Skip to content

fix(deploy): complete the LLM env wiring for the demo stack #66

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

Open
librowski wants to merge 3 commits into
base: main
Choose a base branch
from
Open

fix(deploy): complete the LLM env wiring for the demo stack #66

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
431fbf4
fix(deploy): pass OPENROUTER_API_KEY to the backend service
librowski-synergy Jul 17, 2026
48c340c
fix(deploy): wire TAVILY_API_KEY into the worker service
librowski-synergy Jul 17, 2026
dddf90a
fix: unify the AI_MODEL default on the demo model
librowski-synergy Jul 17, 2026
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
2 changes: 1 addition & 1 deletion apps/backend/.env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,4 +19,4 @@ TURNSTILE_SECRET_KEY=
# Optional: leave empty to disable AI adapt (the endpoint returns 501). The
# execution worker keeps its own key for running workflows.
OPENROUTER_API_KEY=
AI_MODEL=google/gemini-2.5-flash-lite
AI_MODEL=mistralai/mistral-small-3.2-24b-instruct
2 changes: 1 addition & 1 deletion apps/backend/src/env.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,5 +20,5 @@ export const env = {
TURNSTILE_SECRET_KEY: process.env['TURNSTILE_SECRET_KEY'] ?? null,
// Null = the "AI adapt" endpoint is disabled (returns 501). The worker keeps its own key.
OPENROUTER_API_KEY: process.env['OPENROUTER_API_KEY'] ?? null,
AI_MODEL: envOr('AI_MODEL', 'google/gemini-2.5-flash-lite'),
AI_MODEL: envOr('AI_MODEL', 'mistralai/mistral-small-3.2-24b-instruct'),
};
2 changes: 1 addition & 1 deletion apps/execution-worker/.env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ TEMPORAL_ADDRESS=127.0.0.1:7233

# OpenRouter — any model
OPENROUTER_API_KEY=sk-or-...
AI_MODEL=google/gemini-2.5-flash-lite
AI_MODEL=mistralai/mistral-small-3.2-24b-instruct

# Tavily web search (optional). Enables the AI Agent's "Web search" tool. Get a
# free key at https://tavily.com (free tier ~1000 searches/month). Leave empty
Expand Down
2 changes: 1 addition & 1 deletion apps/execution-worker/src/env.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ export const env = {
TEMPORAL_ADDRESS: envOr('TEMPORAL_ADDRESS', '127.0.0.1:7233'),
OPENROUTER_API_KEY: requireEnv('OPENROUTER_API_KEY'),
// Cheap, fast default for the public demo; quality-per-cost over frontier capability.
AI_MODEL: envOr('AI_MODEL', 'google/gemini-2.5-flash-lite'),
AI_MODEL: envOr('AI_MODEL', 'mistralai/mistral-small-3.2-24b-instruct'),
// Optional. Enables the AI Agent's web-search tool; agents run without it when unset.
TAVILY_API_KEY: process.env['TAVILY_API_KEY'],
};
7 changes: 6 additions & 1 deletion deploy/ai-studio/.env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,10 +9,15 @@ OPENROUTER_API_KEY=

# --- LLM --------------------------------------------------------------------

# WB-229 demo model. Cheap, EU-hosted, solid tool calling.
# Demo model. Cheap, EU-hosted, solid tool calling.
# ~$0.075/M input + $0.20/M output => ~$0.0004 per 3-call template run.
AI_MODEL=mistralai/mistral-small-3.2-24b-instruct

# Tavily web search (optional). Enables the AI Agent's "Web search" tool -
# free key at https://tavily.com (~1000 searches/month). Leave empty to
# disable: agents with web search toggled on still run, just without the tool.
TAVILY_API_KEY=

# --- abuse gate (per-IP, execute route) ---------------------------------------

RATE_LIMIT_EXECUTE_PER_MINUTE=10
Expand Down
5 changes: 5 additions & 0 deletions deploy/ai-studio/docker-compose.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,9 @@ services:
TRUST_PROXY: 'true'
RATE_LIMIT_EXECUTE_PER_MINUTE: ${RATE_LIMIT_EXECUTE_PER_MINUTE:-10}
RATE_LIMIT_EXECUTE_PER_DAY: ${RATE_LIMIT_EXECUTE_PER_DAY:-50}
# the backend calls the LLM itself for /api/visualize/adapt
OPENROUTER_API_KEY: ${OPENROUTER_API_KEY:?set OPENROUTER_API_KEY in deploy/ai-studio/.env}
AI_MODEL: ${AI_MODEL:-mistralai/mistral-small-3.2-24b-instruct}
depends_on:
app-db:
condition: service_healthy
Expand Down Expand Up @@ -111,6 +114,8 @@ services:
TEMPORAL_ADDRESS: temporal:7233
OPENROUTER_API_KEY: ${OPENROUTER_API_KEY:?set OPENROUTER_API_KEY in deploy/ai-studio/.env}
AI_MODEL: ${AI_MODEL:-mistralai/mistral-small-3.2-24b-instruct}
# optional - empty disables the AI Agent's web search tool
TAVILY_API_KEY: ${TAVILY_API_KEY:-}
depends_on:
app-db:
condition: service_healthy
Expand Down
Loading