docs(changelog): link EdgeTTS retirement PR

ee24799e7c froze 215 'pre-existing' errors measured on this devbox. The CI
artifact from run 32968510623 shows what actually happens on a clean npm ci:
ZERO unsuppressed errors and 150 suppressions that match nothing. The react-hooks
findings those entries described do not fire in CI at all — they are an artifact
of this machine's node_modules, the same phantom-count problem that once produced
a fabricated '925 errors' locally.

So the Lint job was not red because the repo had 215 hidden errors. It was red
because I froze errors that only exist on my machine, and ESLint exits 2 on a
suppression that no longer matches anything.

Rebuilt from the CI artifact (messages + suppressedMessages, which is where a
suppressed violation still shows up) instead of from a local lint: every count is
now the value CI observes. 150 rules removed, 102 files emptied and dropped, back
to the 1249 entries that predate the freeze. RequestLoggerV2's exhaustive-deps
keeps the committed 6 rather than the 7 I derived — 6 is the value the artifact
run demonstrably accepted, and a count above the real one is exactly what turns
this gate red.

The 9->6 prune in 7afacf6c21 stays: those three were genuinely dead, freed by
restoring the manual-model block, and CI agrees.

.env.example

@@ -65,6 +65,12 @@ INITIAL_PASSWORD=CHANGEME
 # OMNIROUTE_RELEASE_REF=origin/main
 # OMNIROUTE_ALLOW_CANARY_BUILD=1
 
+# Build-phase signal (#10060). Set to 1 by scripts/build/build-next-isolated.mjs and
+# inherited by every spawned build worker so the DB layer returns a no-op stub instead
+# of loading the native better-sqlite3 addon (which aborts the worker on exit).
+# Never set this for the running server. Used by: src/lib/buildPhase.ts, src/lib/db/core.ts
+# OMNIROUTE_BUILDING=1
+
 # Encryption key for SQLite database encryption at rest.
 # Used by: src/lib/db/encryption.ts — encrypts the entire SQLite database.
 # Generate: openssl rand -hex 32  |  Leave empty to disable DB encryption.
@@ -87,6 +93,10 @@ DISABLE_SQLITE_AUTO_BACKUP=false
 # Used by: src/shared/utils/rateLimiter.ts
 # Example: redis://localhost:6379 (or redis://redis:6379 in Docker)
 # REDIS_URL=redis://localhost:6379
+# Namespace prefix for ALL OmniRoute Redis keys (rate limiter + auth cache +
+# quota store). Prevents key collisions when OmniRoute shares a Redis instance
+# with other apps (e.g. on 127.0.0.1:6379). Default when unset: omniroute:
+# REDIS_KEY_PREFIX=omniroute:
 # Host interface docker-compose publishes the Redis sidecar on.
 # Default: 127.0.0.1 (loopback only). The compose Redis runs WITHOUT
 # `requirepass`, and app containers reach it over the compose network
@@ -229,6 +239,15 @@ PORT=20128
 # unaffected by this dev-only flag).
 OMNIROUTE_USE_TURBOPACK=1
 
+# Disable systemd sd_notify (Type=notify / WatchdogSec=) even when running
+# under a systemd unit with NOTIFY_SOCKET set.
+# Used by: scripts/dev/systemd-notify.mjs. Set to 1 to disable.
+# OMNIROUTE_DISABLE_SD_NOTIFY=1
+
+# Injected by systemd when running under a service unit (sd_notify protocol).
+# Read by scripts/dev/systemd-notify.mjs — never set this yourself.
+# NOTIFY_SOCKET=/run/systemd/notify
+
 # Skip the SQLite integrity health check on startup (faster boot on large DBs).
 # Used by: src/lib/db/core.ts, src/lib/db/healthCheck.ts. Set to 1 to skip.
 # OMNIROUTE_SKIP_DB_HEALTHCHECK=1
@@ -363,9 +382,8 @@ ALLOW_API_KEY_REVEAL=false
 # NO_LOG_API_KEY_IDS=key_abc123,key_def456
 
 # Fallback per-day request budget applied to API keys whose `rate_limits`
-# column is null. Default (unset/empty/malformed) preserves the legacy
-# 1000/day, 5000/week, 20000/month windows so existing deployments do not
-# silently lose rate limiting on upgrade.
+# column is null. Default (unset/empty) is unlimited (no implicit caps).
+# Malformed values preserve the legacy 1000/day, 5000/week, 20000/month windows.
 # Set explicitly to "0" to opt out entirely (unlimited fallback). Any
 # positive integer N enables N/day, 5N/week, 20N/month.
 # Used by: src/shared/utils/apiKeyPolicy.ts — checkRateLimit() fallback.
@@ -408,6 +426,15 @@ ALLOW_API_KEY_REVEAL=false
 # by OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT and the heap-pressure shed instead. Set a positive
 # value only on memory-constrained deployments that need a hard ceiling.
 # OMNIROUTE_CHAT_HARD_MAX_MESSAGES=0
+
+# Skip OmniRoute's local context-window and max-input-token check for direct
+# single-model requests. Default: false (dangerous opt-in).
+# The upstream provider still enforces its real limits, so enabling this can
+# replace an early OmniRoute 400 with an upstream context-length error.
+# Prompt compression and the model's own output-token cap remain active.
+# Also configurable from Dashboard > Settings > Feature Flags; no restart is
+# required. Used by: src/shared/utils/featureFlags.ts and open-sse/handlers/chatCore.ts.
+# DISABLE_CONTEXT_WINDOW_CHECKS=false
 # How long a heavy request waits for heavyweight capacity before a retryable 503.
 # A short bounded wait serializes agent bursts instead of an instant 503; 0 = instant.
 # Default 2000 (2s).
@@ -696,6 +723,11 @@ NEXT_PUBLIC_ENABLE_SOCKS5_PROXY=true
 # ALL_PROXY=socks5://127.0.0.1:7890
 # NO_PROXY=localhost,127.0.0.1
 
+# Pin the echo-IP target used by proxy egress probes. Unset, the probe tries
+# api64.ipify.org then api4.ipify.org so IPv4-only tunnels are not reported dead.
+# Used by: src/lib/proxyEchoTarget.ts.
+# OMNIROUTE_PROXY_ECHO_URL=https://api4.ipify.org?format=json
+
 # Max concurrent sockets per cached HTTP/SOCKS proxy dispatcher.
 # Long-lived SSE streams such as Codex /v1/responses need more than one
 # connection when multiple requests share the same account-level proxy.
@@ -876,13 +908,21 @@ NEXT_PUBLIC_ENABLE_SOCKS5_PROXY=true
 # Set to 0/false/off to skip compression entirely. Default: rtk
 # OMNIROUTE_MCP_DESCRIPTION_COMPRESSION=rtk
 
+# Abort budget (ms) for MCP-server internal management reads (health, resilience,
+# combos, quota, usage). Default: 10000. Used by: open-sse/mcp-server/fetchTimeout.ts
+# OMNIROUTE_MCP_FETCH_TIMEOUT_MS=10000
+
+# Abort budget (ms) for MCP hops that wait on a provider (route_request, web_search,
+# web_fetch). Default: 60000. Used by: open-sse/mcp-server/fetchTimeout.ts
+# OMNIROUTE_MCP_UPSTREAM_TIMEOUT_MS=60000
+
 # Model catalog sync interval in hours.
 # Used by: src/shared/services/modelSyncScheduler.ts — periodic model refresh.
 # Default: 24
 # MODEL_SYNC_INTERVAL_HOURS=24
 
 # Provider limits sync interval in minutes (rate limit windows, quotas).
-# Used by: src/server-init.ts — polls provider health endpoints.
+# Used by: src/lib/usage/providerLimits.ts — polls provider health endpoints.
 # Default: 70
 PROVIDER_LIMITS_SYNC_INTERVAL_MINUTES=70
 
@@ -987,6 +1027,16 @@ PROVIDER_LIMITS_SYNC_SPACING_MS=1500
 # Used by: open-sse/services/compression/engines/rtk/filterLoader.ts.  Default: 0.
 #OMNIROUTE_RTK_TRUST_PROJECT_FILTERS=0
 
+# Maximum concurrent synchronous compression workers. Excess jobs wait FIFO.
+# Used by: open-sse/services/compression/compressionWorkerPool.ts. Default: 2.
+#OMNI_COMPRESSION_WORKERS=2
+# Per-job worker timeout (ms). A timed-out worker is terminated and the request fails open.
+# Used by: open-sse/services/compression/compressionWorkerPool.ts. Default: 120000.
+#OMNI_COMPRESSION_WORKER_TIMEOUT_MS=120000
+# Terminate idle compression workers after this many milliseconds.
+# Used by: open-sse/services/compression/compressionWorkerPool.ts. Default: 60000.
+#OMNI_COMPRESSION_WORKER_IDLE_MS=60000
+
 # T02 stacked-pipeline engine circuit-breaker (OPT-IN, default off). When enabled, a compression
 # engine that throws repeatedly across requests is skipped (fail-open) for a cooldown.
 # Used by: open-sse/services/compression/pipelineEngineBreaker.ts.
@@ -1269,6 +1319,36 @@ CURSOR_USER_AGENT="Cursor/3.4"
 # set to true/1/yes to enable. Used by: open-sse/executors/codex.ts.
 # OMNIROUTE_CODEX_DROP_NONSTANDARD_EVENTS=true
 
+# Codex app-server WebSocket transport (opt-in). When a WebSocket URL and a
+# capability token are both provided, Codex requests are routed through a local
+# `codex app-server` sidecar over JSON-RPC instead of the HTTP Responses API.
+# Each var is also settable per-connection via providerSpecificData; the env var
+# is the process-wide fallback. Used by:
+# open-sse/executors/codex/appServerConfig.ts.
+#
+# WebSocket endpoint of the codex app-server (ws:// or wss://). Required to
+# enable the transport; leaving it unset keeps Codex on its HTTP transports.
+# OMNIROUTE_CODEX_APPSERVER_WS=ws://127.0.0.1:8081
+# Inline capability/bearer token presented to the app-server.
+# OMNIROUTE_CODEX_APPSERVER_WS_TOKEN=deadbeef...
+# Path to a file holding the capability token (produced by
+# `codex app-server --ws-token-file <path>`). Used when the inline token above
+# is not set.
+# OMNIROUTE_CODEX_APPSERVER_WS_TOKEN_FILE=/run/codex-ws-token
+# Working directory the app-server turn runs in (defaults to /tmp).
+# OMNIROUTE_CODEX_APPSERVER_CWD=/tmp
+# Approval policy passed to the app-server turn (e.g. never, on-request).
+# OMNIROUTE_CODEX_APPSERVER_APPROVAL=never
+# Sandbox policy passed to the app-server turn (e.g. read-only,
+# workspace-write, danger-full-access). When unset, the executor defaults to
+# "workspace-write" (hardened; used to be "danger-full-access").
+# OMNIROUTE_CODEX_APPSERVER_SANDBOX=read-only
+# Auto-approve the app-server's own approval prompts (command/file/permission
+# execution on the host). Defaults to OFF — prompts are auto-denied. Set to
+# true/1/yes only when you trust the deployment to run codex-decided host
+# commands. Per-connection override: providerSpecificData.codexAppServerAutoApprove.
+# OMNIROUTE_CODEX_APPSERVER_AUTO_APPROVE=false
+
 # ═══════════════════════════════════════════════════════════════════════════════
 # 13. CLI FINGERPRINT COMPATIBILITY (Anti-Detection)
 # ═══════════════════════════════════════════════════════════════════════════════
@@ -1352,6 +1432,14 @@ CURSOR_USER_AGENT="Cursor/3.4"
 # FETCH_BODY_TIMEOUT_MS=600000       # Time to receive full response body
 # FETCH_CONNECT_TIMEOUT_MS=30000     # TCP connection establishment (default: 30s)
 # FETCH_KEEPALIVE_TIMEOUT_MS=4000    # Keep-alive socket idle timeout (default: 4s)
+# OMNIROUTE_DIRECT_HEADERS_TIMEOUT_MS=30000  # Bounded response-start window per direct
+#                                     # (no-proxy) attempt (#10214). A silently-dropped
+#                                     # pooled keep-alive socket surfaces no transport
+#                                     # error, so without this bound a direct request can
+#                                     # stall until undici's headersTimeout (600s) or the
+#                                     # caller's deadline; on expiry the request retries
+#                                     # once on a fresh no-keep-alive socket. 0 disables
+#                                     # the bound (default: 30000 = 30s).
 
 # Default timeout (ms) for src/shared/utils/fetchTimeout.ts. Acts as the
 # fallback when FETCH_TIMEOUT_MS is unset. Default: 120000 (2 min).
@@ -1406,6 +1494,14 @@ CURSOR_USER_AGENT="Cursor/3.4"
 # OMNIROUTE_PPLX_TLS_TIMEOUT_MS=30000
 # OMNIROUTE_PPLX_TLS_GRACE_MS=10000
 
+# ── Perplexity web: built-in-search hint ──
+# Used by: open-sse/executors/perplexity-web/protocol.ts — appends "You have
+# built-in web search. Answer questions directly using search results." to the
+# caller's system message. Off by default: Perplexity's answer engine searches
+# anyway, and for coding clients the sentence leaks into replies as
+# meta-commentary. Set to 1/true/yes/on to restore the old behavior.
+# OMNIROUTE_PPLX_SEARCH_HINT=0
+
 # ── Grok web TLS sidecar (Chrome-fingerprinted client) ──
 # Used by: open-sse/services/grokTlsClient.ts — wire-level timeout for the
 # bogdanfinn/tls-client koffi binding and the JS-side grace window layered on
@@ -1436,6 +1532,20 @@ CURSOR_USER_AGENT="Cursor/3.4"
 # OMNIROUTE_BROWSER_POOL=on
 # WEB_COOKIE_USE_BROWSER=0
 
+# ── Kimi Web (international kimi.ai Connect-RPC) ──
+# Used by: open-sse/executors/kimi-web.ts. Override the base/chat URLs only if
+# you need a mirror or proxy endpoint; defaults target https://www.kimi.ai with
+# the Connect-RPC chat path /apiv2/kimi.gateway.chat.v1.ChatService/Chat.
+# KIMI_WEB_BASE_URL=https://www.kimi.ai
+# KIMI_WEB_CHAT_URL=https://www.kimi.ai/apiv2/kimi.gateway.chat.v1.ChatService/Chat
+
+# When OIDC is enabled, disable password login so users can only authenticate
+# via OIDC Single Sign-On. The bare alias OIDC_DISABLE_PASSWORD_LOGIN is also
+# accepted; the Dashboard Feature Flag takes precedence. Used by:
+# src/app/api/auth/login/route.ts, src/app/api/settings/require-login/route.ts.
+# OMNIROUTE_OIDC_DISABLE_PASSWORD_LOGIN=false
+# OIDC_DISABLE_PASSWORD_LOGIN=false
+
 # ── Adobe Firefly browser sign-in (system Chrome/Edge CDP) ──
 # Used by: open-sse/services/adobeFireflyBrowserLogin.ts. The Firefly login
 # flow drives a real, system-installed Chrome or Microsoft Edge via CDP so the
@@ -1880,10 +1990,6 @@ APP_LOG_TO_FILE=true
 # Default: 300000 (5 minutes)
 # SEARCH_CACHE_TTL_MS=300000
 
-# ── OpenAI-compatible multi-connection ──
-# Allow multiple simultaneous connections per OpenAI-compatible provider node.
-# Used by: src/app/api/providers/route.ts
-# ALLOW_MULTI_CONNECTIONS_PER_COMPAT_NODE=false
 
 # ── CC-compatible provider (experimental) ──
 # Enable the Claude Code compatible provider endpoint.
@@ -1915,6 +2021,9 @@ APP_LOG_TO_FILE=true
 # CLIPROXYAPI_HOST=127.0.0.1
 # CLIPROXYAPI_PORT=5544
 # CLIPROXYAPI_CONFIG_DIR=~/.cli-proxy-api
+# Management key for an externally managed instance. Embedded instances use
+# OmniRoute's encrypted service key.
+# CLIPROXYAPI_MANAGEMENT_KEY=
 
 # ── Mux embedded service ──
 # Override the port where the embedded Mux (coder/mux) agent-orchestration
@@ -1979,6 +2088,16 @@ APP_LOG_TO_FILE=true
 # Reachability probe target for the scheduler and the auto-test endpoint.
 # Point it at an internal/self-hosted URL to avoid the public default.
 # PROXY_HEALTH_TEST_URL=https://httpbin.org/ip
+# Probes started at once per batch, for the scheduler and the auto-test endpoint.
+# Floored at 1 and capped at 50. Default: 10.
+# PROXY_HEALTH_TEST_CONCURRENCY=10
+# Delay in ms between two probe departures inside a batch. Without it the whole batch
+# leaves at once and a shared egress IP can trip a rate-limited target. 0 disables the
+# spacing; capped at 5000. Default: 100.
+# PROXY_HEALTH_TEST_STAGGER_MS=100
+# Set "false" to stop probing the real host of a proxy's assigned provider (GET /models,
+# no API key) and always use the generic target above instead. Default: enabled.
+# PROXY_HEALTH_USE_PROVIDER_TARGET=true
 # Set "true" to let the scheduler auto-remove proxies after repeated failures.
 # PROXY_AUTO_REMOVE=false
 # Consecutive failures before an auto-remove fires. Default: 3.
@@ -2121,6 +2240,19 @@ APP_LOG_TO_FILE=true
 # Used by: open-sse/utils/cursorAgentCliVersion.ts. Default: detect local install, else pin.
 # CURSOR_AGENT_CLI_VERSION=2026.07.08-0c04a8a
 
