docs + unit test fix

This commit is contained in:
Ian 2026-09-29 21:40:43 -04:00 • committed by Ahmed Allam
parent c77bdd2c2a
commit 9b72488c92
2 changed files with 13 additions and 5 deletions

View file

@ -49,6 +49,14 @@ Configure Strix using environment variables or a config file.
Timeout in seconds for memory compression operations (context summarization).
</ParamField>
<ParamField path="STRIX_OPENROUTER_STICKY_SESSIONS" default="false" type="boolean">
Send a per-agent `session_id` on OpenRouter requests, so each agent's calls stay on one upstream provider and its prompt cache carries over between turns. When unset, OpenRouter routes every request freely.
</ParamField>
<ParamField path="STRIX_CACHE_BLOCK_TOKENS" default="128" type="integer">
Token block size that providers cache prompts in. A turn counts as a cache miss in the run report only when the cached tokens fall at least this many tokens short of the previous prompt and the prompt did not shrink. Lower it for providers with smaller blocks (DeepSeek and GLM use 64; vLLM defaults to 16).
</ParamField>
### Dedicated deduplication model
Finding deduplication is a cheap, structured classification task. By default it

View file

@ -381,11 +381,11 @@ def test_openrouter_request_carries_agent_session_id() -> None:
assert "session_id" not in body()
token = request_log.bind_call_context("a1b2c3d4", "root")
try:
session_id = body()["session_id"]
assert str(uuid.UUID(session_id)) == session_id
assert body()["session_id"] == session_id
assert "session_id" not in body()
with patch("strix.config.models.load_settings") as settings:
settings.return_value.llm.openrouter_sticky_sessions = False
assert "session_id" not in body()
settings.return_value.llm.openrouter_sticky_sessions = True
session_id = body()["session_id"]
assert str(uuid.UUID(session_id)) == session_id
assert body()["session_id"] == session_id
finally:
request_log.reset_call_context(token)