Diego Rodrigues de Sa e Souza 9450e03b1e fix(api): exempt test-model requests from Output Styles injection (#6240) (#6511) ...

* fix(api): exempt test-model requests from Output Styles injection (#6240)

Root cause: handleChatCore's Phase 4A Output Styles injection (chatCore.ts)
was gated only by the operator's global compression.enabled switch,
independent of the per-request x-omniroute-compression header. The
dashboard 'Test model' action (modelTestRunner.ts) never sent that header,
so a globally-enabled Output Style (e.g. 'Ultra terse') always leaked its
system-prompt injection into a plain connection test.

Fix: skip Output Styles injection when the request explicitly opts out via
x-omniroute-compression: off, and always send that header from
buildInternalChatRequest / buildInternalRerankRequest.

Regression guard: tests/integration/test-model-compression-off-6240.test.ts,
tests/unit/model-test-runner-compression-off-6240.test.ts

* chore: sync CHANGELOG to release tip (#6511; bullet re-added at merge)

2026-07-07 20:07:30 -03:00

..

config

feat(glm): add team plan quota settings for glm-cn connections (#6351)

2026-07-06 21:35:04 -03:00

executors

fix(providers): strip reasoning_effort/reasoning from grok-cli requests (#6288) (#6503)

2026-07-07 17:20:25 -03:00

handlers

fix(api): exempt test-model requests from Output Styles injection (#6240) (#6511)

2026-07-07 20:07:30 -03:00

lib

Release v3.8.4 (#2678)

2026-05-26 23:51:47 -03:00

mcp-server

feat: add TinyFish Fetch support to web-fetch provider and update related documentation (#6349)

2026-07-06 21:32:15 -03:00

services

fix(providers): warn when config.judgeModel is set on a non-fusion combo (#6455) (#6532)

2026-07-07 19:32:15 -03:00

shared

feat(providers): add Zed hosted LLM aggregator (native-app sign-in) — NEEDS LIVE OAUTH VALIDATION (#6118)

2026-07-06 20:43:11 -03:00

transformer

Release v3.8.40

2026-06-29 08:40:06 -03:00

translator

feat(providers): Gemini tool-calling end-to-end on /v1beta (#6222) (#6394)

2026-07-06 19:31:12 -03:00

utils

fix(providers): enrich model_cooldown 429 body with retry_after ISO + credential count (#6460) (#6523)

2026-07-07 19:49:57 -03:00

.npmignore

feat: OmniRoute v1.0.0 — Intelligent AI Gateway & Universal LLM Proxy

2026-02-18 00:02:15 -03:00

index.ts

feat: add ModelScope provider with circuit breaker and daily quota lock (#1430)

2026-04-19 21:13:45 -03:00

package.json

chore(release): open v3.8.47 development cycle

2026-07-07 07:58:13 -03:00

tsconfig.json

Release v3.8.23

2026-06-12 23:49:22 -03:00

types.d.ts

Release v3.8.40

2026-06-29 08:40:06 -03:00