+# Path to the Cursor Agent binary used for image generation.
+# Used by: open-sse/handlers/imageGeneration/providers (CURSOR_IMAGE.md).
+# CURSOR_AGENT_BIN=/path/to/agent
+
+# Cursor image-generation wall clock (ms). Default: 210000.
+# CURSOR_IMG_TIMEOUT_MS=210000
+
+# Shared-seat concurrency gate for Cursor image jobs. Default: 2.
+# CURSOR_IMG_MAX_CONCURRENT=2
+
+# Override Cursor CLI --model for image jobs. Default: request model / auto.
+# CURSOR_IMG_MODEL=auto
+
 # Cursor Agent CLI data directory override (versions live under <dir>/versions/).
 # Used by: open-sse/utils/cursorAgentCliVersion.ts. Default: ~/.local/share/cursor-agent (unix)
 # or %LOCALAPPDATA%\cursor-agent (win32). Official agent CLI also honors this var.
@@ -2301,10 +2433,10 @@ APP_LOG_TO_FILE=true
 # test suite must NEVER mutate the OS trust store (a fake test PEM installed via
 # update-ca-certificates broke all system TLS on a persistent runner, 2026-07-05).
 # OMNIROUTE_SKIP_SYSTEM_TRUST=1
-# check-changelog-integrity.mjs (anti CHANGELOG-eat gate): explicit base ref
-# override, and the justified-removal escape hatch for intentional bullet removals.
+# check-changelog-integrity.mjs (anti CHANGELOG-eat gate): explicit base ref override.
+# Intentional transformations require an exact reviewed entry in
+# config/release/changelog-reconciliations.json; there is no runtime bypass.
 # CHANGELOG_BASE_REF=origin/release/v0.0.0
-# ALLOW_CHANGELOG_REMOVALS=1
 
 # ── Remote audio provider nodes ──
 # Used by: src/app/api/v1/_shared/audioProviderNodes.ts — lets the /v1/audio/*
@@ -2494,6 +2626,11 @@ APP_LOG_TO_FILE=true
 # intended to be published as `omniroute-secure`. See SECURITY.md.
 # OMNIROUTE_BUILD_PROFILE=full
 
+# Override the standalone build output directory consumed by the post-build
+# colocation step. Default: the real Next.js standalone output under .build/.
+# Used by: scripts/build/colocate-standalone.mjs (build tooling, not runtime).
+# OMNIROUTE_STANDALONE_DIR=
+
 # Skip emitting `.tar.gz` tarballs during optional-pack staging for the Electron
 # standalone tree (pack directories + optional-packs.index.json are still produced).
 # Used by the desktop release workflow to trim artifact upload size.
@@ -2508,6 +2645,8 @@ APP_LOG_TO_FILE=true
 # ELECTRON_SMOKE_DATA_DIR=
 # ELECTRON_SMOKE_KEEP_DATA=0
 # ELECTRON_SMOKE_STREAM_LOGS=0
+# #7592: second launch against the same DATA_DIR must pick the native driver.
+# ELECTRON_SMOKE_COLD_RESTART=0
 
 # Playground Studio
 # Default model used by the improve-prompt route (optional; falls back to model in request body).

.gitattributes

@@ -0,0 +1,11 @@
+# Shell scripts must always be checked out with LF line endings.
+#
+# On Windows, core.autocrlf=true converts text files to CRLF in the working
+# tree. Scripts that are kernel-exec'd (Docker ENTRYPOINT, bin/*.sh on Linux
+# hosts) then fail with `exec ...: no such file or directory` because the
+# shebang becomes "#!/bin/sh\r". eol=lf overrides autocrlf for these files.
+*.sh text eol=lf
+
+# This file must stay LF too: git parses it as-is, and a trailing CR would
+# corrupt every pattern (e.g. "*.sh\r" matches nothing).
+.gitattributes text eol=lf

.github/dependabot.yml

@@ -50,13 +50,13 @@ updates:
       # bumps; majors here need their own PR and a deliberate migration review.
       - dependency-name: "ioredis"
         update-types: ["version-update:semver-major"]
-      # @huggingface/transformers is HARD-PINNED at 3.5.2 (exact, no caret) — FROZEN.
-      # It is load-bearing for the LLMLingua ONNX compression engine (open-sse/services/
-      # compression/engines/llmlingua/ — worker.ts pins @huggingface/transformers@3.5.2)
-      # and for local memory embeddings (src/lib/memory/embedding/transformersLocal.ts),
-      # and was VPS-validated at 3.5.2 (#4014). 4.x breaks both, and even 3.x minors must
-      # be re-validated on the VPS — so freeze ALL auto-bumps (no update-types = ignore
-      # every version). Migrate it intentionally, not via dependabot (#4050).
+      # @huggingface/transformers is VPS-validated at ^4.2.0 (migrated intentionally in
+      # #9962). It is load-bearing for the LLMLingua ONNX compression engine (open-sse/
+      # services/compression/engines/llmlingua/ — @atjsh/llmlingua-2@2.0.5 peers on
+      # "@huggingface/transformers": "^3.5.2 || ^4.0.0") and for local memory embeddings
+      # (src/lib/memory/embedding/transformersLocal.ts). Further majors must be re-validated
+      # on the VPS — so keep auto-bumps frozen (no update-types = ignore every version).
+      # Migrate it intentionally, not via dependabot (#4050).
       - dependency-name: "@huggingface/transformers"
 
   - package-ecosystem: "github-actions"

.github/workflows/ci.yml

@@ -685,7 +685,50 @@ jobs:
       - run: npm run build:cli
       - name: Assert dist/server.js exists
         run: test -f dist/server.js || (echo "dist/server.js missing — build:cli did not assemble correctly" && exit 1)
+      # `build:cli` monta dist/ mas NAO grava dist/BUILD_SHA — so `build:release` faz
+      # isso, chamando write-build-sha.mjs. O guard de proveniencia do #10427, dentro
+      # de check:pack-artifact, rejeita um artefato sem SHA (e rejeita mesmo com
+      # OMNIROUTE_ALLOW_CANARY_BUILD=1: o que nao da para identificar nao da para
+      # vouchear). Sem este passo o par build+validate deste job e estruturalmente
+      # incompativel e falha 100% das vezes.
+      - name: Stamp dist/BUILD_SHA for the provenance guard (#10427)
+        # O SHA TEM de vir do head da PR, nao de `git rev-parse HEAD`. Este workflow
+        # roda em `pull_request`, entao o checkout e o MERGE COMMIT efemero que o
+        # GitHub cria — um commit que nao existe em branch nenhuma e portanto nunca e
+        # ancestral da release. O guard de proveniencia (#10427) rejeita exatamente
+        # isso, e com razao: um artefato carimbado com o merge commit nao pode ser
+        # rastreado ate codigo que passou pelos gates.
+        env:
+          OMNIROUTE_BUILD_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
+        run: |
+          export OMNIROUTE_BUILD_SHA="${OMNIROUTE_BUILD_SHA:0:7}"
+          node scripts/build/write-build-sha.mjs
+      # O guard de proveniencia checa ancestralidade contra `origin/main` por padrao.
+      # Esse e o ref certo na PUBLICACAO (npm-publish.yml roda em main), mas em
+      # `pull_request` e estruturalmente impossivel: enquanto a PR esta aberta o head
+      # dela NUNCA e ancestral de main — e o checkout raso nem traz `origin/main` para
+      # o grafo local, entao a sonda responde `false` de qualquer jeito. Resultado: o
+      # gate falhava 100% das vezes em PR. Pre-merge o unico invariante checavel e "o
+      # stamp corresponde a branch sob teste", entao apontamos o ref para o head da PR.
+      # Usamos `refs/pull/<N>/head` e nao `head.ref` porque aquele existe no PROPRIO
+      # origin mesmo quando a PR vem de um fork; `head.ref` so existe no repo do autor.
+      - name: Resolve the provenance ref for the pack gate (#10427)
+        id: provenance-ref
+        env:
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+        run: |
+          if [ -n "$PR_NUMBER" ]; then
+            git fetch --no-tags --depth=50 origin \
+              "+refs/pull/$PR_NUMBER/head:refs/remotes/origin/pr-head"
+            echo "ref=origin/pr-head" >> "$GITHUB_OUTPUT"
+          else
+            git fetch --no-tags --depth=50 origin \
+              "+refs/heads/$GITHUB_REF_NAME:refs/remotes/origin/$GITHUB_REF_NAME"
+            echo "ref=origin/$GITHUB_REF_NAME" >> "$GITHUB_OUTPUT"
+          fi
       - run: npm run check:pack-artifact
+        env:
+          OMNIROUTE_RELEASE_REF: ${{ steps.provenance-ref.outputs.ref }}
       # WS1.2 (#7065 class): pack the real tarball, install it into a clean prefix and
       # BOOT it to a healthy /api/monitoring/health — the gate that structure checks
       # cannot provide (3 releases shipped boot-crashing tarballs with green lists).
@@ -792,9 +835,23 @@ jobs:
       # D3 (plano mestre): a coverage é coletada NESTE mesmo run (c8/NODE_V8_COVERAGE propaga
       # aos filhos através do npm) — elimina a matrix Coverage Shard ×8, que re-executava a
       # suíte inteira só para medir o gate. Padrão usado pelo CI do próprio nodejs/node.
+      # Heap: os shards rodam sob instrumentacao de cobertura do V8, que retem muito
+      # mais memoria que a suite crua. Com o teto antigo de 4096 MB os shards passaram
+      # a abortar com SIGABRT (exit 134, "Ineffective mark-compacts near heap limit")
+      # ao redor de 4086 MB conforme o catalogo de providers cresceu no ciclo v3.8.50 —
+      # todos os testes passavam e o processo morria no fim, o que le como falha de
+      # teste sem ser. O teto vive em `test:unit:ci:shard` (package.json) e agora
+      # acompanha os 8192 MB ja usados pelas variantes nao-shardadas; os runners
+      # GitHub-hosted tem 16 GB.
       - name: Unit tests (shard ${{ matrix.shard }}/8) with V8 coverage
         env:
           TEST_SHARD: ${{ matrix.shard }}/8
+          # NODE_OPTIONS (nao so o flag em test:unit:ci:shard) porque quem estoura o
+          # heap e o processo `c8` que embrulha a suite — ele agrega ~577 MB de JSON
+          # de cobertura bruta. Subir o teto so no node filho deixa o pai no default
+          # do V8 (~4 GB) e o OOM continua igual, em ~4083 MB. Mesmo padrao ja usado
+          # pelo job de merge de cobertura mais abaixo.
+          NODE_OPTIONS: --max-old-space-size=8192
         run: |
           rm -rf coverage-shard coverage-shard-report
           npx c8 \

.github/workflows/codeql.yml

@@ -22,10 +22,10 @@ jobs:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           persist-credentials: false
-      - uses: github/codeql-action/init@5595ccaf912efad79be6eef63a5619ff05969be3 # v4.37.6
+      - uses: github/codeql-action/init@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd # v4.37.7
         with:
           languages: javascript-typescript
           queries: security-extended
-      - uses: github/codeql-action/analyze@5595ccaf912efad79be6eef63a5619ff05969be3 # v4.37.6
+      - uses: github/codeql-action/analyze@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd # v4.37.7
         with:
           category: "/language:javascript-typescript"

.github/workflows/dast-smoke.yml

@@ -46,6 +46,7 @@ jobs:
         env:
           PORT: "20128"
           INJECTION_GUARD_MODE: block
+          REQUIRE_API_KEY: "false"
         run: |
           node dist/server.js > server.log 2>&1 &
           echo $! > server.pid
@@ -64,16 +65,20 @@ jobs:
           # those 302s as "the API accepted a schema-violating request" and the configured-off
           # 400 as "rejected a schema-compliant request". Documenting the flow in the spec is
           # still right (operators need it); fuzzing it is not what this smoke is for.
+          # /api/auth/login has brute-force rate limiting: repeated failed logins return 429,
+          # which Schemathesis flags as rejection of schema-compliant requests.
           schemathesis run docs/openapi.yaml --url http://localhost:20128 \
             --include-path-regex '^/v1/(chat/completions|models)$|^/api/(auth|keys)' \
-            --exclude-path-regex '^/api/auth/oidc/' \
+            --exclude-path-regex '^/api/auth/(oidc/|login)' \
             --max-examples 8 --workers 4 --checks all --max-response-time 30 \
             --request-timeout 20 --suppress-health-check all --no-color
+      - name: Install promptfoo
+        run: npm install -g promptfoo@0.122.0
       - name: promptfoo injection-guard (blocking)
         env:
           OMNIROUTE_URL: http://localhost:20128
           OMNIROUTE_API_KEY: not-needed-blocked-before-upstream
-        run: npx --yes promptfoo@latest eval -c promptfooconfig.yaml --no-cache
+        run: promptfoo eval -c promptfooconfig.yaml --no-cache
       - name: Stop server
         if: always()
         run: kill "$(cat server.pid)" || true

.github/workflows/docker-publish.yml

@@ -183,15 +183,55 @@ jobs:
         env:
           DOCKER_BUILDKIT_INLINE_CACHE: 1
 
+      - name: Build and push BUN base platform image by digest
+        id: build-bun-base
+        uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7
+        with:
+          context: .
+          file: Dockerfile.bun
+          target: runner-base
+          platforms: ${{ matrix.platform }}
+          outputs: type=image,push-by-digest=true,name-canonical=true,push=true
+          tags: |
+            ${{ env.IMAGE_NAME }}
+            ${{ env.GHCR_IMAGE_NAME }}
+          cache-from: type=gha,scope=docker-bun-base-${{ matrix.arch }}
+          cache-to: type=gha,scope=docker-bun-base-${{ matrix.arch }},mode=max
+          no-cache: false
+        env:
+          DOCKER_BUILDKIT_INLINE_CACHE: 1
+
+      - name: Build and push BUN web platform image by digest
+        id: build-bun-web
+        uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7
+        with:
+          context: .
+          file: Dockerfile.bun
+          target: runner-web
+          platforms: ${{ matrix.platform }}
+          outputs: type=image,push-by-digest=true,name-canonical=true,push=true
+          tags: |
+            ${{ env.IMAGE_NAME }}
+            ${{ env.GHCR_IMAGE_NAME }}
+          cache-from: type=gha,scope=docker-bun-web-${{ matrix.arch }}
+          cache-to: type=gha,scope=docker-bun-web-${{ matrix.arch }},mode=max
+          no-cache: false
+        env:
+          DOCKER_BUILDKIT_INLINE_CACHE: 1
+
       - name: Export digests
         env:
           DIGEST_BASE: ${{ steps.build.outputs.digest }}
           DIGEST_WEB: ${{ steps.build-web.outputs.digest }}
+          DIGEST_BUN_BASE: ${{ steps.build-bun-base.outputs.digest }}
+          DIGEST_BUN_WEB: ${{ steps.build-bun-web.outputs.digest }}
         run: |
           set -euo pipefail
-          mkdir -p /tmp/digests/base /tmp/digests/web
+          mkdir -p /tmp/digests/base /tmp/digests/web /tmp/digests/bun-base /tmp/digests/bun-web
           touch "/tmp/digests/base/${DIGEST_BASE#sha256:}"
           touch "/tmp/digests/web/${DIGEST_WEB#sha256:}"
+          touch "/tmp/digests/bun-base/${DIGEST_BUN_BASE#sha256:}"
+          touch "/tmp/digests/bun-web/${DIGEST_BUN_WEB#sha256:}"
 
       - name: Upload base digests
         uses: actions/upload-artifact@v7
@@ -209,6 +249,22 @@ jobs:
           if-no-files-found: error
           retention-days: 1
 
+      - name: Upload bun-base digests
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: digests-bun-base-${{ matrix.arch }}
+          path: /tmp/digests/bun-base/*
+          if-no-files-found: error
+          retention-days: 1
+
+      - name: Upload bun-web digests
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: digests-bun-web-${{ matrix.arch }}
+          path: /tmp/digests/bun-web/*
+          if-no-files-found: error
+          retention-days: 1
+
   merge:
     name: Publish multi-arch manifests
     needs:
@@ -263,6 +319,20 @@ jobs:
           path: /tmp/digests/web
           merge-multiple: true
 
+      - name: Download bun-base digests
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
+        with:
+          pattern: digests-bun-base-*
+          path: /tmp/digests/bun-base
+          merge-multiple: true
+
+      - name: Download bun-web digests
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
+        with:
+          pattern: digests-bun-web-*
+          path: /tmp/digests/bun-web
+          merge-multiple: true
+
       - name: Create Docker Hub manifest
         run: |
           set -euo pipefail
@@ -286,6 +356,8 @@ jobs:
 
           create_manifest "${IMAGE_NAME}" "" /tmp/digests/base
           create_manifest "${IMAGE_NAME}" "-web" /tmp/digests/web
+          create_manifest "${IMAGE_NAME}" "-bun" /tmp/digests/bun-base
+          create_manifest "${IMAGE_NAME}" "-web-bun" /tmp/digests/bun-web
 
       - name: Create GHCR manifest
         run: |
@@ -310,6 +382,8 @@ jobs:
 
           create_manifest "${GHCR_IMAGE_NAME}" "" /tmp/digests/base
           create_manifest "${GHCR_IMAGE_NAME}" "-web" /tmp/digests/web
+          create_manifest "${GHCR_IMAGE_NAME}" "-bun" /tmp/digests/bun-base
+          create_manifest "${GHCR_IMAGE_NAME}" "-web-bun" /tmp/digests/bun-web
 
