Thanks @adivekar-utexas! Rebuilt on release/v3.8.32 with just the UI commits (combo+command-code landed via #4472/#4473). Extracted a pure targetFormatBadgeI18nKey helper + added its unit test (Rule #18 gap) and reconciled the file-size baseline. targetFormat selector now ships.
Thanks @artickc! Rebased onto release/v3.8.32. Added a regression guard for the terminal type-scan shortcut (the one change with correctness risk) — typed/event-line/OpenAI/[DONE] shapes all verified. CRC gate stays opt-in, busy_timeout is tuning, compact artifacts round-trip via JSON.parse. 4/4.
Thanks @janeza2! Rebased onto release/v3.8.32 and completed the end-to-end wiring on review: kimi-coding-apikey was missing from USAGE_SUPPORTED_PROVIDERS (dashboard 400) and USAGE_FETCHER_PROVIDERS (preflight) — added both + header-selection/wiring tests. Now fully routable.
Thanks @adivekar-utexas! Rebuilt on release/v3.8.32 with just the command-code commits (the combo half landed via #4472). reasoning/thinking passthrough + body.model rewrite now ship.
#4023 added validateWebCookieProvider (generic /models session ping -> AUTH_007
SESSION_EXPIRED on 401/403) and dispatched ALL web-cookie providers to it at the TOP
of validateProviderApiKey, BEFORE the SPECIALTY_VALIDATORS table. That shadowed the
rich per-provider validators (validateGrokWebProvider with #3474 IP-reputation/
Cloudflare guidance, validateChatGptWebProvider cf-mitigated, claude/gemini/copilot/
qwen/t3-web), which became dead code and broke all 41 web-cookie assertions in
provider-validation-specialty.test.ts (latent on release/v3.8.32; surfaced by a
__RUN_ALL__ unit run).
Move the generic dispatch to AFTER SPECIALTY_VALIDATORS so it is a FALLBACK only for
web-cookie providers without a dedicated validator. Rich validators run first
(provider-validation-specialty 112/112 restored); the generic + its AUTH_007
capability are preserved (web-cookie-auth007 stays 5/5, it calls the function directly).
Rebaselines validation.ts file-size 4518->4522 (+4, justified). Note: the sibling
pricing half of this restore-green already landed via #4447; this PR carries only the
stranded web-cookie validator fix.
* fix(cli): non-interactive-safe prompts + singular `context` alias
Two CLI-polish follow-ups (the third — an async-warn refactor for #2807 — is moot:
#4373 replaced the Gemini remote-URL drop+warn with fileData pass-through, so no
async warn remains).
1) createPrompt (io.mjs) — the shared interactive helper used rl.question with no
EOF guard, so a non-interactive stdin (pipe, CI, `< /dev/null`) left the await
pending and Node warned about an 'unsettled top-level await' while the command
hung. ask/askSecret now resolve on the readline `close` event (fired on EOF)
with the default / empty string. A genuinely piped line still arrives via the
question callback first, so `echo value | omniroute …` keeps working — only the
no-input EOF case falls back. This fixes every command that prompts, centrally
(mirrors the contexts `confirm()` fix from #4397).
2) `contexts` gains a singular `context` alias — the connect output and older docs
said `omniroute context current`; the alias keeps that muscle-memory working.
Tests: cli-io.test.ts (ask default/empty + askSecret resolve on EOF, no hang) and a
cli-contexts.test.ts case asserting the `context` alias is registered. 11/11.
* test(cli): mock .alias() in the fake program for the contexts subcommand test
The existing 'registers a current subcommand' test uses a minimal fake commander
program; registerContexts now calls .alias("context"), so the fake needs an alias()
stub (returns this) or the chain throws. Add it. (Self-introduced by the alias in
this branch; my 4 new tests already pass in CI.)
* docs(compression): design spec for the unified compression config panel
Engine-centric central panel (single source for master + per-engine on/off + level),
default pipeline derived from the engines map; Combos page owns named ordered pipelines +
active-profile selection; per-engine pages keep only detailed config. Phased: (1) core
consolidation + Model A migration, (2) named profiles + active selector, (3) per-request
x-omniroute-compression header.
