint_config.md" rel="nofollow">ThinkingBox LLM configuration
guide</a>.</p> <table><thead><tr><th>Variable</th><th>Default</th><th>Purpose</th></tr></thead><tbody><tr><td><code>OPENENV_TB_PROXY_URL</code></td><td><code>http://127.0.0.1:7111</code></td><td>Session Proxy fallback</td></tr><tr><td><code>OPENENV_TB_DATASET</code></td><td>pinned release</td><td>Local executable-data override</td></tr><tr><td><code>OPENENV_TB_DATA_CACHE</code></td><td><code>~/.cache/openenv/thinkingbox_bench</code></td><td>Verified release cache</td></tr><tr><td><code>OPENENV_TB_AGENT</code></td><td><code>think</code></td><td>Native agent definition</td></tr><tr><td><code>OPENENV_TB_CONFIG</code></td><td>unset</td><td>Native server-side model/proxy config</td></tr><tr><td><code>OPENENV_TB_PROXY_TIMEOUT</code></td><td><code>120</code></td><td>Proxy timeout without config override</td></tr><tr><td><code>OPENENV_TB_DATA_TIMEOUT</code></td><td><code>120</code></td><td>Release download timeout</td></tr><tr><td><code>OPENENV_TB_MAX_CONCURRENT_ENVS</code></td><td><code>8</code></td><td>Independent environment instances</td></tr></tbody></table> <p>The client message timeout remains longer than server-side model and episode
operations so a valid long-running turn is not abandoned prematurely.</p> <!--[1--><h2 class="relative group"><a id="deployment-boundary" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#deployment-boundary"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span>Deployment Boundary</span></h2><!--]--><!----> <p>The image starts only the OpenEnv API. It currently needs an externally
managed ThinkingBox Session Proxy, benchmark MCP servers, Typesense, and agent,
user-simulator, and judge model endpoints. <code>GET /health</code> reports process
liveness; <code>GET /ready</code> reports the observable external dependencies and marks
scenario-specific Typesense readiness as unobservable from this process.</p> <!--[1--><h2 class="relative group"><a id="citation" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#citation"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span>Citation</span></h2><!--]--><!----> <p>Please cite the paper if ThinkingBox is useful in your experiments.</p> <ul><li>Paper: <a href="https://arxiv.org/abs/2608.19741" rel="nofollow">One Success Isn’t Reliability: Thinkingbox, a Sandbox and Benchmark
for Agents in Stateful Business Workflows</a></li> <li>Framework: <a href="https://github.com/microsoft/thinkingbox" rel="nofollow"><code>microsoft/thinkingbox</code></a></li> <li>Executable benchmark: <a href="https://github.com/microsoft/thinkingbox-data" rel="nofollow"><code>microsoft/thinkingbox-data</code></a></li> <li>Viewer dataset: <a href="https://huggingface.co/datasets/microsoft/ThinkingBox-Bench" rel="nofollow"><code>microsoft/ThinkingBox-Bench</code></a></li></ul> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-bibtex "><!---->@misc{li2026successisntreliabilitythinkingbox,
title={One Success Isn&#x27;t Reliability: Thinkingbox, a Sandbox<span class="hljs-built_in"> and </span>Benchmark for Agents in Stateful Business Workflows},
author={Zhuochun Li<span class="hljs-built_in"> and </span>Youngmin Ko<span class="hljs-built_in"> and </span>Ali Keramati<span class="hljs-built_in"> and </span>Nicola Ferri<span class="hljs-built_in"> and </span>Susana Palmaz Lopez Pelaez<span class="hljs-built_in"> and </span>Liang-Chun Tsai<span class="hljs-built_in"> and </span>Calvin Wang<span class="hljs-built_in"> and </span>Mirco Milletari<span class="hljs-built_in"> and </span>Tuhin Kundu<span class="hljs-built_in"> and </span>Vadim Smolyakov<span class="hljs-built_in"> and </span>Kjartan Olafsson<span class="hljs-built_in"> and </span>Tommy Guy},
year={2026},
eprint={2608.19741},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2608.19741},
}<!----></pre></div><!----> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/openenv/blob/main/docs/source/environments/thinkingbox.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg><!----> <span><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
<script>
{
__sveltekit_1aprp76 = {
base: "/docs/openenv/main/en",
assets: "/docs/openenv/main/en"
};
const element = document.currentScript.parentElement;
Promise.all([
import("/docs/openenv/main/en/_app/immutable/entry/start.DV-RUl-a.js"),
import("/docs/openenv/main/en/_app/immutable/entry/app.DV37A4P_.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 40],
data: [null,null],
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
29 kB
·
Xet hash:
1915ca9c17baa165fc2445f47f5925fcaaa5b95ef10916365c997c1a1341761a

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.