From fa418a8b14305e06545401d44b60273e250906da Mon Sep 17 00:00:00 2001 From: Moe Khalil Date: Mon, 7 Sep 2026 16:42:13 +0000 Subject: [PATCH] fix(deploy): rename gitignored config.yaml to proxy_config.yaml Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- deploy/autorouter-sandbox/Dockerfile | 2 +- deploy/autorouter-sandbox/README.md | 4 +-- deploy/autorouter-sandbox/proxy_config.yaml | 39 +++++++++++++++++++++ 3 files changed, 42 insertions(+), 3 deletions(-) create mode 100644 deploy/autorouter-sandbox/proxy_config.yaml diff --git a/deploy/autorouter-sandbox/Dockerfile b/deploy/autorouter-sandbox/Dockerfile index 5b05cbb2e97..ede9f547fb2 100644 --- a/deploy/autorouter-sandbox/Dockerfile +++ b/deploy/autorouter-sandbox/Dockerfile @@ -8,6 +8,6 @@ COPY enterprise/ /app/enterprise/ COPY litellm-proxy-extras/litellm_proxy_extras/ ${SITE_PACKAGES}/litellm_proxy_extras/ COPY litellm-proxy-extras/ /app/litellm-proxy-extras/ COPY schema.prisma /app/schema.prisma -COPY deploy/autorouter-sandbox/config.yaml /app/config.yaml +COPY deploy/autorouter-sandbox/proxy_config.yaml /app/config.yaml CMD ["--config", "/app/config.yaml", "--port", "4000"] diff --git a/deploy/autorouter-sandbox/README.md b/deploy/autorouter-sandbox/README.md index ad34260e659..8a0761b091f 100644 --- a/deploy/autorouter-sandbox/README.md +++ b/deploy/autorouter-sandbox/README.md @@ -2,7 +2,7 @@ A LiteLLM deployment built from this branch that you can push to and redeploy in about a minute, for iterating on the auto router without touching the real sandbox or prod -Every model that is not defined in `config.yaml` is forwarded to the upstream gateway (`UPSTREAM_LITELLM_BASE_URL`, i.e. gateway.litellm-sandbox.ai) through `litellm_proxy/*`, so this instance inherits all upstream models and provider credentials without copying any keys. Auto routers defined here (`moe-router`) pick between those upstream models and the router code running is whatever is on this branch +Every model that is not defined in `proxy_config.yaml` is forwarded to the upstream gateway (`UPSTREAM_LITELLM_BASE_URL`, i.e. gateway.litellm-sandbox.ai) through `litellm_proxy/*`, so this instance inherits all upstream models and provider credentials without copying any keys. Auto routers defined here (`moe-router`) pick between those upstream models and the router code running is whatever is on this branch ## Image @@ -18,7 +18,7 @@ curl localhost:4000/v1/chat/completions -H "Authorization: Bearer $LITELLM_MASTE -d '{"model":"moe-router","messages":[{"role":"user","content":"hi"}]}' -i | grep x-litellm-model-name ``` -Without Docker: `uv run --no-sync litellm --config deploy/autorouter-sandbox/config.yaml --port 4000` +Without Docker: `uv run --no-sync litellm --config deploy/autorouter-sandbox/proxy_config.yaml --port 4000` ## Deploy diff --git a/deploy/autorouter-sandbox/proxy_config.yaml b/deploy/autorouter-sandbox/proxy_config.yaml new file mode 100644 index 00000000000..6638b89f1c3 --- /dev/null +++ b/deploy/autorouter-sandbox/proxy_config.yaml @@ -0,0 +1,39 @@ +model_list: + - model_name: "*" + litellm_params: + model: litellm_proxy/* + api_base: os.environ/UPSTREAM_LITELLM_BASE_URL + api_key: os.environ/UPSTREAM_LITELLM_API_KEY + + - model_name: moe-router + litellm_params: + model: auto_router/complexity_router + complexity_router_default_model: anthropic/claude-sonnet-5 + complexity_router_config: + classifier_type: llm + classifier_llm_config: + model: openai/gpt-4o-mini + timeout_ms: 3000 + classification_rubric: agentic + classifier_context_window_size: 35 + classifier_context_per_turn_chars: 500 + deployment_affinity: true + session_affinity: false + escalation_keywords: + - LITELLM ESCALATE + tiers: + SIMPLE: + - anthropic/claude-haiku-4-5 + MEDIUM: + - anthropic/claude-sonnet-5 + COMPLEX: + - anthropic/claude-opus-5 + REASONING: + - anthropic/claude-fable-5 + +general_settings: + master_key: os.environ/LITELLM_MASTER_KEY + +litellm_settings: + drop_params: true + telemetry: false