       - name: Inspect image
         if: needs.prepare.outputs.version != 'main'
@@ -372,7 +446,7 @@ jobs:
       - name: Upload Trivy SARIF to Security tab
         if: needs.prepare.outputs.version != 'main'
         continue-on-error: true
-        uses: github/codeql-action/upload-sarif@v4.37.6
+        uses: github/codeql-action/upload-sarif@v4.37.7
         with:
           sarif_file: trivy-results.sarif
           category: trivy-image

.github/workflows/electron-release.yml

@@ -279,9 +279,14 @@ jobs:
 
       - name: Smoke packaged Electron app (Linux)
         if: matrix.platform == 'linux'
+        # #7592: also cold-restart against the same DATA_DIR and assert a
+        # native SQLite driver (not the sql.js WASM fallback) is selected on
+        # the second launch — blocking here since Linux has no Windows-style
+        # sandbox caveats that would make it flaky.
         env:
           ELECTRON_SMOKE_TIMEOUT_MS: 60000
           ELECTRON_SMOKE_STREAM_LOGS: "1"
+          ELECTRON_SMOKE_COLD_RESTART: "1"
         run: xvfb-run -a npm run electron:smoke:packaged
 
       - name: Collect installers

.github/workflows/opencode-plugin-ci.yml

@@ -2,11 +2,11 @@ name: opencode-plugin CI
 
 on:
   push:
-    branches: [main, release/v3.8.2]
+    branches: [main, "release/**"]
     paths:
       - "@omniroute/opencode-plugin/**"
   pull_request:
-    branches: [main, release/v3.8.2]
+    branches: [main, "release/**"]
     paths:
       - "@omniroute/opencode-plugin/**"
     types: [opened, synchronize, reopened, ready_for_review]

.gitignore

@@ -14,6 +14,7 @@ _tasks/
 .agents/**
 .claude/**
 .gemini/**
+.code-forge/**
 .config/**
 .data/**
 .logs/**
@@ -291,3 +292,4 @@ docker-compose.yml.bak
 
 # Ad-hoc test sandboxes (never tracked — may contain local DBs)
 /.sandbox/
+.aider*

.gitleaks.toml

@@ -92,5 +92,9 @@
       # - x-api-key PUBLICO do Firefly web (documentado em open-sse/utils/publicCreds.ts:207);
       #   as duas ocorrencias sinalizadas estao em COMENTARIOS JSDoc, o runtime le de resolvePublicCred().
       '''omniroute-kimi-sponsor-banner-dismissed-v\d+''',
+      # CheaperInference sponsor banner localStorage key (upstream #11196 /
+      # eb5797370). Same UI-identifier pattern as the kimi banner above, not a
+      # credential; the generic-api-key rule flags the long hyphenated string.
+      '''omniroute-cheaperinference-sponsor-banner-dismissed-v\d+''',
       '''SunbreakWebUI1''',
     ]

@omniroute/opencode-plugin/package.json

@@ -23,7 +23,7 @@
   "scripts": {
     "build": "tsup",
     "clean": "rm -rf dist",
-    "test": "node --import tsx/esm --test tests/scaffold.test.ts tests/auth.test.ts tests/options-schema.test.ts tests/multi-instance.test.ts tests/fetch-interceptor.test.ts tests/provider.test.ts tests/gemini-sanitize.test.ts tests/combos.test.ts tests/config-shim.test.ts tests/features.test.ts tests/feature-defaults.test.ts tests/usable-combo.test.ts tests/disk-snapshot-perms.test.ts tests/fork-features.test.ts tests/auto-combo-context.test.ts tests/provider-id-routing.test.ts tests/management-read-token.test.ts tests/auto-sync.test.ts tests/model-allowlist.test.ts tests/log-level.test.ts",
+    "test": "node --import tsx/esm --test tests/scaffold.test.ts tests/auth.test.ts tests/options-schema.test.ts tests/multi-instance.test.ts tests/fetch-interceptor.test.ts tests/provider.test.ts tests/gemini-sanitize.test.ts tests/combos.test.ts tests/config-shim.test.ts tests/features.test.ts tests/feature-defaults.test.ts tests/usable-combo.test.ts tests/disk-snapshot-perms.test.ts tests/fork-features.test.ts tests/auto-combo-context.test.ts tests/provider-id-routing.test.ts tests/management-read-token.test.ts tests/auto-sync.test.ts tests/model-allowlist.test.ts tests/log-level.test.ts tests/effort-tier-variants.test.ts",
     "prepublishOnly": "npm run clean && npm run build && npm test"
   },
   "keywords": [

@omniroute/opencode-plugin/src/index.ts

@@ -76,6 +76,17 @@ import {
   type FreeModelFreeType,
 } from "./naming.js";
 
+/**
+ * Minimal leveled logger sink accepted by the default fetchers and the static
+ * catalog builder. A full `Logger` satisfies it structurally; the config hook
+ * injects the same partial shape (see `createOmniRouteConfigHook` deps).
+ */
+type OmniRouteLoggerSink = {
+  error?: (message: string, ...args: unknown[]) => void;
+  warn: (message: string, ...args: unknown[]) => void;
+  debug?: (message: string, ...args: unknown[]) => void;
+};
+
 /**
  * Zod schema for plugin options accepted as the second element of the
  * `plugin: [name, opts]` tuple in opencode.json. Strict by design — unknown
@@ -791,13 +802,18 @@ export async function forceSyncOmniRouteModels(args: {
       try {
         rawCombos = await combosFetcher(auth.baseURL, auth.managementReadToken, 10_000);
       } catch (err) {
-        console.warn("[omniroute-plugin] force sync: combos fetch failed", err);
+        logger.warn("force sync: combos fetch failed", err);
       }
     }
     let rawAutoCombos: OmniRouteRawAutoCombo[] = [];
     if (wantAutoCombos) {
       try {
-        rawAutoCombos = await autoCombosFetcher(auth.baseURL, auth.managementReadToken, 5_000);
+        rawAutoCombos = await autoCombosFetcher(
+          auth.baseURL,
+          auth.managementReadToken,
+          5_000,
+          logger
+        );
       } catch {
         /* soft-fail */
       }
@@ -1089,7 +1105,7 @@ export const OmniRoutePlugin: Plugin = async (_input, options) => {
 
   return {
     auth: createOmniRouteAuthHook(resolved),
-    provider: createOmniRouteProviderHook(resolved, { cache: sharedCache }),
+    provider: createOmniRouteProviderHook(resolved, { cache: sharedCache, logger }),
     config: configWithSyncCommand,
     tool: {
       omniroute_sync_models: syncTool,
@@ -1145,6 +1161,8 @@ export interface OmniRouteRawModelEntry {
     attachment?: boolean;
     structured_output?: boolean;
     temperature?: boolean;
+    /** Runtime-learned or synced reasoning tiers (server-gated, blind-mapped). */
+    effort_tiers?: string[];
   };
   release_date?: string;
   last_updated?: string;
@@ -1286,6 +1304,18 @@ export function mapRawModelToModelV2(
   ctx: { providerId: string; baseURL: string; apiFormat?: { anthropicPrefixes?: string[] } }
 ): ModelV2 {
   const caps = raw.capabilities ?? {};
+  // effort_tiers loop: server-declared tiers become ModelV2 variants so the
+  // UI offers exactly the tiers OmniRoute vouches for (instead of opencode's
+  // invented [low, medium, high] fallback). Blind: filtering/exclusion rules
+  // live server-side. Absent/empty/malformed => key omitted ENTIRELY (an
+  // empty variants object would suppress opencode's fallback for this model).
+  const declaredTiers = Array.isArray(caps.effort_tiers)
+    ? caps.effort_tiers.filter((t): t is string => typeof t === "string" && t.length > 0)
+    : [];
+  const variants =
+    declaredTiers.length > 0
+      ? Object.fromEntries(declaredTiers.map((tier) => [tier, { reasoningEffort: tier }]))
+      : undefined;
   const inMods = new Set(raw.input_modalities ?? ["text"]);
   const outMods = new Set(raw.output_modalities ?? ["text"]);
 
@@ -1294,10 +1324,12 @@ export function mapRawModelToModelV2(
     // `(providerID, modelID)`. If the raw id is already provider-prefixed
     // (e.g. `cc/claude-opus-4-7` from the `cc` Claude Code alias, or
     // `nvidia/llama-3-70b` from a provider that ships prefixed ids), leave
-    // it as-is — double-prefixing breaks OC's lookup. Otherwise prefix with
-    // the resolved `providerId` so a bare key like `claude-opus-4` parses as
-    // `(omniroute, claude-opus-4)` and the credentials resolve correctly.
-    id: raw.id.includes("/") ? raw.id : `${ctx.providerId}/${raw.id}`,
+    // it as-is — double-prefixing breaks OC's lookup. Bare **combo** ids
+    // (`owned_by: "combo"`, e.g. `gpt-5.6-sol`) must also stay unprefixed:
+    // OpenCode looks up `-m <plugin>/<combo>` as model id `<combo>` under
+    // the plugin provider (#10345). Other bare ids still prefix with
+    // `providerId` so credentials resolve as `(omniroute, model)`.
+    id: raw.id.includes("/") || raw.owned_by === "combo" ? raw.id : `${ctx.providerId}/${raw.id}`,
     /**
      * Display name. Falls back to raw.id when no enrichment is available;
      * the caller (`createOmniRouteProviderHook`) overlays
@@ -1336,6 +1368,7 @@ export function mapRawModelToModelV2(
       ...(typeof raw.max_input_tokens === "number" ? { input: raw.max_input_tokens } : {}),
       output: typeof raw.max_output_tokens === "number" ? raw.max_output_tokens : 0,
     },
+    ...(variants ? { variants } : {}),
     status: "active",
     options: {},
     headers: {},
@@ -1671,7 +1704,8 @@ export interface OmniRouteRawAutoCombo {
 export type OmniRouteAutoCombosFetcher = (
   baseURL: string,
   apiKey: string,
-  timeoutMs?: number
+  timeoutMs?: number,
+  logger?: OmniRouteLoggerSink
 ) => Promise<OmniRouteRawAutoCombo[]>;
 
 /**
@@ -1683,9 +1717,11 @@ export type OmniRouteAutoCombosFetcher = (
 export const defaultOmniRouteAutoCombosFetcher: OmniRouteAutoCombosFetcher = async (
   baseURL,
   apiKey,
-  timeoutMs = 5_000
+  timeoutMs = 5_000,
+  logger?: OmniRouteLoggerSink
 ) => {
   if (!apiKey || !baseURL) return [];
+  const log = logger ?? _logger;
 
   const trimmed = trimTrailingSlashes(baseURL);
   const root = trimmed.replace(/\/v\d+$/, "");
@@ -1704,15 +1740,11 @@ export const defaultOmniRouteAutoCombosFetcher: OmniRouteAutoCombosFetcher = asy
     });
     // 404 = endpoint not deployed yet — expected during rollout
     if (res.status === 404) {
-      console.warn(
-        `[omniroute-plugin] /api/combos/auto not available (404) — auto combos disabled`
-      );
+      log.warn(`/api/combos/auto not available (404) — auto combos disabled`);
       return [];
     }
     if (!res.ok) {
-      console.warn(
-        `[omniroute-plugin] /api/combos/auto failed: ${res.status} ${res.statusText} — auto combos disabled`
-      );
+      log.warn(`/api/combos/auto failed: ${res.status} ${res.statusText} — auto combos disabled`);
       return [];
     }
     const body = (await res.json()) as unknown;
@@ -1730,8 +1762,8 @@ export const defaultOmniRouteAutoCombosFetcher: OmniRouteAutoCombosFetcher = asy
     return out;
   } catch (err) {
     // Network error, timeout, abort — all non-fatal
-    console.warn(
-      `[omniroute-plugin] /api/combos/auto fetch failed: ${err instanceof Error ? err.message : String(err)} — auto combos disabled`
+    log.warn(
+      `/api/combos/auto fetch failed: ${err instanceof Error ? err.message : String(err)} — auto combos disabled`
     );
     return [];
   } finally {
@@ -2930,10 +2962,7 @@ export function passesModelAllowlist(
  * filter is set, all combos pass. Combos with zero resolvable members pass
  * (mirrors `isUsableCombo` semantics).
  */
-export function passesComboAllowlist(
-  combo: OmniRouteRawCombo,
-  visible?: ModelListFilter
-): boolean {
+export function passesComboAllowlist(combo: OmniRouteRawCombo, visible?: ModelListFilter): boolean {
   if (!visible) return true;
   const steps = Array.isArray(combo.models) ? combo.models : [];
   if (steps.length === 0) return true;
@@ -3125,9 +3154,15 @@ export function createOmniRouteProviderHook(
     providersFetcher?: OmniRouteProvidersFetcher;
     now?: () => number;
     cache?: OmniRouteFetchCache;
+    logger?: _Logger;
   } = {}
 ): ProviderHook {
   const resolved = resolveOmniRoutePluginOptions(opts);
+  const logger =
+    deps.logger ??
+    createLogger(
+      resolved.features?.startupDebug ? "debug" : (resolved.features?.logLevel ?? "warn")
+    );
   const fetcher = deps.fetcher ?? defaultOmniRouteModelsFetcher;
   // T-05: combo discovery merges `/api/combos` entries into the same map as
   // `/v1/models`. Default fetcher is declared further down the file; the
@@ -3201,8 +3236,8 @@ export function createOmniRouteProviderHook(
           : undefined) ??
         "";
       if (!baseURL) {
-        console.warn(
-          `[omniroute-plugin] provider.models(${resolved.providerId}): ` +
+        logger.error(
+          `provider.models(${resolved.providerId}): ` +
             `no baseURL resolvable — checked plugin opts, auth.json, and provider config. ` +
             `Set baseURL in opencode.json plugin options or run \`opencode connect ${resolved.providerId}\` with a baseURL.`
         );
@@ -3233,8 +3268,8 @@ export function createOmniRouteProviderHook(
         rawModels = await fetcher(baseURL, apiKey, 10_000);
 
         // T-05: combos fetch is best-effort, gated by features.combos.
-        // Soft-fail on any error: emit a console.warn and fall back to a
-        // models-only catalog. Rationale: /api/combos requires a
+        // Soft-fail on any error: emit a warn-level diagnostic and fall back
+        // to a models-only catalog. Rationale: /api/combos requires a
         // management-scoped key and OmniRoute may not have any combos
         // provisioned. Hard-failing when combos are optional would
         // silently hide the whole provider from OC's picker.
@@ -3243,10 +3278,7 @@ export function createOmniRouteProviderHook(
           try {
             rawCombos = await combosFetcher(baseURL, managementReadToken, 10_000);
           } catch (err) {
-            console.warn(
-              "[omniroute-plugin] combos fetch failed, falling back to models-only catalog",
-              err
-            );
+            logger.warn("combos fetch failed, falling back to models-only catalog", err);
           }
         }
 
@@ -3256,7 +3288,7 @@ export function createOmniRouteProviderHook(
         rawAutoCombos = [];
         if (wantAutoCombos) {
           try {
-            rawAutoCombos = await autoCombosFetcher(baseURL, managementReadToken, 5_000);
+            rawAutoCombos = await autoCombosFetcher(baseURL, managementReadToken, 5_000, logger);
           } catch {
             // Already handled inside the default fetcher — this catch
             // is belt-and-suspenders for injected stubs.
@@ -3270,10 +3302,7 @@ export function createOmniRouteProviderHook(
           try {
             rawEnrichment = await enrichmentFetcher(baseURL, managementReadToken, 10_000);
           } catch (err) {
-            console.warn(
-              "[omniroute-plugin] enrichment fetch failed, falling back to raw ids",
-              err
-            );
+            logger.warn("enrichment fetch failed, falling back to raw ids", err);
           }
         }
 
@@ -3288,7 +3317,7 @@ export function createOmniRouteProviderHook(
               10_000
             );
           } catch (err) {
-            console.warn("[omniroute-plugin] compression-metadata fetch failed", err);
+            logger.warn("compression-metadata fetch failed", err);
           }
         }
 
@@ -3302,8 +3331,8 @@ export function createOmniRouteProviderHook(
           try {
             rawConnections = await providersFetcher(baseURL, managementReadToken, 10_000);
           } catch (err) {
-            console.warn(
-              "[omniroute-plugin] /api/providers fetch failed; usableOnly filter disabled for this refresh",
+            logger.warn(
+              "/api/providers fetch failed; usableOnly filter disabled for this refresh",
               err
             );
           }
@@ -3322,8 +3351,9 @@ export function createOmniRouteProviderHook(
         // Debug breadcrumb: surface fetch result so operators can confirm
         // the dynamic pipeline fired and how much catalog OmniRoute returned.
         // Emitted once per cache miss (TTL refresh) — quiet on cache hits.
-        console.warn(
-          `[omniroute-plugin] catalog refreshed for providerId=${resolved.providerId} baseURL=${baseURL}: ` +
+        // Info-level: hidden at the default `warn` level (see #8982).
+        logger.info(
+          `catalog refreshed for providerId=${resolved.providerId} baseURL=${baseURL}: ` +
             `${rawModels.length} models + ${rawCombos.length} combos + ` +
             `${rawEnrichment.size} enrichment entries + ` +
             `${rawCompressionCombos.length} compression combos + ` +
@@ -3603,9 +3633,7 @@ export function createOmniRouteProviderHook(
               const dedupeKey = `${cacheKey}::${comboKey}`;
               if (!collisionWarned.has(dedupeKey)) {
                 collisionWarned.add(dedupeKey);
-                console.warn(
-                  `[omniroute-plugin] combo key "${comboKey}" collides with a model id; combo wins.`
-                );
+                logger.warn(`combo key "${comboKey}" collides with a model id; combo wins.`);
               }
             }
           }
@@ -3623,8 +3651,8 @@ export function createOmniRouteProviderHook(
       }
 
       if (pending.length > 0) {
-        console.warn(
-          `[omniroute-plugin] ${pending.length} combo(s) could not resolve all nested combo-refs after ${MAX_COMBO_PASSES} passes; they will advertise context=0 to avoid over-claiming.`
+        logger.warn(
+          `${pending.length} combo(s) could not resolve all nested combo-refs after ${MAX_COMBO_PASSES} passes; they will advertise context=0 to avoid over-claiming.`
         );
       }
 
