IMBENJI.NET/Duriin-API
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: bound max_tokens on the openrouter calls

Browse Source 
Neither the coordinator nor the graph resolver set max_tokens, so openrouter
reserved the model's entire output window against the key's remaining budget and
returned 402 before running anything: 131k tokens reserved to produce a few
hundred. It never showed up with the old model because its output window is
small enough to fit under the limit.

Both are now bounded and overridable by env. The headroom is deliberate, the
newer reasoning models spend completion tokens thinking before they answer.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WnNxwxfXSbeNtjvtz5gayb
This commit is contained in:
ImBenji
2026-09-01 21:32:22 +01:00
co-authored by Claude Opus 5
parent 9fc443579f
commit 4718635c75
3 changed files with 10 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+1 -1
View File
@@ -12,7 +12,7 @@ ALPHA_VANTAGE_API_KEY=
FINNHUB_API_KEY=
OPEN_ROUTER_API_KEY=
OPEN_ROUTER_LLM_MODEL=qwen/qwen3-235b-a22b-2507
OPEN_ROUTER_LLM_MODEL=~deepseek/deepseek-v4-flash-latest
OPEN_ROUTER_EMBED_MODEL=qwen/qwen3-embedding-8b
# Paper execution is disabled unless AUTONOMY_EXECUTION_MODE=paper.