feat: US-016 - Starter tasks: Category G cross-org discovery (2 tasks)

Added 2 tasks for ccb_mcp_crossorg suite using multi-org-go fixture:

CCX-crossorg-061 (G61 — cross-org interface impl):
- Find all explicit storage.Interface implementations via `var _ storage.Interface`
- Oracle: store struct (kubernetes/kubernetes) + Storage struct (grafana/grafana)
- Exercises cross-org discovery: baseline finds kubernetes org only,
  MCP-Full needed to discover grafana org implementation

CCX-crossorg-066 (G66 — authoritative repo identification):
- Find authoritative source for go.etcd.io/etcd/client/v3 Go module
- Oracle: keyword_presence (module declaration) + provenance (etcd-io/etcd, client/v3/go.mod)
- Natural decoy: kubernetes/kubernetes vendors it locally, agent must distinguish

Both tasks: 8 files each, VALID gate (gold=1.0, empty=0.0).
Selection file updated to 10 tasks total.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: sjarmak

benchmarks/ccb_mcp_crossorg/ccx-crossorg-061/environment/Dockerfile

@@ -0,0 +1,27 @@
+FROM ubuntu:22.04
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Base tools
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    git \
+    ca-certificates \
+    curl \
+    python3 \
+    golang-go \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /workspace
+
+# Clone local checkout repos (baseline config: agent has local access to these)
+RUN git clone --depth 1 --branch v1.32.0 https://github.com/kubernetes/kubernetes /workspace/kubernetes
+
+# Initialize git identity for agent commits
+RUN git config --global user.email "agent@example.com" && \
+    git config --global user.name "Agent" && \
+    git config --global safe.directory '*'
+
+# Create log directories
+RUN mkdir -p /logs/agent /logs/verifier
+
+ENTRYPOINT []

benchmarks/ccb_mcp_crossorg/ccx-crossorg-061/environment/Dockerfile.sg_only

@@ -0,0 +1,30 @@
+# CCX-crossorg-061 — sg_only variant
+# No local repo clone — agent uses Sourcegraph MCP exclusively for code access.
+# The verifier restores the full repo from /repo_full/ before scoring.
+
+FROM ubuntu:22.04
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    git \
+    ca-certificates \
+    python3 \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /workspace
+
+# Empty workspace — agent discovers code via MCP tools only
+RUN git init && \
+    git config user.email "agent@example.com" && \
+    git config user.name "Agent" && \
+    git config --global safe.directory '*'
+
+# Create log directories
+RUN mkdir -p /logs/agent /logs/verifier
+
+# Mark sg_only mode — verifiers and eval scripts check this flag
+RUN touch /tmp/.sg_only_mode
+
+ENTRYPOINT []

benchmarks/ccb_mcp_crossorg/ccx-crossorg-061/instruction.md

@@ -0,0 +1,55 @@
+# Cross-Org Interface Implementation Discovery
+
+## Your Task
+
+Your platform team is conducting a cross-organization audit to find all implementations
+of a core Kubernetes storage abstraction. The `k8s.io/apiserver/pkg/storage.Interface`
+is the standard backend abstraction used by the Kubernetes API server — any project that
+embeds a Kubernetes-compatible API layer must implement it.
+
+**Specific question**: Find all Go source files across the repos in this ecosystem that
+contain an explicit interface compliance check for `storage.Interface` using the
+Go pattern `var _ storage.Interface = (*StructName)(nil)`. For each match, report
+the repo, file path, and the struct name that implements the interface.
+
+## Context
+
+This pattern (`var _ InterfaceName = (*TypeName)(nil)`) is used in Go to verify at
+compile time that a type implements an interface. Finding all such declarations across
+repos from different organizations reveals who has independently implemented the same
+storage abstraction — a key signal for platform compatibility audits.
+
+The search should be **exhaustive across all repos in the ecosystem**, not just the
+local repo. The interface is defined in the Kubernetes ecosystem but can be implemented
+by projects from entirely different organizations.
+
+## Available Resources
+
+The local `/workspace/` directory contains: kubernetes/kubernetes.
+
+**Note:** Additional repositories are accessible via Sourcegraph MCP tools:
+- `etcd-io/etcd` (distributed-kv-store)
+- `grafana/grafana` (observability-platform)
+
+## Output Format
+
+Create a file at `/workspace/answer.json` with your findings:
+
+```json
+{
+  "symbols": [
+    {
+      "repo": "org/repo-name",
+      "path": "relative/path/to/file.go",
+      "symbol": "StructName"
+    }
+  ],
+  "text": "Narrative explanation citing which repos and orgs implement storage.Interface and where."
+}
+```
+
+## Evaluation
+
+Your answer is evaluated on:
+- **Symbol recall and precision**: Did you find all structs that explicitly implement `storage.Interface` via the `var _` pattern?
+- The oracle expects implementations from at least 2 different GitHub organizations.