@@ -4268,8 +4296,10 @@ export function buildStaticProviderEntry(
   enrichment?: OmniRouteEnrichmentMap,
   compressionCombos?: OmniRouteCompressionCombo[],
   connections?: OmniRouteProviderConnection[],
-  rawAutoCombos?: OmniRouteRawAutoCombo[]
+  rawAutoCombos?: OmniRouteRawAutoCombo[],
+  logger?: OmniRouteLoggerSink
 ): OmniRouteStaticProviderEntry {
+  const log = logger ?? _logger;
   const models: Record<string, OmniRouteStaticModelEntry> = {};
   const rawModelKeys = new Set<string>();
 
@@ -4647,8 +4677,8 @@ export function buildStaticProviderEntry(
   }
 
   if (pendingStatic.length > 0) {
-    console.warn(
-      `[omniroute-plugin] ${pendingStatic.length} combo(s) in the static catalog could not resolve all nested combo-refs after ${MAX_STATIC_COMBO_PASSES} passes; they will be omitted.`
+    log.warn(
+      `${pendingStatic.length} combo(s) in the static catalog could not resolve all nested combo-refs after ${MAX_STATIC_COMBO_PASSES} passes; they will be omitted.`
     );
   }
 
@@ -4669,9 +4699,7 @@ export function buildStaticProviderEntry(
         const isExpectedRawTwin = autoCombo.id === key && rawModelKeys.has(key);
         if (!isExpectedRawTwin && !reportedCollisions.has(key)) {
           reportedCollisions.add(key);
-          console.warn(
-            `[omniroute-plugin] auto combo key "${key}" collides with an existing model; auto combo wins.`
-          );
+          log.warn(`auto combo key "${key}" collides with an existing model; auto combo wins.`);
         }
       }
       models[key] = entry;
@@ -5342,7 +5370,8 @@ export function createOmniRouteConfigHook(
           warmSnapshot = snapshotResult;
           // Log snapshot age (accept any age — instant beats empty).
           const age = (snapshotResult as { writtenAt?: number }).writtenAt;
-          const ageLabel = typeof age === "number" ? `${Math.round((Date.now() - age) / 3_600_000)}h` : "unknown";
+          const ageLabel =
+            typeof age === "number" ? `${Math.round((Date.now() - age) / 3_600_000)}h` : "unknown";
           logAt(
             "warn",
             `config shim: warm startup from disk snapshot (${snapshotResult.rawModels.length} models, age ${ageLabel})`
@@ -5394,7 +5423,12 @@ export function createOmniRouteConfigHook(
         const doAutoCombos = async (): Promise<void> => {
           if (!wantAutoCombos) return;
           try {
-            localRawAutoCombos = await autoCombosFetcher(baseURL, managementReadToken, 5_000);
+            localRawAutoCombos = await autoCombosFetcher(
+              baseURL,
+              managementReadToken,
+              5_000,
+              logger
+            );
           } catch {
             // Already handled inside the default fetcher
           }
@@ -5415,7 +5449,11 @@ export function createOmniRouteConfigHook(
         const doCompression = async (): Promise<void> => {
           if (!wantCompressionMeta) return;
           try {
-            localRawCompressionCombos = await compressionMetaFetcher(baseURL, managementReadToken, 10_000);
+            localRawCompressionCombos = await compressionMetaFetcher(
+              baseURL,
+              managementReadToken,
+              10_000
+            );
           } catch (err) {
             logAt(
               "error",
@@ -5528,7 +5566,8 @@ export function createOmniRouteConfigHook(
             localRawEnrichment,
             localRawCompressionCombos,
             localRawConnections,
-            localRawAutoCombos
+            localRawAutoCombos,
+            logger
           );
           const inputWithProvider2 = input as { provider?: Record<string, unknown> };
           if (inputWithProvider2.provider) {
@@ -5618,7 +5657,8 @@ export function createOmniRouteConfigHook(
       rawEnrichment,
       rawCompressionCombos,
       rawConnections,
-      rawAutoCombos
+      rawAutoCombos,
+      logger
     );
 
     // Mutate the input.provider map. The Config type declares

@omniroute/opencode-plugin/tests/bare-combo-ids-10345.test.ts

@@ -0,0 +1,34 @@
+import test from "node:test";
+import assert from "node:assert/strict";
+
+import { mapRawModelToModelV2 } from "../src/index.ts";
+
+test("mapRawModelToModelV2: bare combo ids stay unprefixed (#10345)", () => {
+  const combo = mapRawModelToModelV2(
+    {
+      id: "gpt-5.6-sol",
+      owned_by: "combo",
+      context_length: 272000,
+      max_output_tokens: 8192,
+    },
+    { providerId: "omniroute", baseURL: "https://or.example.com/v1" }
+  );
+  assert.equal(combo.id, "gpt-5.6-sol");
+  assert.equal(combo.providerID, "omniroute");
+
+  const slashed = mapRawModelToModelV2(
+    {
+      id: "cx/gpt-5.6-sol",
+      owned_by: "combo",
+      context_length: 272000,
+    },
+    { providerId: "omniroute", baseURL: "https://or.example.com/v1" }
+  );
+  assert.equal(slashed.id, "cx/gpt-5.6-sol");
+
+  const ordinary = mapRawModelToModelV2(
+    { id: "claude-primary", context_length: 200000 },
+    { providerId: "omniroute", baseURL: "https://or.example.com/v1" }
+  );
+  assert.equal(ordinary.id, "omniroute/claude-primary");
+});

@omniroute/opencode-plugin/tests/effort-tier-variants.test.ts

@@ -0,0 +1,62 @@
+/**
+ * effort_tiers loop — plugin maps server-declared tiers to ModelV2 variants.
+ * Blind mapping (I3): no owned_by/provider knowledge here — the SERVER gates
+ * eligibility (shouldExposeSyncedEffortVariants). Absence semantics (M3):
+ * no tiers => NO variants key at all (an empty object would also kill
+ * opencode's own fallback for non-tiered models).
+ */
+import test from "node:test";
+import assert from "node:assert/strict";
+import { mapRawModelToModelV2, type OmniRouteRawModelEntry } from "../src/index.js";
+
+const CTX = { providerId: "omniroute", baseURL: "http://127.0.0.1:20128" } as const;
+
+test("maps declared tiers to reasoningEffort variants", () => {
+  const raw: OmniRouteRawModelEntry = {
+    id: "oc/x-preview-f-free",
+    owned_by: "opencode",
+    capabilities: { reasoning: true, effort_tiers: ["low", "high", "max"] },
+  };
+  const model = mapRawModelToModelV2(raw, { ...CTX });
+  const variants = (model as unknown as Record<string, unknown>).variants as
+    Record<string, Record<string, unknown>> | undefined;
+  assert.ok(variants, "variants key present when tiers declared");
+  assert.deepEqual(Object.keys(variants).sort(), ["high", "low", "max"]);
+  assert.deepEqual(variants.max, { reasoningEffort: "max" });
+  assert.deepEqual(variants.low, { reasoningEffort: "low" });
+});
+
+test("no tiers => NO variants key (not an empty object)", () => {
+  const raw: OmniRouteRawModelEntry = {
+    id: "plain-model",
+    capabilities: { reasoning: true },
+  };
+  const model = mapRawModelToModelV2(raw, { ...CTX }) as unknown as Record<string, unknown>;
+  assert.equal("variants" in model, false);
+});
+
+test("empty or malformed tiers array => NO variants key", () => {
+  const empty = mapRawModelToModelV2(
+    { id: "m", capabilities: { effort_tiers: [] } },
+    { ...CTX }
+  ) as unknown as Record<string, unknown>;
+  assert.equal("variants" in empty, false);
+
+  const junk = mapRawModelToModelV2(
+    { id: "m", capabilities: { effort_tiers: [42, null, "ok"] as unknown as string[] } },
+    { ...CTX }
+  ) as unknown as Record<string, unknown>;
+  const variants = junk.variants as Record<string, Record<string, unknown>> | undefined;
+  assert.deepEqual(Object.keys(variants ?? {}), ["ok"], "non-string tokens dropped");
+});
+
+test("static registry entry WITH tiers also gets variants (N1 blast radius)", () => {
+  const raw: OmniRouteRawModelEntry = {
+    id: "some-static-model",
+    owned_by: "registry",
+    capabilities: { effort_tiers: ["minimal", "high"] },
+  };
+  const model = mapRawModelToModelV2(raw, { ...CTX }) as unknown as Record<string, unknown>;
+  const variants = model.variants as Record<string, Record<string, unknown>> | undefined;
+  assert.deepEqual(Object.keys(variants ?? {}).sort(), ["high", "minimal"]);
+});

@omniroute/opencode-plugin/tests/log-level.test.ts

@@ -5,8 +5,14 @@ import { join } from "node:path";
 import test from "node:test";
 import type { Config } from "@opencode-ai/plugin";
 
-import { createOmniRouteConfigHook, OmniRoutePlugin } from "../src/index.js";
-import { getLogLevel, logger, setLogLevel, type LogLevel } from "../src/logger.js";
+import {
+  createOmniRouteConfigHook,
+  createOmniRouteProviderHook,
+  defaultOmniRouteAutoCombosFetcher,
+  OmniRoutePlugin,
+  type OmniRouteRawModelEntry,
+} from "../src/index.js";
+import { createLogger, getLogLevel, logger, setLogLevel, type LogLevel } from "../src/logger.js";
 
 type ConsoleMethod = "error" | "info" | "log" | "warn";
 type ConsoleEntries = Record<ConsoleMethod, unknown[][]>;
@@ -216,3 +222,105 @@ test("logger error output remains visible at error level", async () => {
     setLogLevel(previousLevel);
   }
 });
+
+const MINIMAL_MODELS: OmniRouteRawModelEntry[] = [
+  {
+    id: "claude-primary",
+    object: "model",
+    owned_by: "combo",
+    capabilities: { tool_calling: true, reasoning: true, vision: true, thinking: true },
+    context_length: 200000,
+    max_output_tokens: 64000,
+    input_modalities: ["text", "image"],
+    output_modalities: ["text"],
+  },
+];
+
+function providerHookWithLevel(level: LogLevel, baseURL?: string) {
+  return createOmniRouteProviderHook(
+    {
+      baseURL,
+      features: { autoCombos: false, enrichment: false, logLevel: level },
+    },
+    {
+      fetcher: async () => MINIMAL_MODELS,
+      combosFetcher: async () => {
+        throw new Error("combos boom");
+      },
+    }
+  );
+}
+
+test("logLevel error suppresses provider.models() fallback warnings and the catalog-refresh breadcrumb", async () => {
+  const hook = providerHookWithLevel("error", "https://or.example.com/v1");
+  const lines = rendered(
+    await captureConsole(async () => {
+      await hook.models!({} as never, { auth: { type: "api", key: "sk-x" } as never });
+    })
+  );
+
+  assert.equal(lines.filter((line) => line.includes("combos fetch failed")).length, 0);
+  assert.equal(lines.filter((line) => line.includes("catalog refreshed")).length, 0);
+});
+
+test("logLevel debug preserves the provider.models() catalog-refresh breadcrumb", async () => {
+  const hook = providerHookWithLevel("debug", "https://or.example.com/v1");
+  const lines = rendered(
+    await captureConsole(async () => {
+      await hook.models!({} as never, { auth: { type: "api", key: "sk-x" } as never });
+    })
+  );
+
+  assert.ok(
+    lines.some((line) => line.includes("catalog refreshed")),
+    "catalog-refresh breadcrumb emitted at debug level"
+  );
+});
+
+test("no baseURL resolvable stays visible at error level", async () => {
+  const hook = providerHookWithLevel("error");
+  const lines = rendered(
+    await captureConsole(async () => {
+      await hook.models!({} as never, { auth: { type: "api", key: "sk-x" } as never });
+    })
+  );
+
+  assert.ok(
+    lines.some((line) => line.includes("no baseURL resolvable")),
+    "genuine misconfiguration error remains visible at error level"
+  );
+});
+
+test("default auto-combos fetcher 404 warning respects the threaded logger level", async () => {
+  const originalFetch = globalThis.fetch;
+  (globalThis as { fetch: unknown }).fetch = (async () => ({
+    status: 404,
+    ok: false,
+  })) as typeof fetch;
+  try {
+    const silent = await captureConsole(async () => {
+      await defaultOmniRouteAutoCombosFetcher(
+        "https://or.example.com/v1",
+        "sk-x",
+        5_000,
+        createLogger("error")
+      );
+    });
+    assert.equal(rendered(silent).length, 0, "404 warning suppressed at error level");
+
+    const loud = await captureConsole(async () => {
+      await defaultOmniRouteAutoCombosFetcher(
+        "https://or.example.com/v1",
+        "sk-x",
+        5_000,
+        createLogger("warn")
+      );
+    });
+    assert.ok(
+      rendered(loud).some((line) => line.includes("/api/combos/auto not available")),
+      "404 warning emitted at warn level"
+    );
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});

@omniroute/opencode-plugin/tests/provider.test.ts

@@ -104,7 +104,10 @@ test("models: extracts apiKey from ctx.auth (type=api) and calls fetcher with it
   // #6859: dynamic-hook catalog keys use the unprefixed omnirouteProviderId
   // ("omniroute"), not the OC-gate-prefixed hook.id ("opencode-omniroute") —
   // that prefix must never leak into anything OmniRoute's server parses.
-  assert.ok(out["omniroute/claude-primary"]);
+  // #10345/#10821: bare combo ids (owned_by: "combo") stay unprefixed —
+  // OpenCode looks up `-m <plugin>/<combo>` as model id `<combo>` under the
+  // plugin provider, so `claude-primary` here carries no provider prefix.
+  assert.ok(out["claude-primary"]);
 });
 
 test("models: returns {} when ctx.auth is null/undefined/wrong-type/empty-key", async () => {
@@ -159,11 +162,15 @@ test("models: maps a sample /v1/models entry to ModelV2 (sanity)", async () => {
   // omnirouteProviderId ("omniroute") — the OC-gate prefix ("opencode-")
   // must stay OC-internal (hook.id / AuthHook.provider) and never leak into
   // anything OmniRoute's own server parses for credential lookup.
-  const claude = out["omniroute/claude-primary"];
+  // #10345/#10821: bare **combo** ids (owned_by: "combo", e.g.
+  // "claude-primary") must also stay unprefixed — OpenCode looks up
+  // `-m <plugin>/<combo>` as model id `<combo>` under the plugin provider.
+  const claude = out["claude-primary"];
   assert.ok(claude, "claude-primary present");
-  // `mapRawModelToModelV2` stamps the provider prefix on the id so OC's
-  // static-catalog reader resolves `(providerID, modelID)` from the key.
-  assert.equal(claude.id, "omniroute/claude-primary");
+  // `mapRawModelToModelV2` leaves bare combo ids unprefixed (see
+  // src/index.ts mapRawModelToModelV2) so OC's `-m <plugin>/<combo>` lookup
+  // resolves the combo id directly.
+  assert.equal(claude.id, "claude-primary");
   assert.equal(claude.name, "claude-primary");
   assert.equal(claude.providerID, "omniroute");
   assert.equal(claude.api.id, "openai-compatible");

AGENTS.md

@@ -46,7 +46,7 @@ Repository map and Reference Documentation sections below.
 
 ## Project at a Glance
 
-**OmniRoute** — unified AI proxy/router. One endpoint, 342 LLM providers, auto-fallback.
+**OmniRoute** — unified AI proxy/router. One endpoint, 352 LLM providers, auto-fallback.
 
 | Layer         | Location                | Purpose                                                                                                                                                                   |
 | ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
@@ -56,9 +56,9 @@ Repository map and Reference Documentation sections below.
 | Translators   | `open-sse/translator/`  | Format conversion (OpenAI↔Claude↔Gemini)                                                                                                                                  |
 | Transformer   | `open-sse/transformer/` | Responses API ↔ Chat Completions                                                                                                                                          |
 | Services      | `open-sse/services/`    | Combo routing, rate limits, caching, etc                                                                                                                                  |
-| Database      | `src/lib/db/`           | SQLite domain modules (154 migrations)                                                                                                                                    |
+| Database      | `src/lib/db/`           | SQLite domain modules (159 migrations)                                                                                                                                    |
 | Domain/Policy | `src/domain/`           | Policy engine, cost rules, fallback logic                                                                                                                                 |
-| MCP Server    | `open-sse/mcp-server/`  | 109 tools (44 canonical + memory/skill/GitHub/pool/gamification/plugin/Notion/Obsidian/local-corpus/RTK modules), 3 transports (stdio / SSE / Streamable HTTP), 33 scopes |
+| MCP Server    | `open-sse/mcp-server/`  | 110 tools (44 canonical + memory/skill/GitHub/pool/gamification/plugin/Notion/Obsidian/local-corpus/RTK modules), 3 transports (stdio / SSE / Streamable HTTP), 33 scopes |
 | A2A Server    | `src/lib/a2a/`          | JSON-RPC 2.0 agent protocol                                                                                                                                               |
 | Skills        | `src/lib/skills/`       | Extensible skill framework                                                                                                                                                |
 | Memory        | `src/lib/memory/`       | Persistent conversational memory                                                                                                                                          |
@@ -718,3 +718,13 @@ The dashboard is reachable at the operator's chosen URL/port (default `http://lo
 - **Local VPS / shared dev environments**: ask the operator for the URL and current credentials — they live in their personal vault, NOT in this repo.
 
