fix(prompt): isolate truncation warnings per context

Follow-up to salvaged PR #41619: replace the module-global
_truncation_warnings list with a contextvars.ContextVar so concurrent
gateway-session prompt builds can't drain or clear each other's pending
warnings (cross-session leak). Adds a context-isolation test.

agent/prompt_builder.py

@@ -8,6 +8,7 @@ import json
 import logging
 import os
 import threading
+import contextvars
 from collections import OrderedDict
 from pathlib import Path
 
@@ -976,14 +977,32 @@ def _get_context_file_max_chars() -> int:
     return CONTEXT_FILE_MAX_CHARS
 
 # Collect truncation warnings so the caller (run_agent) can surface them.
-_truncation_warnings: list = []
+# A ContextVar (not a module-global list) isolates accumulation per thread /
+# per async task, so concurrent gateway-session prompt builds can't drain or
+# clear each other's pending warnings (cross-session leak). Each build runs in
+# its own context, collects its own warnings, and drains them synchronously.
+_truncation_warnings: "contextvars.ContextVar[Optional[list]]" = contextvars.ContextVar(
+    "context_file_truncation_warnings", default=None
+)
+
+
+def _record_truncation_warning(msg: str) -> None:
+    """Append a truncation warning to the current context's accumulator."""
+    warnings = _truncation_warnings.get()
+    if warnings is None:
+        warnings = []
+        _truncation_warnings.set(warnings)
+    warnings.append(msg)
 
 
 def drain_truncation_warnings() -> list:
-    """Return and clear any truncation warnings accumulated since last drain."""
-    warnings = _truncation_warnings.copy()
-    _truncation_warnings.clear()
-    return warnings
+    """Return and clear any truncation warnings accumulated in this context."""
+    warnings = _truncation_warnings.get()
+    if not warnings:
+        return []
+    drained = list(warnings)
+    warnings.clear()
+    return drained
 
 
 # =========================================================================
@@ -1503,7 +1522,7 @@ def _truncate_content(content: str, filename: str, max_chars: Optional[int] = No
         f"increase context_file_max_chars or trim the file!"
     )
     logger.warning(msg)
-    _truncation_warnings.append(msg)
+    _record_truncation_warning(msg)
     head_chars = int(max_chars * CONTEXT_TRUNCATE_HEAD_RATIO)
     tail_chars = int(max_chars * CONTEXT_TRUNCATE_TAIL_RATIO)
     head = content[:head_chars]

tests/agent/test_prompt_builder.py

@@ -190,6 +190,34 @@ class TestTruncateContent:
         assert "context_file_max_chars" in warnings[0]
         assert "CONTEXT_FILE_MAX_CHARS" not in warnings[0]
 
+    def test_warnings_isolated_across_contexts(self, monkeypatch):
+        """Truncation warnings accumulate per-context — a concurrent build in
+        a separate context must not see or drain this context's warnings."""
+        import contextvars
+
+        def fake_load_config():
+            return {"context_file_max_chars": 120}
+
+        monkeypatch.setattr("hermes_cli.config.load_config", fake_load_config)
+
+        # Generate a warning in a fresh child context, then assert it did NOT
+        # leak into the parent context's accumulator.
+        def _child():
+            _truncate_content("x" * 180, "child.md")
+            # Inside the child context, the warning is visible & drainable.
+            assert any("child.md" in w for w in drain_truncation_warnings())
+
+        contextvars.copy_context().run(_child)
+
+        # Parent context never saw the child's warning.
+        assert drain_truncation_warnings() == []
+
+        # And a warning raised in the parent stays in the parent.
+        _truncate_content("y" * 180, "parent.md")
+        parent_warnings = drain_truncation_warnings()
+        assert len(parent_warnings) == 1
+        assert "parent.md" in parent_warnings[0]
+
 
 # =========================================================================
 # _parse_skill_file — single-pass skill file reading