benchmarks/ccb_mcp_crossorg/ccx-crossorg-061/task.toml

@@ -0,0 +1,28 @@
+version = "1.0"
+
+[metadata]
+name = "CCX-crossorg-061"
+description = "Cross-org interface implementation discovery: k8s storage.Interface"
+license = "Apache-2.0"
+
+[task]
+id = "CCX-crossorg-061"
+repo = "kubernetes/kubernetes"
+category = "cross-org-discovery"
+language = "go"
+difficulty = "hard"
+time_limit_sec = 900
+mcp_suite = "ccb_mcp_crossorg"
+use_case_id = 61
+repo_set_id = "multi-org-go"
+mcp_unique = true
+
+[verification]
+type = "eval"
+command = "bash /tests/eval.sh"
+
+reward_type = "score"
+description = "Cross-org interface implementation discovery"
+
+[environment]
+build_timeout_sec = 600.0

benchmarks/ccb_mcp_crossorg/ccx-crossorg-061/tests/__pycache__/oracle_checks.cpython-310.pyc

@@ -0,0 +1,68 @@
+#!/bin/bash
+# eval.sh — MCP-unique benchmark evaluator for CCX-crossorg-061
+# Exit-code-first (SWE-Factory pattern):
+#   exit 0 — agent produced useful output (composite score > 0)
+#   exit 1 — total failure (composite score == 0 or missing answer)
+#
+# Writes /logs/verifier/reward.txt with the composite score [0.0, 1.0]
+
+set -euo pipefail
+
+TASK_ID="CCX-crossorg-061"
+ANSWER_PATH="/workspace/answer.json"
+TASK_SPEC_PATH="/tests/task_spec.json"
+ORACLE_CHECKS="/tests/oracle_checks.py"
+REWARD_PATH="/logs/verifier/reward.txt"
+
+mkdir -p /logs/verifier
+
+echo "=== CCX-crossorg-061 evaluator ==="
+echo "Task spec: $TASK_SPEC_PATH"
+echo "Answer:    $ANSWER_PATH"
+echo ""
+
+# sg_only mode guard: restore full repo if verifier wrapper exists
+if [ -f /tmp/.sg_only_mode ] && [ -f /tests/sgonly_verifier_wrapper.sh ]; then
+    echo "sg_only mode: sourcing verifier wrapper..."
+    source /tests/sgonly_verifier_wrapper.sh
+fi
+
+# Verify answer file exists
+if [ ! -f "$ANSWER_PATH" ]; then
+    echo "ERROR: answer.json not found at $ANSWER_PATH"
+    echo "0.0" > "$REWARD_PATH"
+    exit 1
+fi
+
+# Validate answer is valid JSON
+if ! python3 -c "import json; json.load(open('$ANSWER_PATH'))" 2>/dev/null; then
+    echo "ERROR: answer.json is not valid JSON"
+    echo "0.0" > "$REWARD_PATH"
+    exit 1
+fi
+
+echo "answer.json found and valid JSON"
+
+# Run oracle checks
+if [ ! -f "$ORACLE_CHECKS" ]; then
+    echo "ERROR: oracle_checks.py not found at $ORACLE_CHECKS"
+    echo "0.0" > "$REWARD_PATH"
+    exit 1
+fi
+
+echo "Running oracle checks..."
+SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1)
+
+# Validate score is a number
+if ! echo "$SCORE" | python3 -c "import sys; float(sys.stdin.read().strip())" 2>/dev/null; then
+    echo "ERROR: oracle_checks.py did not return a valid score: $SCORE"
+    echo "0.0" > "$REWARD_PATH"
+    exit 1
+fi
+
+echo ""
+echo "Composite score: $SCORE"
+echo "$SCORE" > "$REWARD_PATH"
+
+# Exit based on score (SWE-Factory exit-code-first pattern)
+python3 -c "import sys; sys.exit(0 if float('$SCORE') > 0 else 1)"

benchmarks/ccb_mcp_crossorg/ccx-crossorg-061/tests/eval.sh

@@ -0,0 +1,24 @@
+{
+  "symbols": [
+    {
+      "repo": "kubernetes/kubernetes",
+      "path": "staging/src/k8s.io/apiserver/pkg/storage/etcd3/store.go",
+      "symbol": "store"
+    },
+    {
+      "repo": "grafana/grafana",
+      "path": "pkg/storage/unified/apistore/store.go",
+      "symbol": "Storage"
+    }
+  ],
+  "text": "The k8s.io/apiserver/pkg/storage.Interface is explicitly implemented in two repos from different GitHub organizations using the `var _ storage.Interface = (...)` compile-time check pattern. First, in kubernetes/kubernetes (kubernetes org) at staging/src/k8s.io/apiserver/pkg/storage/etcd3/store.go, the `store` struct implements storage.Interface via `var _ storage.Interface = (*store)(nil)` at line 100. Second, in grafana/grafana (grafana org) at pkg/storage/unified/apistore/store.go, the `Storage` struct implements storage.Interface via `var _ storage.Interface = (*Storage)(nil)` at line 52. The grafana implementation is part of their unified storage layer that embeds a Kubernetes-compatible API server. This cross-org pattern shows that both the kubernetes org and grafana org independently implement the same storage abstraction.",
+  "_metadata": {
+    "oracle_type": "symbol_resolution",
+    "discovery_method": "sourcegraph_keyword_search",
+    "queries": [
+      "repo:^github.com/kubernetes/kubernetes$ \"var _ storage.Interface\" file:staging",
+      "repo:^github.com/grafana/grafana$ \"var _ storage.Interface\""
+    ],
+    "unique_orgs": ["kubernetes", "grafana"]
+  }
+}