 > Any credential observed in a previous version of this file was a non-production demo value; treat it as compromised and do not reuse it.
+
+<!-- BEGIN:nextjs-agent-rules -->
+
+# This is NOT the Next.js you know
+
+This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in `node_modules/next/dist/docs/` (resolved from this file's directory; in monorepos the `next` package may not be visible from the repo root) before writing any code. Heed deprecation notices.
+
+This block is written and re-added by `next dev` — verify at `node_modules/next/dist/server/lib/generate-agent-files.js`. Removing it from a diff only re-creates the uncommitted change; committing it with your work keeps the tree clean.
+
+<!-- END:nextjs-agent-rules -->

CHANGELOG.md

@@ -2,13 +2,99 @@
 
 ## [Unreleased]
 
----
+### ✨ New Features
 
-## [3.8.50] — TBD
+- **feat(sse): STRICT_ZERO_COST** — opt-in, off-by-default `freeAccessPolicy: "strict"` setting
+  that hard-verifies every auto-combo candidate against live quota state and per-connection
+  economic safety before it can be dispatched, going beyond `hidePaidModels`'s static catalog
+  check. Adds curated `hardStopGuaranteed` metadata to `FREE_MODEL_BUDGETS`, a short-TTL quota
+  cache reusing `getUsageForProvider()`, and a connection-safety guarantee: a candidate backed
+  by multiple accounts has its `allowedConnectionIds` narrowed to exactly the connections
+  independently verified `SAFE`, so dispatch can never use an unverified account. An
+  `excludeTosAvoid` guard (default `false`) is available separately for contractual risk. See
+  `docs/routing/STRICT_ZERO_COST.md`.
+
+---
+- feat(services): show sanitized CLIProxyAPI account health from its authenticated management API without exposing credentials, file paths, or raw account metadata (#6342)
+- **feat(credential-health):** pace the credential health sweep per connection via `provider_connections.healthCheckInterval` (minutes, 0 = never), with `CREDENTIAL_HEALTH_CHECK_INTERVAL` as the global default ([#8443](https://github.com/diegosouzapw/OmniRoute/issues/8443))
+- **behavior change:** `healthCheckInterval` is a shared column — it paces both the OAuth token refresh and the credential health sweep, and `0` disables both. The connection editor defaults it to 60, so configured OAuth connections are now credential-checked at 60min instead of the previous ~10min (aligned with the probe-volume goal of #8443)
+- **feat(providers):** publish Poolside's Laguna Preview catalog statically — `poolside/laguna-xs-2.1` and `poolside/laguna-s-2.1` (262144 context, 32768 max completion, tools + reasoning, text-only), so the models are routable and visible before a key is configured instead of only after live discovery. Pins the catalog form of the XS id against the `laguna-xs.2` variant carried by third-party listings. ([#9085](https://github.com/diegosouzapw/OmniRoute/issues/9085))
+- feat(modality-bridge): bridge Chat and Responses video parts through a strict trusted-loopback, quota-bounded FFmpeg broker; enforce HTTPS redirects/SSRF plus format, protocol, stream, pixel, frame, 50 MiB broker/remote, 36 MiB inline, and 120-second limits; propagate caller aborts; preserve the actual successful fallback model through cache/meta/headers; expose sampled latency and honest success telemetry; and ship the localized Video settings UI (#9760)
+- **feat(radar):** Persist local model display-name/enabled overrides and hide/restore tombstones, with authenticated catalog controls and feed safety precedence ([#9830](https://github.com/diegosouzapw/OmniRoute/pull/9830))
+- **feat(radar):** add curated-family combo suggestions, a guided combo page, and the read-only Radar MCP catalog tool ([#9836](https://github.com/diegosouzapw/OmniRoute/pull/9836))
+- **feat(radar):** add a signed live offers feed and supporter offers dashboard ([#9912](https://github.com/diegosouzapw/OmniRoute/pull/9912))
+- **feat(radar):** add signed Intel insights, supporter recognition, and local Radar CLI commands ([#9923](https://github.com/diegosouzapw/OmniRoute/pull/9923))
+- **feat(radar):** add a localized public news feed and dismissible dashboard launch banner, with the Radar announcement staged inactive for a separately authorized launch ([#9926](https://github.com/diegosouzapw/OmniRoute/pull/9926))
+- **feat(admission):** add lane-aware admission probes for combo/fusion/chaos fan-out (fail-open, queueing disabled), an env-wins `OMNIROUTE_CHAT_VIRTUAL_LANES` activation flag applied at boot, and adaptive-lane visibility in the `omniroute_get_health` MCP tool (related to #9654)
+- **docs(mcp):** complete the MCP server README tool reference so the `schemas/` catalog is fully covered (agent-skills, oneproxy, web, tool-search, combo/routing, pricing and DB-health tools were previously only discoverable via `omniroute_tool_search`)
+- **feat(cli):** container-aware auto-config — `setup-*`, `omniroute configure`, `omniroute config set` and the CLI-tool config APIs now refuse to write into a containerised OmniRoute's ephemeral home (CLI exits `2`, API returns `422` with `containerEphemeralTarget`) and point at the host-CLI or bind-mount setup instead; `--allow-container-write` / `OMNIROUTE_ALLOW_CONTAINER_CONFIG_WRITE=true` opt back in. Also fixes `CLI_CONFIG_HOME` so the Compose `host` profile's `/host-home` bind mounts are honoured instead of silently falling back to the container home. (#10057)
+- feat(dashboard): opt-in `DASHBOARD_ALLOW_EMBED=vscode` relaxes CSP `frame-ancestors` to `'self' vscode-webview:` and drops `X-Frame-Options` for HTML pages only, so the dashboard renders inside the VS Code Simple Browser (OmniCopilot). Default posture unchanged — API routes stay unframable (#10273)
+- **feat(resilience):** warn when `/healthz` is served under event-loop lag ≥200ms so a slow 200 is visible as sick, not healthy ([#10303](https://github.com/diegosouzapw/OmniRoute/issues/10303))
+- **feat(docker):** add `GET`/`HEAD` `/livez` as a process-alive probe, distinct from `/healthz` readiness ([#10316](https://github.com/diegosouzapw/OmniRoute/issues/10316))
+- feat(providers): add **Cloudflare AI Playground** as a No Auth provider (`cloudflare-playground`, alias `cfp`) — free anonymous chat over the reverse-engineered `cf_agent` WebSocket protocol (PartySocket transport, no account/API key/cookies) with GLM 5.2, Kimi K2.7 Code, DeepSeek V4 Pro, gpt-oss-120B, Llama 3.3 70B, Qwen2.5 Coder 32B and 14 more curated models. The executor drives a headless Chromium via Playwright (the WS upgrade is TLS-fingerprint-gated), translates the `cf_agent` frame stream into OpenAI SSE, and surfaces upstream rate limits (3021) as HTTP 429. Fixes #10389
+- **feat(providers):** AI Horde accepts an optional registered API key and advertises only live image models that currently have workers ([#10542](https://github.com/diegosouzapw/OmniRoute/pull/10542))
+- **fix(providers):** AI Horde Check validates keys via `/v2/find_user` instead of the unauthenticated OpenAI models list ([#10542](https://github.com/diegosouzapw/OmniRoute/pull/10542))
+- **feat(audio):** proxy native ElevenLabs voices, text-to-speech, and speech-to-text HTTP routes through stored OmniRoute credentials, preserving query strings, multipart uploads, binary responses, and upstream errors (#10556).
+- **feat(providers):** complete Jina AI as one credential pool — dashboard `jina-ai` / `jina-reader` share a token, `JINA_AI_API_KEY` is a real fallback, Test probes `GET https://api.jina.ai/v1/models` (embeddings fallback hits `jina-embeddings-v5-omni-small`), embed/rerank logs keep `connection_id`, catalog adds `jina-reranker-v3.5`, Omni v5 multimodal `{text}`/`{image}`/`{content}` docs pass through intact, and OmniRoute proxies classify / segment / `jina-search` (`s.jina.ai`). Reader stays a separate `r.jina.ai` card with an explicit label. Gemini Embedding 2 (`gemini/gemini-embedding-2`, alias `google/gemini-embedding-2`) uses dashboard `gemini` keys (or `GEMINI_API_KEY` / `GOOGLE_API_KEY` only when none exist), forwards native multimodal parts, and maps N OpenAI `input` items to N `:batchEmbedContents` vectors instead of one aggregated `:embedContent`. ([#10581](https://github.com/diegosouzapw/OmniRoute/pull/10581))
+- **feat(providers):** accept `response_format=ogg` on `/v1/audio/speech` as an alias for the existing Opus/Ogg encoder ([#10587](https://github.com/diegosouzapw/OmniRoute/issues/10587))
+- Added Google AI Studio Gemini batch text-to-speech support through `POST /v1/audio/speech`.
+- **feat(settings):** add `autoDisableBannedScope` so permanent-ban auto-disable can target subscription/OAuth accounts only, leaving prepaid API keys in the routing pool ([#10617](https://github.com/diegosouzapw/OmniRoute/pull/10617))
+- feat(server): emit systemd sd_notify READY/WATCHDOG/STOPPING (generated unit becomes Type=notify with WatchdogSec=180) so a frozen server process is killed and restarted by systemd instead of lingering undetected
+- **feat(providers):** add the TabiToken NewAPI gateway (`tabitoken`) and teach the existing HCNSec entry (`hcnsec`) the three further protocols it actually serves. TabiToken leaves the NewAPI pricing endpoint public, so its catalog is read from the host rather than guessed: four Claude models, each reporting the Anthropic and OpenAI protocols. HCNSec shipped OpenAI-only; probing the host showed `/v1/messages`, `/v1/responses` and the Gemini `/v1beta` path all reach its token layer, so each is now declared as an alternate format — with its default format, base URL, auth scheme and regional catalog classification untouched. ([#10668](https://github.com/diegosouzapw/OmniRoute/pull/10668)) — thanks @yawar-aquil
+- **feat(sse):** allow an alternate protocol to build its own upstream URL. `AlternateFormat` gained an optional `urlBuilder`, because the Gemini protocol carries the model inside the path (`{base}/{model}:generateContent`) and the existing `chatPath`/`urlSuffix` fields are constants that cannot express it. The route builder is extracted as `buildGeminiGenerateContentUrl` and shared with the native `gemini` provider so the two consumers cannot drift on the `?alt=sse` streaming suffix. ([#10668](https://github.com/diegosouzapw/OmniRoute/pull/10668)) — thanks @yawar-aquil
+- **feat(call_logs):** persist the per-call error family in `call_logs.error_type` and expose a failure breakdown (`errorBreakdown`) in the usage analytics endpoint, reusing the existing production classifier ([#10670](https://github.com/diegosouzapw/OmniRoute/issues/10670))
+- **feat(proxy):** the proxy-health sweep and `GET /api/settings/proxies/egress` now report an anonymous summary of egress-IP sharing — how many rotation groups share an egress IP and the largest number of accounts behind one IP — computed from persisted `proxy_logs` over a 24h window. No IPs and no account identities by default; `PROXY_LOG_INCLUDE_IPS=true` restores raw details. ([#10677](https://github.com/diegosouzapw/OmniRoute/issues/10677))
+- **docs(guides):** OmniRoute now serves VS Code's **native Copilot Chat model picker** through the [OmniCopilot](https://github.com/diegosouzapw/OmniCopilot) extension ([Marketplace](https://marketplace.visualstudio.com/items?itemName=diegosouzapw.omnicopilot) · [Open VSX](https://open-vsx.org/extension/diegosouzapw/omnicopilot) — Cursor, Windsurf, VSCodium, Theia…) — no Copilot subscription needed since VS Code 1.122. New [`docs/guides/VSCODE-COPILOT.md`](docs/guides/VSCODE-COPILOT.md) covers setup, how the picker collapses the `dual`-prefix catalog via `GET /v1/models?prefix=alias`, and the **build-time** `DASHBOARD_ALLOW_EMBED=vscode` flag that renders the dashboard in an editor tab ([#10697](https://github.com/diegosouzapw/OmniRoute/pull/10697))
+- **feat(docker):** `DASHBOARD_ALLOW_EMBED` is now a Docker build argument — `docker build --build-arg DASHBOARD_ALLOW_EMBED=vscode` produces an image whose dashboard renders inside the VS Code Simple Browser (OmniCopilot's `dashboardOpen: "editor"`). Previously the flag was only reachable from a source build: Docker silently drops a `--build-arg` with no matching `ARG`, so the operator got the default image and no error. Builder-stage only and empty by default — the runtime stages deliberately do not carry it, and the unframable default posture is unchanged ([#10701](https://github.com/diegosouzapw/OmniRoute/pull/10701))
+- **feat(providers):** new `cursor-api` provider (card "Cursor API", alias `cua`): connect a Cursor user API key (`crsr_…`) and route `cursor-api/<model>` through the existing Cursor agent executor (the key is exchanged for a 1h session token and cached), plus a `/api/cursor-cli/*` passthrough so the Cursor CLI itself runs through OmniRoute (`CURSOR_API_ENDPOINT=http://<omniroute>/api/cursor-cli`, `CURSOR_API_KEY=<OmniRoute key>`) with every RPC attributed and logged. The IDE `cursor` provider is unchanged. (#10729)
+- **feat(api):** `GET /api/health` now answers `{ status, timestamp }` without a key. Until now the path had no route, so the management-auth boundary answered first with a 401 — indistinguishable from a wrong key or an unknown route, which left Docker HEALTHCHECKs and Kubernetes probes unable to tell "down" from "misconfigured". Kept deliberately minimal: version, uptime and memory stay behind the authenticated `/api/monitoring/health` ([#PRNUM](https://github.com/diegosouzapw/OmniRoute/pull/10771)).
+- feat(routing): make Task-Aware Smart Routing's detection patterns operator-configurable via `settings.taskRouting.patternOverrides` (`PUT /api/settings/task-routing`) — the built-in patterns are English-only, so a non-English dashboard had no recourse short of turning detection off entirely; an override now replaces the pattern list for one task type without touching the rest (#10783)
+- feat(api): accept PATCH on /api/combos/[id], the verb the OpenAPI spec already documents (#10869)
+- **feat(sse):** add GLM-5.3 support (`glm-5.3`, `glm-5.3-high`, `glm-5.3-low`) across the z.ai first-party providers, mapping the upstream `reasoning_effort` request parameter to the existing 5.2 tier UX ([#10896](https://github.com/diegosouzapw/OmniRoute/pull/10896)) — thanks @phuongddx
+- **feat(home):** add a live **Recent Requests** panel beside the home Provider Topology (polls `GET /api/usage/call-logs?excludeTests=1` every ~3s, gated by the topology appearance toggle + page visibility). `excludeTests` is now an allowlist of real provider inference (`/v1/%` or `/api/v1/%`), applied before `LIMIT`, so connection-test/model-sync/management rows can never leak into the feed ([#10897](https://github.com/diegosouzapw/OmniRoute/pull/10897), extracted from [#8450](https://github.com/diegosouzapw/OmniRoute/pull/8450)) — thanks @nguyenha935
+- **feat(rankings):** free provider rankings now expose a `reliability` field (raw `testStatus`/`rateLimitedUntil` per connection plus a `healthy`/`degraded`/`down` state, reusing the `ProviderHealthState` vocabulary of the provider health matrix) when the configured/available filters are active — derived from already-loaded data, without touching the ranking order ([#10909](https://github.com/diegosouzapw/OmniRoute/pull/10909))
+- `feat(resilience)`: when an allowlisted provider (opencode family) answers
+  429 classified `quota_exhausted` or `rate_limit_exceeded` and its free-tier
+  quota is bucketed by egress IP (#9611), every connection of that family
+  sharing the IP is cooled down together before the rotation tries them — one
+  guaranteed-failed upstream call per episode instead of N, on the combo path
+  as well. For the allowlisted family a 429 now cools the connection instead
+  of locking a single model. Exclusive allowlist, never terminal, best-effort
+  when the egress IP is unknown (#10920).
+- **feat(rankings):** free provider rankings can now report what each provider actually served — `reliability.usage` (requests, successes, success rate over a window) behind the opt-in `withUsage`/`usageRange` query parameters, so a provider that answers every call with an error is no longer described as healthy ([#10926](https://github.com/diegosouzapw/OmniRoute/pull/10926))
+- **feat(providers):** add Logfare as a free OpenAI-compatible provider — dashboard card with a Free badge and request-logging disclosure (every prompt/completion is logged for research; opt out at logfare.ai/consent), live model discovery from `https://logfare.ai/v1/models` (20 models, 11 chat-capable: kimi-k3, deepseek-v4-pro, glm-5.2, gpt-5.6-luna, minimax-m3…), full chat/streaming through the existing OpenAI-compatible path, the real Logfare logo on the card, and a listing in the free-tiers guide. ([#10987](https://github.com/diegosouzapw/OmniRoute/pull/10987))
+- Run synchronous RTK and Caveman request compression in a bounded worker-thread pool, keeping
+  large `/v1/responses` compression heaps outside the HTTP isolate while preserving strict
+  fail-open behavior and per-engine telemetry.
+- **feat(providers):** let operators declare per-provider error rules through `settings.providerErrorRules` instead of patching the catalog — an operator-supplied rule for a provider is consulted before the built-in `providerRuleRegistry`, receives the raw error text, and has its declared scope/cooldown/reason actually honored end to end, for any provider (declaring the rule is the opt-in — no extra allowlist entry needed). Matches are plain case-insensitive substrings (never RegExp) and bounded to 50 rules to keep the hot path safe ([#11104](https://github.com/diegosouzapw/OmniRoute/pull/11104))
+- **feat(combo):** the shared per-request combo attempt budget is now operator-configurable via `maxGlobalAttempts` (combo config / `comboDefaults` cascade), instead of the hardcoded 30. Lower it to fail fast on a dead target pool, raise it for large combos; clamped to `[1, 200]` so an unbounded budget can never cause runaway background requests ([#11134](https://github.com/diegosouzapw/OmniRoute/issues/11134))
+- **feat(api):** `/api/usage/om-usage` gains a structured form — `?format=json` returns the key's own usage as `ApiKeyUsageLimitStatus` + `UsageSnapshot` instead of `text/plain`. This is the surface a UI (the OmniCopilot panel) consumes to show a key holder their daily/weekly spend and quota reset. The route is self-service (the caller's own key, gated by `allowUsageCommand`), not the management surface; refusals come back as a discriminated `{ "allowed": false, "error": … }` so a UI can tell "not allowed" apart from "allowed but nothing cached yet". The endpoint was previously undocumented in `API_REFERENCE.md`; it now has a section ([#11190](https://github.com/diegosouzapw/OmniRoute/pull/11190))
+- **feat(api):** `/api/usage/om-usage?format=json` now returns `providers[]` — every connection's quota snapshot, not just the single selected one — so a panel can render Codex / Claude / OpenCode side by side. The collector already gathered all of them; the single-pick `provider` field (kept) is a terminal presentation choice. Closes the per-connection gap from OmniCopilot #8 ([#11192](https://github.com/diegosouzapw/OmniRoute/pull/11192))
+- **feat(providers):** allow overriding the rate-limit queue wait timeout (`maxWaitMs`) per connection, alongside the existing `rpm`/`tpm`/`tpd`/`minTime`/`maxConcurrent` overrides — a single slow provider no longer has to lower the global wait budget for every other provider (#11251)
+- **feat(dashboard):** replace the hard Home → onboarding redirect with a dismissable first-run readiness card so returning users can stay on Home while new users still get a clear 4-step path ([#11282](https://github.com/diegosouzapw/OmniRoute/pull/11282))
+- **feat(dashboard):** lead Traffic Inspector with a purpose-first header that separates "what happened" from "how it happened", so beginners can read request outcomes without drowning in protocol detail ([#11283](https://github.com/diegosouzapw/OmniRoute/pull/11283))
+- **feat(dashboard):** add an Essentials sidebar preset that shows only the beginner core path (Home → Endpoints → API Keys → Providers → Health → Settings) while keeping Advanced tools reachable via Command Palette search ([#11286](https://github.com/diegosouzapw/OmniRoute/pull/11286))
+- **feat(video bridge):** harden the optional drill-down cache substrate with exact-path broker policy, canonical principal/session/media isolation, independent retained-byte quotas, cancellation-safe commits, rejection of excess or non-canonical Base64 padding and non-JPEG/truncated media, warning-sensitive full JPEG canonicalization that strips trailing polyglot bytes, server-derived dimensions, and auditable derivation metadata; production tenant binding and multi-resolution selection remain follow-up work ([#11369](https://github.com/diegosouzapw/OmniRoute/pull/11369))
+- **feat(video):** add an opt-in focused analysis mode that safely uses a normalized, 500-code-point latest-user hint for task-aware frame captions while preserving full-mode prompts, temporal-window isolation, and cache identity without storing raw task text ([#11383](https://github.com/diegosouzapw/OmniRoute/pull/11383)).
+- feat(command-code): advertise low/medium/high/xhigh/max reasoning-effort suffixes for reasoning-capable models in the catalog and Combo Builder, with request-time resolution to reasoning_effort
+- feat(crof): advertise reasoning-effort tiers (none/low/medium/high/max) for live-discovered and seed models, so the catalog, Playground, and Combo Builder surface <model>-<tier> aliases and requests resolve max upstream
+- feat(sse): add Cursor plan image generation via Agent CLI (`IMAGE_PROVIDERS.cursor`, format `cursor-agent-image`), reusing the chat Cursor OAuth connection
+- feat(routing): add the default-off `DISABLE_CONTEXT_WINDOW_CHECKS` feature flag to let operators bypass OmniRoute's local context-window and max-input-token check for direct single-model requests, leaving upstream limits, prompt compression, and output-token caps intact.
+- **feat(catalog):** surface runtime-learned `reasoning_effort` tiers in `/v1/models` `capabilities.effort_tiers` (learned set replaces synced metadata when present), map them to OpenCode `ModelV2.variants` in the OmniRoute plugin, and align dispatch `-<tier>` suffix validation to the effective (learned ?? synced) set — so the UI offers exactly the tiers the upstream accepts (e.g. `{low, high, max}` for `oc/x-preview-f-free`) and each advertised variant completes. Excludes codex/glm/kimi, which keep their own dedicated `-{effort}` suffix mechanism and never gain `effort_tiers` from this path (related to #7694, builds on #11232)
+- **feat(usage):** show Kimi Coding's fixed-order Code 5-hour/7-day quota windows plus Extra Usage status, balance, monthly spend/limit, and the official Additional Credits link on Dashboard → Quota cards.
+- **feat(providers):** copilot-m365-web now supports OpenAI tool calling — a router planning turn asks the substrate model (as a tool-selection assistant emitting `CALL_TOOL: name({...})` / `NO_TOOL_NEEDED` text, which bypasses its plugin-registry refusal) and validated decisions surface as `tool_calls` with `finish_reason: "tool_calls"` in both stream and non-stream modes; also flattens the full message history (assistant `tool_calls` + compacted tool results) so multi-turn agent loops keep context, replies to SignalR `type:6` keepalives, surfaces `type:3` error frames instead of a silent empty `stop`, and suppresses `writeAtCursor` text from tool-progress frames
+- **feat(api):** add `GET`/`POST` `/v1/multimodal-embeddings` as an alias of `/v1/embeddings` so Jina-compatible clients do not receive HTTP 404 `unknown_route` — thanks @RaviTharuma
+- feat(opencode-go): expose Muse Spark 1.2 Contributor reasoning-effort aliases (minimal/low/medium/high/xhigh) in the Combo Builder
+- **feat(providers):** restore the operator-owned upstream timeout tier per connection via `providerSpecificData.timeoutMs` (preempts the maintainer-only model/provider registry tiers and the global `FETCH_TIMEOUT_MS`), and make the combo per-target timeout ceiling follow the selected connection
+- **feat(cli):** run `omniroute serve --tray` as a detached desktop process after server and tray readiness, with graphical login auto-start support.
+- **feat(routing):** add client-, provider-, and model-neutral exclusive managed session connection leases with API-key-bound generation fencing, durable SQLite ownership, explicit allowlist policy, and bounded 429 capacity retry semantics.
+
+## [3.8.50] — 2026-08-25
 
