Skip to content

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

fix(cache): avoid fallback session collisions (#1827)

Rod Boev0f606b6281dd
diff --git a/headroom/cache/prefix_tracker.py b/headroom/cache/prefix_tracker.py
index 4d5baebea..7fd2d4c9f 100644
--- a/headroom/cache/prefix_tracker.py
+++ b/headroom/cache/prefix_tracker.py
@@ -613,20 +613,19 @@ class SessionTrackerStore:
if session_header:
return str(session_header)
- # Fall back to hashing model + system prompt
- system_content = ""
+ # Fall back to hashing model + all system-text content.
+ system_parts: list[str] = []
for msg in messages:
if msg.get("role") == "system":
content = msg.get("content", "")
if isinstance(content, str):
- system_content = content[:500] # First 500 chars is enough
+ system_parts.append(content)
elif isinstance(content, list):
for block in content:
if isinstance(block, dict) and block.get("type") == "text":
- system_content = block.get("text", "")[:500]
- break
- break
+ system_parts.append(block.get("text", ""))
+ system_content = json.dumps(system_parts, ensure_ascii=False, separators=(",", ":"))
key = f"{model}:{system_content}"
return hashlib.md5(key.encode()).hexdigest()[:16] # nosec B324
diff --git a/tests/test_cache/test_prefix_tracker.py b/tests/test_cache/test_prefix_tracker.py
index a2e095292..01d296755 100644
--- a/tests/test_cache/test_prefix_tracker.py
+++ b/tests/test_cache/test_prefix_tracker.py
@@ -370,6 +370,47 @@ class TestSessionTrackerStore:
id3 = store.compute_session_id(MockRequest(), "gpt-4", messages)
assert id3 != id1
+ def test_compute_session_id_uses_all_system_messages(self, store):
+ """Different dynamic system messages should not collide."""
+
+ class MockRequest:
+ headers = {}
+
+ static_prompt = "framework prompt " * 80
+ conv_a = [
+ {"role": "system", "content": [{"type": "text", "text": static_prompt}]},
+ {"role": "system", "content": [{"type": "text", "text": "context: session A"}]},
+ {"role": "user", "content": "hello"},
+ ]
+ conv_b = [
+ {"role": "system", "content": [{"type": "text", "text": static_prompt}]},
+ {"role": "system", "content": [{"type": "text", "text": "context: session B"}]},
+ {"role": "user", "content": "hello"},
+ ]
+
+ id_a = store.compute_session_id(MockRequest(), "claude-3", conv_a)
+ id_b = store.compute_session_id(MockRequest(), "claude-3", conv_b)
+
+ assert id_a != id_b
+
+ def test_compute_session_id_is_stable_when_only_non_system_turns_change(self, store):
+ """Appending non-system turns should keep the same fallback session id."""
+
+ class MockRequest:
+ headers = {}
+
+ base_messages = [
+ {"role": "system", "content": [{"type": "text", "text": "framework prompt"}]},
+ {"role": "system", "content": [{"type": "text", "text": "context: session A"}]},
+ {"role": "user", "content": "hello"},
+ ]
+ extended_messages = base_messages + [{"role": "assistant", "content": "hi there"}]
+
+ id1 = store.compute_session_id(MockRequest(), "claude-3", base_messages)
+ id2 = store.compute_session_id(MockRequest(), "claude-3", extended_messages)
+
+ assert id1 == id2
+
def test_compute_session_id_no_system(self, store):
"""Should work without system messages."""