* docs(compression): Phase 1 implementation plan for the unified config panel
12 TDD tasks: engine catalog, engines map + activeComboId, deriveDefaultPlan,
migration 102 + backfill, resolveCompressionPlan, runtime wiring, API, default-combo
shim, the engine-grid panel, consolidation, menu. Ends with a recap + the pending
follow-ups (Phase 2 named profiles/active selector, Phase 3 header, deferred items).
* feat(compression): engine catalog metadata (levels, single-mode, order)
* feat(compression): add engines map + activeComboId to CompressionConfig
* feat(compression): deriveDefaultPlan (engines map -> mode/pipeline)
Pure function that converts a per-engine EngineToggle map + masterEnabled
flag into a { mode, stackedPipeline } plan: off when master is off or no
engines on; single-mode when exactly one single-mode engine is enabled;
stacked (sorted by stackPriority) otherwise.
* feat(compression): persist+backfill engines map and activeComboId (migration 102)
* feat(compression): resolveCompressionPlan precedence resolver (header>override>active>default)
* feat(compression): selectCompressionStrategy uses resolveCompressionPlan
* feat(api): settings/compression carries engines map + activeComboId
Extends compressionSettingsUpdateSchema with engines (Record<string,{enabled:boolean,level?:string}>)
and activeComboId (string|null) so the PUT route accepts and persists these fields.
GET already returns the full getCompressionSettings() object which includes both fields.
TDD: added route round-trip tests (PUT+GET) for engines, activeComboId, null clear,
and schema rejection of invalid engines shape.
* refactor(compression): default-combo route is a read-only shim (default derived from engines)
* feat(dashboard): engine-grid compression panel (single source for on/off + level)
* refactor(dashboard): remove duplicate compression toggles; per-engine pages keep only detailed config
* feat(compression): unified panel menu order + derived-pipeline integration coverage
* fix(compression): import ENGINE_IDS via types re-export so it resolves under vitest
The bare "@omniroute/open-sse/.../engineCatalog.ts" specifier resolves under tsc/tsx
but not under vitest's MCP config: Vite externalizes a brand-new open-sse module to
Node, which can't load the .ts subpath. types.ts is already in Vite's graph, so route
ENGINE_IDS through its re-export. Fixes 3 failing MCP vitest suites (cacheTools,
dbHealthTool, essentialTools).
* fix(compression): engines map drives dispatch only when explicitly panel-saved
Code-review finding: the legacy seeded default combo (present on every install via
migration 042/043) was silently overriding a panel-configured engines map — the
default-combo block in chatCore set compressionComboApplied=true, skipping the
engines-map override, so an operator's panel toggles were ignored.
Gate the engines-map path on a new runtime-only CompressionConfig.enginesExplicit
(true when a stored engines row exists). Panel-saved installs: the engines map is
authoritative (deriveDefaultPlanFromConfig + new enginesMapDerivesStackedPipeline
guard the chatCore default-combo block). Legacy/backfilled installs: the map is
display-only and dispatch stays on the historical defaultMode/default-combo path —
zero behaviour change until the operator opts in via the panel.
Also documents why resolveCacheAwareConfig's getCacheAwareStrategy(config.defaultMode)
arg is safe (skipSystemPrompt is mode-independent).
* docs(compression): add MDX frontmatter + escape inline brace to fix fumadocs build
docs/compression/**/*.md is compiled as MDX by the Next build (fumadocs,
source.config.ts). The two planning docs lacked the required `title`
frontmatter (build error: 'title: expected string, received undefined') and the
design doc had a bare {rtk,caveman} that MDX parsed as a JSX expression. Adds
frontmatter matching the sibling docs and backticks the brace. Fixes the
dast-smoke build step.