 _Living section — regenerated 2026-08-12 from all cycle commits (cycle open `ed2db6cb19` → tip). Bullets carry the merged PR and its author; direct pushes listed separately._
 
 ### ✨ New Features
+- **feat(search):** first-class X Search provider (`x-search`) on `POST /v1/search` and MCP `omniroute_x_search` using SuperGrok / xAI server-side `x_search`. Explicit provider or `search_type: "x"` only — never auto-selected for web. Reuses `xai-oauth` / `xao` / `xai` credentials. Not the X Developer Platform MCP. ([#10985](https://github.com/diegosouzapw/OmniRoute/issues/10985))
 - **feat(core):** add Layer A capability filter at router (#5696)
 - **feat(providers):** add DeepAI as paid API-key image provider ([#6671](https://github.com/diegosouzapw/OmniRoute/issues/6671))
 - **feat(providers):** add Naga.ac and ChatAnywhere aggregator gateway providers (#6674 — thanks @chirag127)
@@ -165,10 +251,60 @@ _Living section — regenerated 2026-08-12 from all cycle commits (cycle open `e
 - **feat(dashboard):** Kimi 15% first-top-up campaign — dedicated tracked link + discount-first banner copy ([#10240](https://github.com/diegosouzapw/OmniRoute/pull/10240))
 - **feat(providers):** integrate audited free-tier gateways ([#9210](https://github.com/diegosouzapw/OmniRoute/pull/9210))
 
+<!-- reconciliation pass 2 (Phase 0a.1): commits that landed in the cycle without a bullet -->
+
+- **feat(radar):** **OmniRoute Radar** — the signed free-model catalog overlay — landed end to end this cycle: local catalog state is persisted, guided combo suggestions feed a guided combos page, guided provider setup walks a new operator through connecting, verified model metadata and an owner-only admin link are surfaced, signed supporter offers get their own dashboard and sync path, signed Intel insights arrive with a supporter-recognition UI, a launch-news surface was added, and catalog export runs through a stable workflow that carries provenance ([#10826](https://github.com/diegosouzapw/OmniRoute/issues/10826)). The catalog is also reachable as an MCP tool and through the new `radar status` / `radar sync` CLI commands.
+- **feat(video):** Video Bridge gained a full sampling and caching stack — scene-aware and segment-aware sampling with a structural fallback, conservative frame deduplication, validated focus windows, timestamped contact sheets, and an optional audio-fusion timeline that preserves transcript provenance, reports fusion telemetry, and degrades to *partial* on invalid audio. Results are cached with metadata (the key includes the audio transcript and focus window), and drill-downs use an isolated cache bounded by a global byte budget; a sampler/contact-sheet benchmark script ships alongside ([#10483](https://github.com/diegosouzapw/OmniRoute/issues/10483)) — thanks @backryun
+- **feat(volcengine):** Volcengine **Ark plan providers** — live model discovery through `ListAgentPlanLatestModel` (retaining only API-callable Agent Plan models) and phone/SMS console auto-login with MFA and identity selection ([#11333](https://github.com/diegosouzapw/OmniRoute/issues/11333) — thanks @rengaryang)
+- **feat(providers):** new upstreams this cycle — **Token Kiosk** as an OpenAI-compatible provider ([#10722](https://github.com/diegosouzapw/OmniRoute/issues/10722) — thanks @hgaib), a local **ZCode ACP** backend ([#10184](https://github.com/diegosouzapw/OmniRoute/issues/10184) — thanks @megamen32), and the **tencent-aistudio-web** cookie provider (`tasw`) ([#10174](https://github.com/diegosouzapw/OmniRoute/issues/10174) — thanks @MeRezaRezaei)
+- **feat(providers):** Cursor PKCE login with Bearer quota reporting, automatic router selection and explicit empty-turn errors ([#9909](https://github.com/diegosouzapw/OmniRoute/issues/9909) — thanks @yansigit); `cursor` also discovers the account's Agent endpoint instead of assuming one ([#10804](https://github.com/diegosouzapw/OmniRoute/issues/10804) — thanks @tuandinh0801)
+- **feat(providers):** tool calling for `copilot-m365-web` via router planning ([#10948](https://github.com/diegosouzapw/OmniRoute/issues/10948) — thanks @acc0mplish)
+- **feat(providers):** per-connection upstream timeout tier is back — a connection can again override the provider-wide request timeout ([#10885](https://github.com/diegosouzapw/OmniRoute/issues/10885) — thanks @maxmad64bis)
+- **feat(providers):** catalog refreshes — Qwen3.8 model catalogs ([#10226](https://github.com/diegosouzapw/OmniRoute/issues/10226)), Grok 4.6 plus a DeepSeek V4 refresh ([#10195](https://github.com/diegosouzapw/OmniRoute/issues/10195)) — thanks @backryun — and the `agnes` chat catalog moved to the 2026-07-30 listing ([#10942](https://github.com/diegosouzapw/OmniRoute/issues/10942) — thanks @oyi77)
+- **feat(providers):** the web-session credential guide gained a Cookie Editor fast path, so cookie-based providers can be connected without hand-copying headers — thanks @benzntech
+- **feat(sse):** explicit `glm-5.3-max` reasoning-effort tier ([#11415](https://github.com/diegosouzapw/OmniRoute/issues/11415) — thanks @phuongddx)
+- **feat(sse):** discover Anthropic partner models served through Vertex AI ([#11279](https://github.com/diegosouzapw/OmniRoute/issues/11279) — thanks @maci0)
+- **feat(sse):** opt-in `STRICT_ZERO_COST` free-access policy — refuses any target that is not verifiably zero-cost ([#10965](https://github.com/diegosouzapw/OmniRoute/issues/10965) — thanks @mymusicmyspace)
+- **feat(sse):** Kimi Web token lifecycle manager — rolling auto-refresh and 401 recovery, so `kimi-web` connections stop expiring silently ([#10944](https://github.com/diegosouzapw/OmniRoute/issues/10944) — thanks @MeRezaRezaei)
+- **feat(sse):** Cursor plan images through the Agent CLI (`IMAGE_PROVIDERS.cursor`) ([#10842](https://github.com/diegosouzapw/OmniRoute/issues/10842)), and the `i-have-adhd` output style reached vi/ja/id parity behind a style × language guard matrix ([#10425](https://github.com/diegosouzapw/OmniRoute/issues/10425))
+- **feat(api):** health and liveness surface — `GET /livez` as a process-alive probe ([#10819](https://github.com/diegosouzapw/OmniRoute/issues/10819)), `GET/HEAD /readyz` aliased to `/healthz` ([#10977](https://github.com/diegosouzapw/OmniRoute/issues/10977)), and `GET /api/health` answering without a key ([#10771](https://github.com/diegosouzapw/OmniRoute/issues/10771)) — thanks @RaviTharuma and @maxmad64bis
+- **feat(api):** `/v1/multimodal-embeddings` is now an alias of `/v1/embeddings` ([#10568](https://github.com/diegosouzapw/OmniRoute/issues/10568) — thanks @RaviTharuma), and `/v1/combos` steps flag a pinned account without leaking its id ([#11076](https://github.com/diegosouzapw/OmniRoute/issues/11076) — thanks @ntdatt812)
+- **feat(audio):** native ElevenLabs HTTP compatibility routes ([#11312](https://github.com/diegosouzapw/OmniRoute/issues/11312)), Google AI Studio Gemini TTS ([#11315](https://github.com/diegosouzapw/OmniRoute/issues/11315)), and `response_format=ogg` accepted as an opus alias on `/v1/audio/speech` ([#10822](https://github.com/diegosouzapw/OmniRoute/issues/10822)) — thanks @RaviTharuma
+- **feat(gemini-web):** image generation exposed through `/v1/images/generations` ([#10494](https://github.com/diegosouzapw/OmniRoute/issues/10494) — thanks @Abhishek4512009)
+- **feat(cli):** native Bun backend support plus `Dockerfile.bun` ([#11039](https://github.com/diegosouzapw/OmniRoute/issues/11039) — thanks @rqzbeh), with matching `-bun` / `-web-bun` container images published by the Docker workflow ([#11168](https://github.com/diegosouzapw/OmniRoute/issues/11168))
+- **feat(cli):** tray mode detaches from the terminal ([#11230](https://github.com/diegosouzapw/OmniRoute/issues/11230) — thanks @tuandinh0801), Grok Build accepts a custom host ([#10830](https://github.com/diegosouzapw/OmniRoute/issues/10830) — thanks @tuandinh0801), and Linux autostart inherits the login shell `PATH` ([#11372](https://github.com/diegosouzapw/OmniRoute/issues/11372) — thanks @ziuus)
+- **feat(cli):** relay-like CLI closure — a target manifest, Codex TOML generation, a Gemini launcher and drift guards, so `omniroute run <cli>` covers the documented agent surface — thanks @backryun
+- **feat(dashboard):** beginner-oriented UX pass across the app — a guided endpoint-connection header ([#11228](https://github.com/diegosouzapw/OmniRoute/issues/11228)), a stable outcome header on the batch page ([#11227](https://github.com/diegosouzapw/OmniRoute/issues/11227)), plain-language verdicts for health status ([#11224](https://github.com/diegosouzapw/OmniRoute/issues/11224)) and for the resilience page ([#11215](https://github.com/diegosouzapw/OmniRoute/issues/11215)), orientation before API-key management ([#11195](https://github.com/diegosouzapw/OmniRoute/issues/11195)), and ACP framed as optional advanced setup ([#11206](https://github.com/diegosouzapw/OmniRoute/issues/11206)) — thanks @ignamiranda
+- **feat(dashboard):** agentic conversation tracking ([#10263](https://github.com/diegosouzapw/OmniRoute/issues/10263) — thanks @hartmark), a Recent Requests panel on the home page ([#10900](https://github.com/diegosouzapw/OmniRoute/issues/10900)), a VS Code Copilot Chat home banner replacing the Provider Quota card ([#10520](https://github.com/diegosouzapw/OmniRoute/issues/10520)), a CheaperInference sponsor banner with its links routed through the branded shortener ([#11196](https://github.com/diegosouzapw/OmniRoute/issues/11196), [#11329](https://github.com/diegosouzapw/OmniRoute/issues/11329)), and Auto-Combo snapshot generation/duplication in the UX ([#10354](https://github.com/diegosouzapw/OmniRoute/issues/10354) — thanks @swingtempo)
+- **feat(routing):** quota-aware provider scheduling, phase 2 ([#10126](https://github.com/diegosouzapw/OmniRoute/issues/10126) — thanks @benzntech); exclusive managed-session connection leases so two sessions cannot claim the same account ([#10362](https://github.com/diegosouzapw/OmniRoute/issues/10362) — thanks @KaspaPulse); an adaptive feedback loop v2 scoring operational and semantic quality, confidence and TTFT/ITL ([#10881](https://github.com/diegosouzapw/OmniRoute/issues/10881) — thanks @Egorich-print); and a `DISABLE_CONTEXT_WINDOW_CHECKS` bypass for the direct-request input/context check ([#10927](https://github.com/diegosouzapw/OmniRoute/issues/10927))
+- **feat(combo):** an opaque per-invocation decision trace for priority fallbacks, so an operator can see why a combo picked the target it picked without exposing account identities ([#10730](https://github.com/diegosouzapw/OmniRoute/issues/10730) — thanks @stanleytejakusuma)
+- **feat(admission):** adaptive overload and pressure controls wired across the LLM routes, with a monitoring snapshot exposing the structural chat-admission state and shed counters ([#11268](https://github.com/diegosouzapw/OmniRoute/issues/11268)); Responses and Messages bodies are reserved before clone ([#10814](https://github.com/diegosouzapw/OmniRoute/issues/10814) — thanks @RaviTharuma) and structural chat-admission shedding is gated on real heap pressure ([#10437](https://github.com/diegosouzapw/OmniRoute/issues/10437)) — thanks @xz-dev
+- **feat(compression):** adopts omniglyph 1.4.0 with semantic profiles and evidence-backed accounting ([#10647](https://github.com/diegosouzapw/OmniRoute/issues/10647)), and the sync engines now run in a bounded worker pool instead of on the request thread ([#11318](https://github.com/diegosouzapw/OmniRoute/issues/11318) — thanks @RaviTharuma)
+- **feat(models):** learned `reasoning_effort` sets are surfaced in the catalog, in model variants and at dispatch ([#11252](https://github.com/diegosouzapw/OmniRoute/issues/11252) — thanks @maxmad64bis); `opencode-go` and `command-code` expose Muse Spark reasoning-effort aliases/suffixes ([#10883](https://github.com/diegosouzapw/OmniRoute/issues/10883), [#10884](https://github.com/diegosouzapw/OmniRoute/issues/10884) — thanks @excessivechaos)
+- **feat(search):** `context7` added as a library-docs search and fetch provider ([#11140](https://github.com/diegosouzapw/OmniRoute/issues/11140) — thanks @HouMinXi)
+- **feat(mcp):** dynamic runtime tool-schema plumbing so blocked providers are removed from the advertised enums instead of failing at call time ([#11155](https://github.com/diegosouzapw/OmniRoute/issues/11155) — thanks @rqzbeh), plus a Radar catalog tool
+- **feat(a2a):** A2A v1.0 client compatibility — a `SendMessage` alias and a v1.0-shaped agent card ([#10839](https://github.com/diegosouzapw/OmniRoute/issues/10839) — thanks @wpec)
+- **feat(server):** native systemd `sd_notify` watchdog support (`Type=notify`), so a stalled process is restarted by the supervisor rather than hanging ([#10662](https://github.com/diegosouzapw/OmniRoute/issues/10662) — thanks @maxmad64bis)
+- **feat(redis):** configurable key namespace prefix, so several OmniRoute instances can share one Redis ([#11042](https://github.com/diegosouzapw/OmniRoute/issues/11042) — thanks @MeRezaRezaei)
+- **feat(docker):** hardened Linux VPS deployment recipe ([#10623](https://github.com/diegosouzapw/OmniRoute/issues/10623) — thanks @freudantunes)
+- **feat(proxy):** anonymous egress-IP sharing surfaced in the health sweep and the egress API ([#10876](https://github.com/diegosouzapw/OmniRoute/issues/10876) — thanks @maxmad64bis), and a non-destructive auto-disable mode for the proxy health scheduler ([#10342](https://github.com/diegosouzapw/OmniRoute/issues/10342) — thanks @Gi99lin)
+- **feat(services):** sanitized CLIProxyAPI account health exposed to the dashboard ([#11314](https://github.com/diegosouzapw/OmniRoute/issues/11314) — thanks @RaviTharuma)
+- **feat(db):** the DB health check now reports which SQLite driver is active and what durability it gives you ([#10652](https://github.com/diegosouzapw/OmniRoute/issues/10652) — thanks @maxmad64bis)
+- **feat(codex):** sync with Codex v178 identity mechanisms — turn-state relay, persisted seeds and identity faces ([#10716](https://github.com/diegosouzapw/OmniRoute/issues/10716) — thanks @xz-dev)
+- **feat(usage):** Kimi Coding "Extra Usage" is shown on the provider card ([#10712](https://github.com/diegosouzapw/OmniRoute/issues/10712) — thanks @xz-dev)
+- **feat(oauth):** `gemini-3.7-flash` models added for the `antigravity` and `agy` providers ([#10305](https://github.com/diegosouzapw/OmniRoute/issues/10305) — thanks @Chewji9875)
+- **feat(cli-tools):** Prime Agent added to the CLI agents catalog ([#11166](https://github.com/diegosouzapw/OmniRoute/issues/11166) — thanks @arminanton)
+- **feat(guardrails):** a focused video-analysis mode for the vision guardrail, so long videos are judged on the requested window instead of the whole timeline
+- **feat(ops):** canary deploy path with a provenance gate, a real smoke run and a rollback anchor ([#10446](https://github.com/diegosouzapw/OmniRoute/issues/10446)), backed by artifact provenance verification and a `buildSha` on the health endpoint ([#10444](https://github.com/diegosouzapw/OmniRoute/issues/10444))
+- **feat(api):** list embeddings models from the configured providers ([#11249](https://github.com/diegosouzapw/OmniRoute/issues/11249)) and guided Qdrant memory configuration ([#11213](https://github.com/diegosouzapw/OmniRoute/issues/11213)) — thanks @rafacpti23
+- **feat(responses):** `previous_response_id` continuation is virtualized even when the upstream does not support it ([#10262](https://github.com/diegosouzapw/OmniRoute/issues/10262) — thanks @hartmark)
+
 ### 🐛 Bug Fixes
 
