feat(cccl): integrate missing CCCL directories — python/, ci/, .agent/, docs/, test/

Sparse-checkout from NVIDIA/cccl main branch to complete cccl_upstream:

Added:
- python/cuda_cccl/ (226 files) — Python bindings for device-level algorithms
  Critical for muh toolchain: cuda.compute.reduce_into, scan, radix_sort, etc.
  Includes 204 .py files with full test coverage for all 27 algorithms
- ci/ (163 files) — Build/test infrastructure
  build_cub.sh, test_cub.sh, build_and_test_targets.sh, matrix.yaml
  Directly maps to our [INFRA-CI] and [INFRA-BUILD] items
- .agent/skills/ (7 files) — NVIDIA's own agent skills for CCCL
  cccl-style/SKILL.md, cccl-test/SKILL.md, sass-diff/SKILL.md
- docs/ (491 files) — Official CCCL documentation
  CI references, CMake guides, Python compute docs, libcudacxx PTX docs
- test/ (12 files) — Top-level integration tests (cuda_smoke, stdpar)
- Root configs: .clang-format, .clang-tidy, CONTRIBUTING.md, pyproject.toml
- CLAUDE.md symlink → AGENTS.md (NVIDIA's standard)

cccl_upstream now mirrors full NVIDIA/cccl structure:
  Before: 42M (cub + thrust + libcudacxx + cudax + c + examples + benchmarks)
  After:  53M (+python +ci +docs +.agent +test +configs)

This completes the CCCL base needed for:
- [muh-bench] items: ci/util/build_and_test_targets.sh for targeted builds
- [CCCL-verify] items: python/cuda_cccl/tests/ as reference implementations
- [CCCL-test] items: ci/test_cub.sh, ci/test_thrust.sh
- Agent workflow: .agent/skills/ for consistent style and test patterns

cccl_upstream/docs/cudax/stf/images/dag-sections-0.dot

@@ -0,0 +1,5 @@
+digraph {
+"NODE_23" [style="filled" fillcolor="red" label="task fence"]
+"NODE_3" -> "NODE_23"
+"NODE_3" [style="filled" fillcolor="white" label="foo"]
+}

cccl_upstream/docs/cudax/stf/images/dag-sections-1.dot

@@ -0,0 +1,14 @@
+digraph {
+"NODE_23" [style="filled" fillcolor="red" label="task fence"]
+subgraph cluster_section_1 {
+     color=black;
+    style=dashed
+    label="foo"
+    "NODE_13"
+    "NODE_3"
+} // end subgraph cluster_section_1
+ "NODE_13" -> "NODE_23"
+"NODE_3" -> "NODE_13"
+"NODE_13" [style="filled" fillcolor="white" label="bar"]
+"NODE_3" [style="filled" fillcolor="white" label="bar"]
+}

cccl_upstream/docs/cudax/stf/images/dag-sections-2.dot

@@ -0,0 +1,36 @@
+digraph {
+"NODE_23" [style="filled" fillcolor="red" label="task fence"]
+subgraph cluster_section_1 {
+ subgraph cluster_section_2 {
+     color=black;
+    style=dashed
+    label="bar"
+    "NODE_9"
+    "NODE_5"
+    "NODE_3"
+} // end subgraph cluster_section_2
+ subgraph cluster_section_5 {
+     color=black;
+    style=dashed
+    label="bar"
+    "NODE_19"
+    "NODE_15"
+    "NODE_13"
+} // end subgraph cluster_section_5
+     color=black;
+    style=dashed
+    label="foo"
+} // end subgraph cluster_section_1
+ "NODE_19" -> "NODE_23"
+"NODE_3" -> "NODE_5"
+"NODE_5" -> "NODE_9"
+"NODE_15" -> "NODE_19"
+"NODE_9" -> "NODE_13"
+"NODE_13" -> "NODE_15"
+"NODE_19" [style="filled" fillcolor="white" label="baz"]
+"NODE_15" [style="filled" fillcolor="white" label="baz"]
+"NODE_13" [style="filled" fillcolor="white" label="t1\nA(read)(0) \nB(rw)(0) "]
+"NODE_9" [style="filled" fillcolor="white" label="baz"]
+"NODE_5" [style="filled" fillcolor="white" label="baz"]
+"NODE_3" [style="filled" fillcolor="white" label="t1\nA(read)(0) \nB(rw)(0) "]
+}