Future-reference 'Quick end-to-end check' in REMOTE-MODE.md: connect -> mint scoped
token -> route a command -> switch back -> tear down, with a placeholder host. Makes
explicit (and verified live) that `contexts remove` is LOCAL-only — it drops the saved
credential but does NOT revoke the server-side token; use `tokens revoke <id>` to kill
access. Also documents that `--yes` is required for non-interactive removal and that
removing the active context falls back to default.
A client (e.g. Fabric-AI) calling POST /v1/responses with `input: []`
used to be translated into `messages: []`, which every upstream Chat-
Completions provider rejects with `400: at least one message is required`
(surfaced to the client as a confusing 406).
Mirror the existing empty-string handling: when input[] is empty, inject
a single placeholder user message so the request is always valid. Touches
`openaiResponsesToOpenAIRequest` only (the same translator that already
covers the empty-string case at the top of the function), preserves any
caller-supplied `instructions` as a system message, and leaves every
non-empty input path byte-identical.
Adds a TDD test reproducing the empty input[] case (RED before fix, GREEN
after) and updates one pre-existing test that enshrined the broken
behavior (`assert.deepEqual(call.body.messages, [])`) to assert the new
correct shape.
Inspired-by: https://github.com/decolua/9router/pull/419
Co-authored-by: anuragg-saxenaa <anuragg.saxenaa@gmail.com>
OmniRoute already references gpt-4.1-mini, gpt-4.1-nano, o3-mini, and o4-mini
throughout sibling subsystems (cost estimator, modelCapabilities, taskFitness,
free-model catalog, multiple aggregator registries) but the direct openai
provider entry exposes only o3/gpt-4.1. Symmetrically, the gemini entry has
gemini-2.0-flash and gemini-3.1-flash-lite-preview but not the lite/lite-preview
siblings that pair with them. Inspired by an upstream effort to refresh both
static lists; scope is intentionally minimal:
- ADD openai: gpt-4.1-mini, gpt-4.1-nano, o3-mini, o4-mini
(o3-mini/o4-mini get REASONING_UNSUPPORTED, matching the o3 entry)
- ADD gemini: gemini-2.0-flash-lite, gemini-3-flash-lite-preview
SKIP (already present elsewhere — kept in their typed registries):
- TTS (tts-1, tts-1-hd, gpt-4o-mini-tts) -> audioRegistry.ts
- OpenAI embeddings (text-embedding-3-small/-large/ada-002) -> embeddingRegistry.ts
- Gemini embeddings (text-embedding-00*, gemini-embedding-*) -> embeddingRegistry.ts
- gemini-3.1-flash-image-preview -> imageRegistry.ts
SKIP (deliberate OmniRoute curation):
- gpt-5/gpt-5-mini/gpt-5-nano/gpt-5.1/gpt-5.2 (superseded by gpt-5.4 series)
- o1, o1-mini (superseded by o3)
- gpt-4-turbo (legacy; gpt-4o is the canonical mid-tier)
- o3-pro (no references anywhere in OmniRoute)
TDD: tests/unit/provider-registry-openai-gemini-expanded-models.test.ts
asserts the new ids and pins the existing ids so a future refactor cannot
silently drop them.
Inspired-by: https://github.com/decolua/9router/pull/398
Co-authored-by: Ibrahim Ryan <ryan@nuevanext.com>
api-airforce carries a real live https://api.airforce/v1/models catalog but was
left out of NAMED_OPENAI_STYLE_PROVIDERS, so the import route served its small
hardcoded seed (grok-3, grok-2-1212, claude-3.7-sonnet …) — models that no
longer exist upstream, so chat failed even though the connection test passed.
Add api-airforce to NAMED_OPENAI_STYLE_PROVIDERS (same shape as #4249/#4202/#3976
and the provider-model-sweep rows) so import does a live <baseUrl>/models fetch.
The registry seed stays as the offline fallback, so import never breaks if the
upstream is unreachable.
TDD: extends tests/unit/provider-sweep-live-discovery.test.ts (red proven: the
api-airforce case did not probe upstream and served local_catalog).