+- **fix(build):** every route no longer answers HTTP 500 on artifacts built from the release tip ([#11343](https://github.com/diegosouzapw/OmniRoute/issues/11343)) — `next.config.mjs` aliased `better-sqlite3` to its build-time stub **unconditionally**, on the premise that `serverExternalPackages` still won at runtime. It does not: a Turbopack `resolveAlias` rewrites the request *before* the externals check, so the request stopped matching the `better-sqlite3` external entry and the stub was baked into the shipped bundle. The sync driver then failed with `r(...) is not a constructor`, fell through `node:sqlite` and sql.js, and the instrumentation hook aborted at boot. Same failure shape as [#6344](https://github.com/diegosouzapw/OmniRoute/issues/6344), so it gets the same treatment: the alias is opt-in via `OMNIROUTE_BETTER_SQLITE3_STUB=1` through the shared `scripts/build/better-sqlite3-stub-flag.mjs` helper — set it only on a build host that actually hits the SIGABRT build-worker teardown ([#10060](https://github.com/diegosouzapw/OmniRoute/issues/10060)); default builds externalize the real native addon. Regression guards: `tests/unit/better-sqlite3-stub-alias-11343.test.mjs` (5) and the env matrix in `tests/unit/next-config.test.ts`.
 - **security(search)**: block SSRF via `/v1/search` `provider_options.baseUrl` for the Firecrawl search provider — the client-controlled override is now validated as a public URL before it is used to build the server-side fetch target, so a caller with a valid API key can no longer redirect search requests at loopback, RFC1918, or cloud-metadata hosts — thanks @zmf963
 - **providers**: honor `PATCH /api/providers/[id]` so `omniroute providers rotate` stops 405ing (the OpenAPI spec and CLI already use PATCH) (PR #10366)
+- **cli**: route provider test commands through configured connection test endpoints (#10570)
 - **executors**: fix internal timeout misclassified as client disconnect (499) for 7 niche executors — pass TimeoutError reason to controller.abort() (#8197 side-finding)
 - test(combo): guard auto/best-free never leaks the combo name as a model (#7754)
 - fix(vision-bridge): describe-model no longer returns unreachable "openai/gpt-4o-mini" when every vision-capable provider is unreachable on the instance — returns null instead and surfaces a clear error (#8430)
@@ -628,6 +764,353 @@ _Living section — regenerated 2026-08-12 from all cycle commits (cycle open `e
 - **fix(security):** resolve open CodeQL alerts ([#10188](https://github.com/diegosouzapw/OmniRoute/pull/10188))
 - **fix(dashboard):** retarget Kimi promo CTA to the API platform aff link ([#10200](https://github.com/diegosouzapw/OmniRoute/pull/10200))
 - **fix(build):** repair broken production build, red lint gate and SWR crash ([#10198](https://github.com/diegosouzapw/OmniRoute/pull/10198))
+- fix(cli): repair hollow externalized package dirs in the nested `<distDir>/node_modules` bundle location too, not just the top-level one, fixing macOS/Linux Electron `ERR_MODULE_NOT_FOUND` on Turbopack-externalized packages (#7346)
+- **Electron packaged smoke test:** add a cold-restart mode (`ELECTRON_SMOKE_COLD_RESTART=1`, wired blocking on the Linux release leg) that relaunches the packaged app against its own persisted `DATA_DIR` and asserts a native SQLite driver was selected instead of the sql.js WASM fallback, closing the regression-test gap flagged in the stale-ABI `better-sqlite3` investigation ([#7592](https://github.com/diegosouzapw/OmniRoute/issues/7592)).
+- **fix(usage):** keep session/weekly/monthly quota windows in chronological order on every provider card. The order is now derived from the quota keys themselves instead of a provider whitelist, so Claude, MiniMax, Z.ai and Command Code stop rendering the two bars in opposite positions across sibling accounts ([#7764](https://github.com/diegosouzapw/OmniRoute/issues/7764))
+- **fix(images):** retry Codex image generation on a sibling ChatGPT account when the requested model isn't entitled on the current account, instead of failing the request outright ([#8307](https://github.com/diegosouzapw/OmniRoute/pull/8307)).
+- fix(dashboard): treat UncloseAI as a no-auth provider so the connect form no longer forces a fake API key (#8864)
+- **fix(dashboard):** model-level allowed/blocked param edits now persist when the compatibility popover is closed by clicking outside, and a failed save no longer clears the edit or reports success ([#9013](https://github.com/diegosouzapw/OmniRoute/pull/9013))
+- fix(ssrf): make `getProviderOutboundGuard()` (used for search-provider connection validation, image generation and remote image fetch) honor the local-first default `OMNIROUTE_ALLOW_LOCAL_PROVIDER_URLS` the same way the chat validation guard already does, so a LAN-hosted SearXNG/Brave search provider works with only the LOCAL flag set instead of silently requiring `OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS` ([#9123](https://github.com/diegosouzapw/OmniRoute/issues/9123)).
+- fix(compression): preserve unfenced raw code (e.g. Copilot #file references) from Caveman's prose recapitalization/whitespace cleanup, which was corrupting keyword casing and indentation (#9144)
+- fix(api): yield the event loop during catalog builds and bulk-load override/hidden-model tables (#9147)
+- fix(combo): recovery hint for all_targets_skipped now points at provider quota/availability instead of 'transient, just retry' (#9303)
+- fix(providers): strip uniqueItems from Gemini tool schemas (Gemini rejects it with 400 'Unknown name uniqueItems') (#9617)
+- **fix(translator):** convert OpenAI `image_url` blocks nested in `role: "tool"` / `tool_result` content to Claude `image` source blocks so OpenAI-compatible clients (Kimi Code CLI `ReadMediaFile`, and any other tool that returns media) no longer 400 the next Claude-format upstream turn ([#9692](https://github.com/diegosouzapw/OmniRoute/issues/9692))
+- **fix(resilience):** retry a retryable Codex pre-output 502/503/504/507 once on the same account (2–3s jitter) before cooling the connection, and stop translating that mixed pool into an all-accounts quota `429` ([#9708](https://github.com/diegosouzapw/OmniRoute/issues/9708))
+- **fix(ratelimit):** respect operator `minTimeBetweenRequestsMs` floor when relaxing the limiter on headroom — the adaptive rate-limit learning no longer silently erases a configured minimum gap between requests when the upstream reports plenty of remaining capacity ([#9763](https://github.com/diegosouzapw/OmniRoute/issues/9763)).
+- **fix(test):** remove live `npm pack` from MCP files unit test (it stalled concurrent `test:unit` via prepare→husky + monorepo pack walk); keep the static #3578 `files` allowlist + negation guards in unit and fold #3821 pack assertions into `check:pack-artifact` / `check:pack-policy` (already `--ignore-scripts`).
+- fix(dashboard): media mini-playgrounds authenticate via session instead of sending the masked API key as Bearer, fixing 401s under REQUIRE_API_KEY (#9935)
+- fix(sse): exclude search providers from credential-health scheduler sweep to stop burning billed API queries (#9970)
+- **Passthrough streaming:** stop leaking upstream SSE control lines (`id:`/`event:`/`retry:`/`:` comments) to plain OpenAI Chat-Completions-format clients, while preserving `event:` framing for OpenAI Responses API and Claude Messages API passthrough ([#10017](https://github.com/diegosouzapw/OmniRoute/issues/10017)).
+- fix(cli): stop diagnosing every Next.js instrumentation-hook failure as the Android/Termux cache bug — only the Android "Unsupported platform: android" signal now triggers the Android hint, so a win32/desktop instrumentation error surfaces its real cause instead of a useless `mkdir -p ~/.cache` (#10028)
+- **fix(build):** stop the native `better-sqlite3` addon from loading during the Next.js production build (#10060). Its `Statement` destructor aborts with `SIGABRT` when a build worker thread exits (assertion in `node::RemoveEnvironmentCleanupHook`, `env == nullptr`), which can leave the build with no standalone bundle. Every DB entry point now keys off a reliable `OMNIROUTE_BUILDING=1` signal (set by `build-next-isolated.mjs` and inherited by every spawned build worker, because Next.js workers sometimes drop `NEXT_PHASE`): `getDbInstance()` returns a no-op SQLite stub during build, `driverFactory` skips the native driver and falls through to `node:sqlite`, and the `codegraph`/`kiro-import` lazy loaders fail closed. A build-time `better-sqlite3` alias to a stub (`next.config.mjs`, turbopack) backs this up without changing runtime behaviour (the real package is still `require()`d natively via `serverExternalPackages`). Also raises the default build heap 4096→6144 MB and caps Next build worker pools (`CIRCLE_NODE_TOTAL=8`) to avoid the many-core page-data-collection SIGSEGV, and adds `.gitattributes` (`*.sh text eol=lf`) so kernel-exec'd shell scripts never ship with CRLF shebangs. Deliberately does NOT downgrade the Node base image: per the maintainer's review on #10060, `release/v3.8.50` moved to `node:26-trixie-slim` through several considered commits, so the `OMNIROUTE_BUILDING` guard is re-derived against the current base rather than reverting the FROM line; the npm pin and binary-hide dance from the original PR are dropped because our build already rebuilds `better-sqlite3` deterministically via `node-gyp` and floats `npm@latest` for the CVE overlay.
+- **fix(providers):** the five g4f.space sub-providers (Groq, Gemini, Pollinations, Ollama, NVIDIA) no longer advertise a free tier — a keyless `POST /v1/chat/completions` now returns `402 insufficient_credits` behind a proof-of-work "cake" wall (re-verified live 2026-08-22), so `hasFree` is `false` and the notes point at `g4f.dev/members.html`. The gateway still works with a member key, so its registry wiring and `authType: "optional"` are unchanged ([#10071](https://github.com/diegosouzapw/OmniRoute/issues/10071)) — thanks @chirag127
+- **fix(chatgpt-web):** Preserve native `max` thinking effort through ChatGPT Web routing ([#10077](https://github.com/diegosouzapw/OmniRoute/pull/10077)) — thanks @zannen7
+- Fix: wire AgentRouter's existing console balance fetcher into the Dashboard Quota UI (visibility gate + provider-limits data path + background sync) so its wallet balance renders instead of falling back to "Usage API not implemented" (#10078)
+- Fix: AgentRouter's dollar balance now renders as a currency-formatted "$X.XX" credits row in the Dashboard Quota UI instead of a bare percentage, and an exhausted wallet always shows exactly $0.00 (#10078)
+- fix(sse): bridge generic openai-compatible/anthropic-compatible provider type ids to their concrete uuid node id in credential lookup (#10085)
+- fix(domain): stop treating an unreported Antigravity quota fraction (`fractionReported:false`) as 0% remaining in `quotaCache.ts`, which was falsely marking every fresh/newly-connected account as exhausted and blocking multi-account rotation (#10095)
+- fix(dashboard): remap unified Kimi Code card API-key save to the admitted `kimi-coding-apikey` connection id, fixing 400 "Invalid provider" on Save (#10096)
+- fix(antigravity): strip trailing model turn for native Gemini requests too, not just Claude (#10104)
+- **fix(admission):** stop the adaptive latency-gradient collapse from permanently locking out ordinary requests — individually valid requests now make solo progress when the system is idle and normal pressure, and the collapsed limit actively recovers on sustained idle windows instead of being stuck; the critical-pressure fuse still wins over solo progress (#10111)
+- fix(sse): downgrade client-supplied `thinking:{type:"adaptive"}` to `enabled` and gate the `context-1m-2025-08-07` beta on model eligibility when a combo/fallback re-routes a request to a non-adaptive/non-1M model like claude-haiku-4-5 (avoids "adaptive thinking is not supported on this model" and "long context beta is not yet available" 400s, #10119)
+- **fix(logging):** move call-log artifact serialization and filesystem writes to a bounded singleton worker to keep request handling responsive (#10123)
+- **perf(logging):** bound each scheduled call-log rotation pass to incremental database and filesystem work (#10125)
+- **fix(streaming):** start early SSE heartbeats when Responses or Messages requests opt into streaming through the request body (#10127)
+- **fix(combo):** scope session-stickiness bindings to their owning Combo so identical first messages cannot carry a successful target into another priority chain and bypass its configured order (fixes #10136)
+- **fix(translator):** resolve the Claude thinking output cap with the routed provider so a provider-scoped-only `max_output_tokens` override is no longer invisible to `fitThinkingToMaxTokens()`, which previously let the synthesized `max_tokens` (caller room + thinking budget) go out unbounded and 400 upstream ([#10139](https://github.com/diegosouzapw/OmniRoute/issues/10139))
+- fix(providers): correct the conol-web registry fallback-models import depth, which pointed at a
+  non-existent `open-sse/config/services/` and made any suite loading the provider registry fail to
+  resolve (#10140)
+- **fix(oauth):** Claude connections created via `claude-auth/import` now send required CLI headers on the bootstrap identity call and persist a `cliUserID` device identity, fixing intermittent "Third-party apps now draw from your extra usage" 400s on otherwise valid imported subscription tokens ([#10144](https://github.com/diegosouzapw/OmniRoute/pull/10144), fixes [#10143](https://github.com/diegosouzapw/OmniRoute/issues/10143))
+- **fix(sse):** Responses-passthrough `response.completed` snapshots now drop `phase:"commentary"` items the same way live SSE frames already do, so the terminal `response.output` array no longer echoes internal commentary text that was already suppressed from the stream (#10156).
+- fix(proxy-subscriptions): allow local/loopback proxy-subscription fetch URLs (local-first, cloud-metadata still blocked) (#10158)
+- **fix(routing):** keep approximate Combo context estimates advisory so requests reach concrete targets instead of returning a pre-dispatch 400 ([#10162](https://github.com/diegosouzapw/OmniRoute/pull/10162)) — thanks @xz-dev
+- **docs(settings):** document Thinking Budget modes (passthrough vs auto-strip); fix dashboard i18n key collision that showed Auto Combo routing copy on the thinking tab; clarify independence from compression/cache ([#10169](https://github.com/diegosouzapw/OmniRoute/pull/10169))
+- fix(cli): guarantee a non-empty `[STARTUP] Fatal:` log line for any instrumentation-hook boot throw, not just DB-driver init failures (#10171)
+- fix(sse): gate structural chat admission shedding on real heap pressure instead of unconditional capacity, with a bounded headroom budget so a healthy heap can no longer bypass admission control indefinitely (#10183, #10268)
+- **fix(guardrails):** Vision Bridge handles OpenAI Responses `input`/`input_image` requests before combo vision filtering ([#10202](https://github.com/diegosouzapw/OmniRoute/pull/10202)) — thanks @Zartharas
+- **fix(cursor):** Stop truncating pending tool calls on non-composer models when a KV checkpoint arrives after text but before the `exec_mcp` frame — the KV short-circuit is now gated to the composer family where it was verified ([#10215](https://github.com/diegosouzapw/OmniRoute/issues/10215)).
