Skip to content

fix(strix): disable streaming to route around contextual-orchestrator's stale invalid_stream_options rejection #1447

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
seonghobae wants to merge 1 commit into from
+19 −0
Closed

fix(strix): disable streaming to route around contextual-orchestrator's stale invalid_stream_options rejection #1447

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 19 additions & 0 deletions .github/workflows/strix.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -743,6 +743,25 @@ jobs:
# The gateway auto pool is provider-diverse. Strix function tools
# must not send a provider-specific reasoning setting to every route.
STRIX_REASONING_EFFORT: none
# TEMPORARY INCIDENT MITIGATION (2026-08-30): strix hardcodes
# ModelSettings(include_usage=True) for every turn
# (strix/core/inputs.py make_model_settings(), strix-agent 1.5.3) with
# no supported env var/CLI/config knob to disable just that flag while
# still streaming. contextual-orchestrator's /v1/chat/completions
# unconditionally rejects stream=true + stream_options.include_usage=true
# whenever tools are present (server.py, "invalid_stream_options"),
# which strix always sends -- so every scan through this gateway fails
# closed with a 400, org-wide, since Strix moved onto orchestrator/free
# today. LLM_DISABLE_STREAMING is a genuine, documented strix env var
# (strix/config/models.py _NonStreamingModel) that makes every turn a
# single non-streaming call, so stream_options is never sent and the
# gateway's check never fires. This trades away real-time SSE streaming
# for a working scan; it is not the fix. Revert this line once the
# tracked contextual-orchestrator fix (removing/narrowing the stale
# tool-loop stream+include_usage rejection -- the honest usage-reporting
# path it guards already works today for non-streaming tool-loop calls)
# is merged and deployed. Tracking: #1446.
LLM_DISABLE_STREAMING: "true"

@devin-ai-integration devin-ai-integration Bot Aug 30, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🔴 Streaming mitigation never reaches Strix

The quick gate omits LLM_DISABLE_STREAMING from its scanner environment, so streaming stays enabled. Gateway requests still fail with 400 responses.

Prompt for agents 
The Run Strix workflow sets LLM_DISABLE_STREAMING=true, but scripts/ci/strix_quick_gate.sh creates child_env from an explicit allowlist before launching the Strix executable. That allowlist includes STRIX_REASONING_EFFORT and STRIX_LLM_MAX_RETRIES but not LLM_DISABLE_STREAMING, so the new setting is discarded. Propagate this setting through the trusted child-environment boundary and add a regression test proving the launched scanner receives it while unrelated environment variables remain excluded.
Devin Review

Was this helpful? React with 👍 or 👎 to provide feedback.

@devin-ai-integration devin-ai-integration Bot Aug 30, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

📝 Info: Upstream switch preserves scan processing

Strix 1.5.3 uses _NonStreamingModel for this setting. It makes one non-streaming request, then replays the result through the normal run loop.

Devin Review

Was this helpful? React with 👍 or 👎 to provide feedback.

STRIX_LLM_MAX_RETRIES: 1
STRIX_TRANSIENT_RETRY_PER_MODEL: 2
STRIX_TRANSIENT_RETRY_BACKOFF_SECONDS: 60
Expand Down
Loading