cccl_upstream/docs/cudax/stf/images/dag-sections.dot

@@ -0,0 +1,69 @@
+digraph {
+"NODE_23" [style="filled" fillcolor="red" label="task fence"]
+subgraph cluster_section_1 {
+ subgraph cluster_section_2 {
+ subgraph cluster_section_3 {
+     color=black;
+    style=dashed
+    label="baz"
+    "NODE_7"
+    "NODE_5"
+} // end subgraph cluster_section_3
+ subgraph cluster_section_4 {
+     color=black;
+    style=dashed
+    label="baz"
+    "NODE_11"
+    "NODE_9"
+} // end subgraph cluster_section_4
+     color=black;
+    style=dashed
+    label="bar"
+    "NODE_3"
+} // end subgraph cluster_section_2
+ subgraph cluster_section_5 {
+ subgraph cluster_section_6 {
+     color=black;
+    style=dashed
+    label="baz"
+    "NODE_17"
+    "NODE_15"
+} // end subgraph cluster_section_6
+ subgraph cluster_section_7 {
+     color=black;
+    style=dashed
+    label="baz"
+    "NODE_21"
+    "NODE_19"
+} // end subgraph cluster_section_7
+     color=black;
+    style=dashed
+    label="bar"
+    "NODE_13"
+} // end subgraph cluster_section_5
+     color=black;
+    style=dashed
+    label="foo"
+} // end subgraph cluster_section_1
+ "NODE_15" -> "NODE_17"
+"NODE_9" -> "NODE_11"
+"NODE_11" -> "NODE_15"
+"NODE_13" -> "NODE_17"
+"NODE_19" -> "NODE_21"
+"NODE_11" -> "NODE_13"
+"NODE_7" -> "NODE_9"
+"NODE_5" -> "NODE_7"
+"NODE_17" -> "NODE_19"
+"NODE_3" -> "NODE_7"
+"NODE_21" -> "NODE_23"
+"NODE_21" [style="filled" fillcolor="white" label="t3\nA(rw)(0) \nB(read)(0) \nC(read)(0) "]
+"NODE_19" [style="filled" fillcolor="white" label="t2\nA(read)(0) \nC(rw)(0) "]
+"NODE_17" [style="filled" fillcolor="white" label="t3\nA(rw)(0) \nB(read)(0) \nC(read)(0) "]
+"NODE_15" [style="filled" fillcolor="white" label="t2\nA(read)(0) \nC(rw)(0) "]
+"NODE_13" [style="filled" fillcolor="white" label="t1\nA(read)(0) \nB(rw)(0) "]
+"NODE_11" [style="filled" fillcolor="white" label="t3\nA(rw)(0) \nB(read)(0) \nC(read)(0) "]
+"NODE_9" [style="filled" fillcolor="white" label="t2\nA(read)(0) \nC(rw)(0) "]
+"NODE_7" [style="filled" fillcolor="white" label="t3\nA(rw)(0) \nB(read)(0) \nC(read)(0) "]
+"NODE_5" [style="filled" fillcolor="white" label="t2\nA(read)(0) \nC(rw)(0) "]
+"NODE_3" [style="filled" fillcolor="white" label="t1\nA(read)(0) \nB(rw)(0) "]
+}

cccl_upstream/docs/cudax/stf/images/graph_01.dot

@@ -0,0 +1,10 @@
+digraph {
+    T_1 [label="T1\nX(rw)"];
+    T_2 [label="T2\nX(read)\nY(rw)"];
+    T_3 [label="T3\nX(read)\nZ(rw)"];
+    T_4 [label="T4\nY(read)\nZ(rw)"];
+    T_1 -> T_2;
+    T_1 -> T_3;
+    T_2 -> T_4;
+    T_3 -> T_4;
+}

