Rakibul Hasan 4938a435ea fix(memory): env-configurable strict system-message-first providers (#9924) ...

* fix(memory): allow OMNIROUTE_STRICT_SYSTEM_PROVIDERS to extend the system-first provider list

PROVIDERS_SYSTEM_MUST_BE_FIRST (added in #6225 for #6135) gates both the
memory-injection placement fix and the #7293 hoistLeadingSystemMessage
translator fix, but was hardcoded to xiaomi-mimo/mimo only. Self-hosted
deployments routing other strict backends (e.g. a custom OpenAI-compatible
connection in front of a self-hosted Qwen3.5+/3.6 model, whose chat template
rejects any non-leading system message the same way) had no way to opt in
without forking and rebuilding the image.

Adds OMNIROUTE_STRICT_SYSTEM_PROVIDERS (comma-separated, case-insensitive
provider ids) to extend the built-in set at read time, mirroring the
injectable-env pattern already used in src/lib/memory/typedDecay.ts. No
behavior change for anyone who doesn't set it.

* chore: fix changelog fragment PR number

2026-08-10 00:27:47 -03:00

..

.gitkeep

feat(release): changelog.d/ fragments — eliminate the CHANGELOG merge-storm cascade (#6783)

2026-07-10 07:22:49 -03:00

5696-layer-a-capability-filter.md

feat(core): add Layer A capability filter at router (#5696)

2026-08-04 08:51:41 -03:00

6736-response-content-encoding.md

feat(api): add response content encoding verification (#6736) (#9444)

2026-08-07 20:53:15 -03:00

6752-plugins-marketplace-install-api.md

feat(api): add plugins marketplace install API (#6752) (#9445)

2026-08-07 20:53:18 -03:00

7679-chatgpt-web-thinking-tool-emulation.md

feat(chatgpt-web): harden prompt-emulated tool contract for thinking models (#7679) (#9422)

2026-08-07 20:53:02 -03:00

7786-management-auth-terminology-docs.md

fix(docs): repair the #7786 squash contamination on release/v3.8.50

2026-08-05 16:16:33 -03:00

8237-reduce-idle-memory-small-vps.md

docs: add small VPS memory optimization guide (#8237) (#9471)

2026-08-06 10:38:57 -03:00

8369-connection-level-upstream-headers.md

feat(providers): add connection-level custom upstream headers (#8369) (#9497)

2026-08-06 10:39:41 -03:00

8461-runomniroutecli-approval-gate.md

feat(copilot): add approval gate for runOmniRouteCli commands (#8461) (#9495)

2026-08-06 10:39:27 -03:00

8468-bun-windows-ci-coverage.md

feat(ci): add windows-latest leg to test-bun-sqlite job (#8468)

2026-08-05 02:39:54 -03:00

8799-electron-remote-server-mode.md

[v3.8.50] feat(electron): add Remote Server Mode to attach to an external OmniRoute instance (#8799)

2026-08-06 06:05:24 -03:00

8862-novita-model-catalog.md

Expand the Novita AI model catalog (#8913)

2026-08-05 21:41:40 -03:00

8870-node-sqlite-adapter-parity.md

feat(db): add node sqlite adapter parity (#8871)

2026-08-05 21:41:12 -03:00

8908-model-token-limit-overrides.md

feat(models): unify token limit overrides (#8908)

2026-08-05 22:41:38 -03:00

8964-xai-agent-tools-passthrough.md

feat(providers): native xAI Agent Tools passthrough for /v1/responses (#9111)

2026-08-05 21:43:40 -03:00

8978-unorouter.md

feat(providers): add UnoRouter provider (#8978) (#9009)

2026-08-05 21:42:35 -03:00

8980-deprecate-gemini-cli-provider.md

feat(sse): deprecate the gemini-cli upstream provider with a real migration path (#8980)

2026-07-30 09:36:54 -03:00

9000-encrypted-reasoning-replay.md

cherry-pick(pr-9601): feat(responses): add encrypted reasoning replay opt-in (#9876)

2026-08-09 09:55:02 -03:00

9031-regolo-ai-provider.md

feat(providers): add Regolo AI provider (#9031) (#9468)

2026-08-06 10:38:41 -03:00

9068-editable-discovered-provider-slugs.md

feat(db): add provider-scoped model aliases (#9068) (#9469)

2026-08-06 10:38:49 -03:00

9208-codex-parenthesized-reasoning.md

feat(codex): accept parenthesized GPT-5.6 effort overrides (#9208)

2026-08-05 22:39:59 -03:00

9214-claude-thinking-token-counts.md

feat(usage): surface Claude thinking token counts to clients (#9214)

2026-08-05 22:40:19 -03:00

9225-ollama-local-embeddings.md

feat(ollama): add Ollama Local embedding support (#9225)

2026-08-05 22:40:46 -03:00

9243-forwarded-header-budget-env.md

feat: make forwarded upstream response-header budget configurable (#9243) (#9492)

2026-08-06 10:39:15 -03:00

9247-provider-detail-connections.md

feat(providers): filter detail connections server-side (#9247)

2026-08-04 14:34:22 -03:00

9248-video-url-passthrough.md

feat(providers): make video_url passthrough configurable per provider/model (#9248) (#9419)

2026-08-07 20:52:57 -03:00

9268-gemini-schema-recursive-type-empty-choices.md

feat(gemini): recursive schema type:object + empty choices interceptor (#9268)

2026-08-04 03:49:35 -03:00

9270-provider-api-key-links.md

feat(dashboard): render provider API key registration links (#9270) (#9336)

2026-08-07 20:52:35 -03:00

9284-json-cookie-input.md

feat(providers): accept JSON cookie objects in normalizeSessionCookieHeader (#9284) (#9335)

2026-08-07 20:52:32 -03:00

9318-opencode-zen-reasoning-effort.md

feat(providers): support max reasoning effort for opencode-zen DeepSeek models (#9318) (#9334)

2026-08-07 20:52:29 -03:00

9322-nanogpt-endpoint-surface.md

feat(providers): expose full NanoGPT endpoint surface (#9322)

2026-08-04 03:35:39 -03:00

9415-newapi-sub2api-aggregator-balance.md

maint: final follow-up cherry-pick #9619 (#9901)

2026-08-09 14:15:53 -03:00

9418-disable-auto-no-think-combos.md

feat(catalog): add hideAutoCombos and hideNoThinkVariants settings toggles (#9418) (#9535)

2026-08-06 10:39:51 -03:00

9473-opencode-plugin-model-allowlist.md

feat(opencode-plugin): add visibleModels/hiddenModels allowlist/blocklist (#9473) (#9538)

2026-08-06 10:40:09 -03:00

9511-quota-exhausted-transient-test-all.md

feat(models): treat quota-exhausted errors as non-hideable in Test All (#9511) (#9537)

2026-08-06 10:40:00 -03:00

9570-plugin-context-headers.md

feat(plugins): expose client request headers in plugin context (#9570) (#9668)

2026-08-07 20:54:32 -03:00

9579-soniox-audio-provider.md

feat(audio): add Soniox STT + TTS provider (#9579)

2026-08-07 20:54:14 -03:00

9782-modality-bridge-settings.md

feat(dashboard): Modality Bridge settings page (vision tabs, model selector, stats, test button) (#9782)

2026-08-10 00:16:06 -03:00

9924-strict-system-providers-env.md

fix(memory): env-configurable strict system-message-first providers (#9924)

2026-08-10 00:27:47 -03:00