WEBDIENSTE/openswarm
1
0
Fork 0
mirror of https://github.com/openswarm-ai/openswarm.git synced 2026-08-17 18:25:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

[eric] latency: a short first message no longer drifts the boot fingerprint, so the pre-warmed CLI is actually used (3.92s -> 1.58s median, 0 wasted spawns)

Browse Source
This commit is contained in:
ciregenz
2026-08-07 00:34:54 -07:00
parent d59b61e810
commit ef8806eda3
2 changed files with 25 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/apps/agents/manager/run/run_options_helpers.py
+7 -2
View File
@@ -181,9 +181,14 @@ def inject_thinking_options(options_kwargs: Dict, session: AgentSession, prompt:
reasoning_effort), with the short-prompt + gc/gemini-3 force-off overrides. Best-effort."""
try:
level = getattr(session, "thinking_level", "auto") or "auto"
# Trivially short prompts ("hi", "thanks") don't benefit from 5-30s of hidden reasoning.
# Trivially short prompts ("hi", "thanks") don't benefit from 5-30s of hidden reasoning, but
# this flip rides the BOOT fingerprint: a short first message drifted it and threw away the
# pre-warmed CLI, measured as a second spawn on 5 of 5 short-prompt sessions. A wasted 0.9s
# respawn costs more than the reasoning it saves, so the flip only applies once a session is
# already running on a live client (later turns), never on the first message.
p_prompt_len = len((prompt or "").strip())
if 0 < p_prompt_len < 50 and level != "off":
p_first_turn = not getattr(session, "sdk_session_id", None)
if 0 < p_prompt_len < 50 and level != "off" and not p_first_turn:
level = "off"
# gc/gemini-3* without Antigravity 400s every multi-step turn on thoughtSignature continuity.
if (
backend/tests/test_capacity_retry.py
+18
View File
@@ -124,3 +124,21 @@ def test_reset_window_401_is_transient_not_auth():
def test_genuine_auth_death_still_cards():
assert is_auth_error(Exception("401 unauthorized: invalid authentication credentials"))
assert capacity_retry_wait(Exception("401 unauthorized: invalid api key"), 0) is None
# --- the first-turn thinking flip must not drift the boot fingerprint (measured: it threw away the
# pre-warmed CLI on 5 of 5 short-prompt sessions, costing ~0.9s of respawn per first message) ------
def test_short_first_message_keeps_the_prewarmed_thinking_setting():
from backend.apps.agents.core.models import AgentSession
from backend.apps.agents.manager.run.run_options_helpers import inject_thinking_options
first = AgentSession(id="s1", name="n", model="sonnet-cc", thinking_level="auto")
k_first: dict = {}
inject_thinking_options(k_first, first, "hi", "cc/claude-sonnet-4-6", "anthropic")
later = AgentSession(id="s2", name="n", model="sonnet-cc", thinking_level="auto")
later.sdk_session_id = "already-running"
k_later: dict = {}
inject_thinking_options(k_later, later, "hi", "cc/claude-sonnet-4-6", "anthropic")
assert k_first != k_later, "a short FIRST message must keep the prewarmed boot options"