cccl_upstream/docs/cudax/stf/images/graph_02.dot

@@ -0,0 +1,16 @@
+digraph {
+    subgraph cluster_0 {
+      label="device 0";
+      T_1 [label="T_1(A^W)"];
+      T_2 [label="T_2(A^R, B^W)"];
+    }
+    subgraph cluster_1 {
+      label="device 1";
+      T_3 [label="T_3(A^R, C^W)"];
+      T_4 [label="T_4(B^R, C^R, D^W)"];
+    }
+    T_1 -> T_2 [label="A"];
+    T_1 -> T_3 [label="A"];
+    T_2 -> T_4 [label="B"];
+    T_3 -> T_4 [label ="C"];
+}

cccl_upstream/docs/cudax/stf/images/task-sequence-user.dot

@@ -0,0 +1,26 @@
+digraph {
+    compound=true;
+    subgraph cluster_0 {
+      label="T1";
+      K1 [label="K1"];
+      K2 [label="K2"];
+    }
+    subgraph cluster_1 {
+      label="T2";
+      K3 [label="K3"];
+    }
+    subgraph cluster_2 {
+      label="T3";
+      K4 [label="K4"];
+    }
+    subgraph cluster_3 {
+      label="T4";
+      cb [label="callback"];
+    }
+
+    K1 -> K2;
+    K2 -> K3 [ltail=cluster_0,lhead=cluster_1,minlen=2];
+    K2 -> K4 [ltail=cluster_0,lhead=cluster_2,minlen=2];
+    K3 -> cb [ltail=cluster_1,lhead=cluster_3,minlen=2];
+    K4 -> cb [ltail=cluster_2,lhead=cluster_3,minlen=2];
+}

cccl_upstream/docs/cudax/stf/images/task-sequence.dot

@@ -0,0 +1,68 @@
+digraph {
+    compound=true;
+    subgraph cluster_00 {
+      label="";
+      AA [label="Allocate A"];
+    }
+
+    subgraph cluster_01 {
+      label="";
+      CA [label="Copy A H->D"];
+    }
+
+    subgraph cluster_10 {
+      label="";
+      AB [label="Allocate B"];
+    }
+
+    subgraph cluster_11 {
+      label="";
+      CB [label="Copy B H->D"];
+    }
+
+    subgraph cluster_0 {
+      label="T1";
+      K1 [label="K1"];
+      K2 [label="K2"];
+    }
+
+    CA -> K1 [ltail=cluster_01,lhead=cluster_0,minlen=2];
+    AA -> CA [ltail=cluster_00,lhead=cluster_01,minlen=2];
+
+    CB -> K1 [ltail=cluster_11,lhead=cluster_0,minlen=2];
+    AB -> CB [ltail=cluster_10,lhead=cluster_11,minlen=2];
+
+    subgraph cluster_1 {
+      label="T2";
+      K3 [label="K3"];
+    }
+    subgraph cluster_2 {
+      label="T3";
+      K4 [label="K4"];
+    }
+
+    K1 -> K2;
+    K2 -> K3 [ltail=cluster_0,lhead=cluster_1,minlen=2];
+    K2 -> K4 [ltail=cluster_0,lhead=cluster_2,minlen=2];
+
+    subgraph cluster_02 {
+      label="";
+      CA2 [label="Copy A D->A"];
+    }
+
+    subgraph cluster_12 {
+      label="";
+      CB2 [label="Copy B D->A"];
+    }
+
+    subgraph cluster_3 {
+      label="T4";
+      cb [label="callback"];
+    }
+
+    K3 -> CA2 [ltail=cluster_1,lhead=cluster_02,minlen=2];
+    K4 -> CB2 [ltail=cluster_2,lhead=cluster_12,minlen=2];
+
+    CA2 -> cb [ltail=cluster_02,lhead=cluster_3,minlen=2]
+    CB2 -> cb [ltail=cluster_12,lhead=cluster_3,minlen=2]
+}