mirror of
https://github.com/lukaszraczylo/traefik-llmgateway.git
synced 2026-10-12 04:54:45 +00:00
lukaszraczylo
730583d98e
Addresses coordinator review of the Task 15 integration suite: 1 critical ruling, 5 important, 3 folded. make integration now exits 0. - integration_test.go: TestStreamingIncrementalityProbe restructured — content assertion (5 deltas + [DONE], in order) always runs; the raw-TCP timing assertion (unchanged, >=3 gaps >=100ms) is gated behind INTEGRATION_STREAMING=1 with t.Skipf naming traefik/traefik#10269, verified to still genuinely fail when re-armed (not silently disabled). - Makefile: integration-up/integration-wait moved from prerequisites into the integration recipe body as go test ./... -count=1 ok github.com/lukaszraczylo/traefik-llmgateway 6.065s sub-invocations with per-stage status capture, so integration-down always runs even when bring-up or the health wait fails; verified with a synthetic failure. Added .NOTPARALLEL (the integration targets are stateful). - translate_gemini.go: fixed the same yaegi multi-value-assignment panic shape as the prior sse.go fix, on the live max_tokens path. Added a gemini chat completion assertion to integration_test.go (renamed TestUnifiedChatAllProviders) so this path now runs under real Yaegi. - providers.go, translate_anthropic.go: documented the never-wrap contract on providerHTTPError/translateError (routes_unified.go asserts their concrete type directly; errors.As panics under yaegi on these). - integration_test.go: TestCrossReplicaLimits now FLUSHALLs Redis first, for idempotence under integration-keep. - mock/main.go: probe's header-terminator search now accumulates a rolling buffer across reads instead of only checking the latest one. - Folded: hot-reload deadline 10s -> 20s; dynamic.yml's real-upstream baseUrl is now a template (dynamic.yml.tmpl) rendered via INTEGRATION_REAL_BASEURL (default https://llmgw.example.com), not a hardcoded-only hostname. See task-15-report.md's addendum for full verification detail.
92 lines
2.8 KiB
Cheetah
92 lines
2.8 KiB
Cheetah
http:
|
|
routers:
|
|
llmgateway-router:
|
|
rule: "PathPrefix(`/`)"
|
|
entryPoints: ["web"]
|
|
service: dummy-service
|
|
middlewares: ["llmgateway"]
|
|
priority: 1
|
|
|
|
llmgateway-real-router:
|
|
rule: "Host(`real.localhost`)"
|
|
entryPoints: ["web"]
|
|
service: dummy-service
|
|
middlewares: ["llmgateway-real"]
|
|
priority: 100
|
|
|
|
services:
|
|
# Placeholder upstream. Every route the plugin recognizes is
|
|
# short-circuited by the middleware itself; this backend is never
|
|
# actually reached by the requests the integration suite sends.
|
|
dummy-service:
|
|
loadBalancer:
|
|
servers:
|
|
- url: "http://mockopenai:8080"
|
|
|
|
middlewares:
|
|
llmgateway:
|
|
plugin:
|
|
llmgateway:
|
|
providers:
|
|
openai:
|
|
type: openai
|
|
baseUrl: "http://mockopenai:8080"
|
|
apiKey: "mock-openai-key"
|
|
discovery: true
|
|
models: ["gpt-mock"]
|
|
anthropic:
|
|
type: anthropic
|
|
baseUrl: "http://mockanthropic:8080"
|
|
apiKey: "mock-anthropic-key"
|
|
models: ["claude-mock"]
|
|
gemini:
|
|
type: gemini
|
|
baseUrl: "http://mockgemini:8080"
|
|
apiKey: "mock-gemini-key"
|
|
models: ["gemini-mock"]
|
|
groups:
|
|
eng:
|
|
limits:
|
|
requestsPerMinute: 1000
|
|
limited:
|
|
limits:
|
|
requestsPerMinute: 3
|
|
users:
|
|
inline:
|
|
- name: alice
|
|
group: eng
|
|
apiKey: "sk-int-alice"
|
|
file: "/users/users.json"
|
|
redis:
|
|
address: "redis:6379"
|
|
mcpServers:
|
|
tool:
|
|
url: "http://mocktool:8080"
|
|
|
|
# Second, separate middleware instance carrying only the optional
|
|
# real-upstream smoke test's "uni" provider (task 7, INTEGRATION_REAL=1
|
|
# gated). Kept isolated from the mock-backed "llmgateway" middleware
|
|
# above so the always-on tests never depend on network egress.
|
|
llmgateway-real:
|
|
plugin:
|
|
llmgateway:
|
|
providers:
|
|
uni:
|
|
type: openai
|
|
baseUrl: "__INTEGRATION_REAL_BASEURL__"
|
|
apiKey: ""
|
|
# Explicit rather than discovered: resolution must not depend
|
|
# on this container reaching the real upstream at Traefik
|
|
# startup (offline dev machines, CI with no egress). The
|
|
# actual chat completion call in task 7 still goes out live.
|
|
models: ["deepseek-v4-flash-0731"]
|
|
groups:
|
|
eng:
|
|
limits:
|
|
requestsPerMinute: 1000
|
|
users:
|
|
inline:
|
|
- name: alice-real
|
|
group: eng
|
|
apiKey: "sk-int-real"
|