All agents now track which variables were explicitly present in their prompt
versus fetched from environment variables or git remote. When constructing
subagent prompts, only explicitly-present variables are included. Fetched
variables are omitted, allowing each subagent to fetch them independently.

This prevents credentials and other fetched values from being garbled as they
propagate through multiple LLM prompt layers.

Affected agents:
- auto-agents (primary orchestrator)
- implementation-supervisor, pr-merge-supervisor, pr-review-supervisor
- supervisor (generic)
- implementation-worker, pr-merge-worker, pr-review-worker
- task-implementor, tier-dispatcher
- work-group-util, git-clone-util, git-push-util, git-checkout-util

@@ -0,0 +17,4 @@
+
+    registry = ProviderRegistry()
+    providers = registry.get_all_providers()
+    assert len(providers) == 10, f"Expected 10 providers, got {len(providers)}"

@@ -0,0 +39,4 @@
+
+    saved = os.environ.pop("OPENAI_API_KEY", None)
+    try:
+        Settings._instance = None  # type: ignore[attr-defined]

@@ -0,0 +8,4 @@
+
+*** Variables ***
+${SRC_DIR}        ${CURDIR}/..
+${HELPER}         ${CURDIR}/helper_provider_integration.py

@@ -0,0 +13,4 @@
+
+def test_discover_all_providers() -> None:
+    """Verify ProviderRegistry discovers all 10 ProviderType entries."""
+    from cleveragents.providers.registry import ProviderRegistry

@@ -0,0 +34,4 @@
+    """get_configured_providers correctly filters among API-key scenarios."""
+    import os
+
+    from cleveragents.config.settings import Settings, get_settings

@@ -0,0 +39,4 @@
+
+    saved = os.environ.pop("OPENAI_API_KEY", None)
+    try:
+        Settings._instance = None  # type: ignore[attr-defined]

@@ -0,0 +14,4 @@
+Discover All Providers Registered
+    [Documentation]    Verify ProviderRegistry discovers all 10 ProviderType entries.
+    [Tags]    provider    registry    discovery    subtags:count
+    ${result}=    Run Process    ${PYTHON}    robot/${HELPER}    discover-all-providers