+- **fix(responses):** repair corrupted SSE deltas for non-ASCII streams by keeping a single stream-aware `TextDecoder` (`{ stream: true }`) across `transform()` calls instead of recreating it per chunk and decoding without the `stream` flag. When a multi-byte UTF-8 character (CJK/emoji) was split across two TCP chunks — common in Chinese streaming text — the per-chunk decoder truncated it to `U+FFFD`, corrupting every delta while the rebuilt `*.done` snapshot stayed internally identical ([#10223](https://github.com/diegosouzapw/OmniRoute/issues/10223))
+- **fix(combo):** defer the known-context-overflow hard rejection for compressible requests so compression runs before the final context gate, instead of a raw-body estimate 400'ing generic Responses clients targeting a large model before OmniRoute can shrink it ([#10225](https://github.com/diegosouzapw/OmniRoute/issues/10225))
+- **fix(api):** deleting a manually-added custom model no longer tombstones a provider-synced model that shares its id. `DELETE /api/provider-models` is addressed by `provider` + `model` alone, so when both a custom row and a synced row existed for one id it removed both and wrote `isDeleted:true`. `replaceSyncedAvailableModelsForConnection` then filtered that id out of every subsequent re-import, so the provider could never resync — model sync kept reporting `added: N` while the catalog stayed empty and `/v1/models` never listed the model again, even though routing to it still worked. The custom row is now removed first and its presence is treated as the operator's intent, leaving the synced sibling importable; a synced-only delete still tombstones as before (#3199, #3782 unaffected) ([#10228](https://github.com/diegosouzapw/OmniRoute/pull/10228)) — thanks @Neuron-Mr-White
+- **Audio Bridge:** fix production transcription self-loop uploads so real audio reaches the configured STT provider instead of falling back to an unavailable-provider stub ([#10229](https://github.com/diegosouzapw/OmniRoute/pull/10229)).
+- **fix(api):** DeepSeek V4's native `max` reasoning tier is now reachable. DeepSeek accepts `reasoning_effort` `low`/`high`/`max` and maps `medium`/`xhigh` down to `high`, while OmniRoute's canonical vocabulary collapses `max` onto `xhigh` — so `{"effort":"max"}` silently resolved to `high` and the catalog never advertised a `max` tier (or its `<model>-max` variant). Following the existing `extendCodexGpt56EffortValues` precedent, the native tier is now preserved for `deepseek`/`ds` V4 models only; the global effort vocabulary is unchanged, routed namespaces (`openrouter/deepseek/…`, `tllm/deepseek_v4`, `oc/deepseek-v4-flash-free`) keep the canonical behavior, and an explicit client `reasoning_effort` still wins ([#10230](https://github.com/diegosouzapw/OmniRoute/pull/10230)) — thanks @Neuron-Mr-White
+- **fix(providers):** FreeAIAPIKey now targets `api.freeaiapikey.com`, the host upstream names in its `410 endpoint_moved` response — every request through the provider was failing — and its catalog is resynced to the 10 models the live `/v1/models` actually serves ([#10233](https://github.com/diegosouzapw/OmniRoute/pull/10233))
+- **fix(providers):** MonsterAPI's deprecation now actually applies — the flag was written as `isDeprecated`, a key no consumer or schema reads, so the provider kept rendering as healthy in the dashboard, the onboarding wizard and the generated provider reference ([#10234](https://github.com/diegosouzapw/OmniRoute/pull/10234))
+- **fix(cliproxy):** read platform/arch at runtime via `os.platform()`/`os.arch()` in `binaryManager` so the embedded installer selects the Windows/ARM assets even when the release bundle is built on a Linux runner (fixes #10244)
+- **fix(providers):** compatible/custom providers now save valid Data URL icons and show Add/Edit save failures instead of silently doing nothing ([#10247](https://github.com/diegosouzapw/OmniRoute/pull/10247)) — thanks @xz-dev
+- **fix(models):** custom model metadata and compatible-provider context overrides now take precedence over discovered metadata, while deleting a synced model no longer creates a permanent tombstone so a later provider sync can restore it ([#10248](https://github.com/diegosouzapw/OmniRoute/pull/10248)) — thanks @jackjinke
+- fix(open-sse): stop concurrent requests colliding on the same dedup hash for non-OpenAI target formats (#10249)
+- **fix(translator):** Text-format tool calls emitted inline by some models are now converted to proper `tool_use` blocks. Certain models (DeepSeek, Qwen) return tool invocations as `<tool_call>{"name":"Bash","arguments":{…}}</tool_call>` or `TOOL_CALL Read: {"file_path":"…"}` inside the text stream instead of the structured `tool_calls` field. Both formats leaked through the Claude translators as plain text, so Claude Code rendered the raw block and stalled instead of executing the tool. `extractXmlInvokeBlocks` (previously `<invoke>`-only) now scans for all three shapes in a single pass and emits `content_block_start`/`input_json_delta`/`content_block_stop` events, in both `openai-to-claude` and `gemini-to-claude` (Antigravity) paths ([#10251](https://github.com/diegosouzapw/OmniRoute/pull/10251))
+- fix(dashboard): make provider card warning indicators expose the interaction they advertise (#10261)
+- fix(command-code): route chat to the documented /provider/v1/chat/completions endpoint instead of the CLI-only /alpha/generate, which Command Code gates/blocks for external callers (#10265)
+- **fix(providers):** preserve validator HTTP status codes in API-key and web connection-test results so callers can distinguish authentication, rate-limit, and upstream failures ([#10272](https://github.com/diegosouzapw/OmniRoute/pull/10272)) — thanks @Zartharas
+- **fix(sse):** tiny-budget reasoning probes (e.g. Claude Code's `/model` check sends `max_tokens: 1`) are answered with a valid truncated 200 instead of relaying the upstream 5xx "empty response content" — which previously also marked the connection unavailable and poisoned fallback/cooldown bookkeeping for a request that is only a probe ([#10281](https://github.com/diegosouzapw/OmniRoute/issues/10281)) — thanks @harkaranbrar7
+- fix(video): stop advertising the googleflow (Veo) video provider as working and fail fast with a clear diagnostic — its submit/poll endpoints 404 and no server-side OAuth transport can satisfy the working endpoint (#10285)
+- **fix(build):** stop Turbopack from dead-code-eliminating the Windows Tailscale branches of `src/lib/tailscaleTunnel.ts` in the published build (#10293). The release `dist` is bundled on a Linux runner, and the bundler constant-folds `process.platform`, pruning every non-Linux branch — the Windows installers shipped with no `where` lookup, an always-injected `--socket`, and a lost `net start Tailscale`/windows-default-binary path. The module now reads the platform at runtime via `os.platform()` (a function call a bundler cannot fold), so the Windows branches survive on any build machine; a vitest regression test mocking `os.platform()` → `win32` guards the anti-fold invariant (RED before, GREEN after).
+- **fix(ops):** Docker HEALTHCHECK defaults to the lightweight `/healthz` lifecycle probe instead of the heavy `/api/monitoring/health` path, with an `OMNIROUTE_HEALTHCHECK_PATH` opt-in override ([#10311](https://github.com/diegosouzapw/OmniRoute/pull/10311))
+- fix(api): hash the API key before using it as the model-catalog cache Map key (no raw credentials in process heap) (#10313)
+- fix(resilience): keep combo quality and auth failure reasons separate and redact connection labels in terminal errors (#10314)
+- fix(dashboard): send periodic WS heartbeat pings so live dashboard connections stop dropping every ~35s (#10319)
+- **fix(chat-body-admission):** restore a single process-wide admission budget — heavyweight leases and queued bytes are now bounded once for the whole process instead of per session, so one session can no longer mint extra capacity or starve others; per-session fairness is preserved via round-robin dispatch ([#10110](https://github.com/diegosouzapw/OmniRoute/issues/10110))
+- **fix(providers):** validate Z.ai web Local Storage sessions against the authenticated user-settings endpoint and preserve exact upstream status codes ([#10329](https://github.com/diegosouzapw/OmniRoute/pull/10329)) — thanks @Zartharas
+- **fix(opencode-plugin):** publish bare combo model ids without the plugin provider prefix so OpenCode can select them ([#10345](https://github.com/diegosouzapw/OmniRoute/issues/10345))
+- **fix(backend):** log `auto/<family> matched no connected models` once per process per label instead of every minute ([#10346](https://github.com/diegosouzapw/OmniRoute/issues/10346))
+- fix(backend): redact client IPs and account prefixes from default proxy logs (#10348)
+- **fix(github):** proactive credential health now verifies GitHub access tokens through the existing Copilot token exchange, marks only a confirmed `401 Unauthorized` as expired, and leaves rate limits, permission failures, upstream failures, and network errors routable ([#10352](https://github.com/diegosouzapw/OmniRoute/issues/10352)) — thanks @RaviTharuma
+- **fix(docker):** warn at boot when `OMNIROUTE_MEMORY_MB` disagrees with `NODE_OPTIONS --max-old-space-size`, and document that the standalone/Docker launcher appends `OMNIROUTE_MEMORY_MB` last ([#10353](https://github.com/diegosouzapw/OmniRoute/issues/10353))
+- fix(providers): GitLab Duo falls back to the public Code Suggestions endpoint when direct_access returns 401 (#10365)
+- **fix(db):** `getSettings()` defaults `debugMode` to `false` — fresh installs no longer run in debug mode (persisted `debugMode: true` is preserved) ([#10372](https://github.com/diegosouzapw/OmniRoute/pull/10372) — thanks @lamchun1110)
+- **fix(translator):** Consolidate tool-name casing normalization into a single `restoreClaudeToolName` helper reused across every response path (`openai-to-claude`, `gemini-to-claude`, `stream` passthrough, xAI and Antigravity handlers), replacing six hand-copied 7-entry casing maps. The shared helper resolves via the request-side `toolNameMap` first (preserving declared PascalCase and MCP/alias names), then the complete `TOOL_RENAME_MAP` (which already covers `glob`/`grep`/`task`/`todowrite`/`skill`/`askuserquestion`/etc.), then the `#7926` TitleCase→lowercase fallback for map-less clients. This closes the coverage gap that left `TodoWrite` and other tools failing with `Error: No such tool available: todowrite`, fixes a `ReferenceError` in `remapToolNamesInResponse`, and preserves the Gemini thought-signature persistence (`#8979`) and OpenAI→Claude `toolNameMap` restoration that must not regress ([#10374](https://github.com/diegosouzapw/OmniRoute/issues/10374))
+- **fix(responses):** preserve native tool definitions for custom OpenAI-compatible providers when using the Responses API (`/v1/responses`). When `apiType` is set to `"responses"` (or `_omnirouteForceResponsesUpstream` is enabled), OmniRoute passes native tool shapes (`custom` with lark grammars, `namespace`, `local_shell`) directly upstream without running a lossy Responses→Chat→Responses conversion ([#10374](https://github.com/diegosouzapw/OmniRoute/issues/10374))
+- fix(dashboard): Free Tier 'used this month' now includes live usage_history rows, not just the rolled-up daily summary (#10381)
+- **fix(executors):** OpencodeExecutor and MimocodeExecutor now rotate to the next account on network exceptions (timeout, connection refused/reset) when the failed account has a dedicated proxy, not only on 429 — a throw on one account no longer fails the whole request when other accounts remain. Accounts sharing the default egress (no proxy) fail fast instead of retrying the same outage against every account. The shared rotation mechanics (`pickAccount`/`markCooldown`/`markSuccess`) are now extracted into `accountRotation.ts`, fixing an identical unconditional-cooldown gap that pre-dated this PR in MimocodeExecutor ([#10393](https://github.com/diegosouzapw/OmniRoute/pull/10393))
+- **fix(sse):** the header-budget drop warning fires once per unique dropped-header set instead of on every SSE response (warn-storm fix) ([#10397](https://github.com/diegosouzapw/OmniRoute/pull/10397) — thanks @lamchun1110)
+- fix(sse): fail over combo streaming responses that reach `finish_reason` with zero content, reasoning, or tool_calls instead of forwarding a terminated-but-empty completion (#10404)
+- **fix(guardrails):** Vision Bridge now reroutes whole requests for named combos whose targets have zero vision-capable models (previously such image requests died with `capability_mismatch` when the describe path could not run), and when the fallback describe path also fails for every image the request degrades to explicit `(unavailable)` stub text instead of preserving images the combo cannot consume ([#10415](https://github.com/diegosouzapw/OmniRoute/pull/10415)) — thanks @rqzbeh
+- **fix(antigravity):** geo-blocked egress (Google "User location is not supported") is now classified (scoped to the Google AI surfaces that emit it: Cloud Code/Gemini Code Assist, Gemini API, Vertex), cached as a 24h per-account exclusion so routing continues with other accounts, and surfaced with an actionable message; the dashboard connection test now probes the real `streamGenerateContent` model surface instead of the non-geo-restricted OAuth userinfo endpoint ([#10420](https://github.com/diegosouzapw/OmniRoute/pull/10420)) — thanks @rqzbeh
+- **fix(antigravity):** strip competing-agent identity sentences from system prompts (e.g. "You are a Claude agent, built on Anthropic's Claude Agent SDK.") that Antigravity flags and answers with 429 RESOURCE_EXHAUSTED (port of decolua/9router b566b20) ([#10420](https://github.com/diegosouzapw/OmniRoute/pull/10420)) — thanks @rqzbeh
+- **fix(antigravity):** accounts with an empty Cloud Code `projectId` now heal themselves — failed auto-onboarding (`onboardUser`) attempts are retried after a short backoff instead of being memoized forever, so the missing Google project is created without user action on a later request or token refresh ([#10424](https://github.com/diegosouzapw/OmniRoute/pull/10424)) — thanks @rqzbeh
+- **fix(antigravity):** Google deprecated automatic project creation for standard-tier (personal) accounts — when `onboardUser` completes without a project id the account now fails fast with a clear `403 GCP_PROJECT_REQUIRED` message (no more generic 422 or delayed 429 RESOURCE_EXHAUSTED), and a manual GCP Project ID override is available in the connection editor so operators can enter their own project id ([#10424](https://github.com/diegosouzapw/OmniRoute/pull/10424)) — thanks @rqzbeh
+- **fix(usage):** read Gemini `usageMetadata` out of the antigravity `{ response: {...} }` envelope so non-streaming requests log real token usage instead of `IN 0 | OUT 0` (port of decolua/9router#59d858b) ([#10430](https://github.com/diegosouzapw/OmniRoute/pull/10430)) — thanks @rqzbeh
+- **fix(usage):** surface Gemini `cachedContentTokenCount` into `cached_tokens` for non-streaming requests so cache-hit accounting matches the OpenAI/Claude/Responses branches and the streaming path (follow-up to the #10430 envelope fix) ([#10465](https://github.com/diegosouzapw/OmniRoute/pull/10465)) — thanks @rqzbeh
+- **fix(antigravity):** automatically rotate to a sibling account when one is BYOP (GCP Project ID required, `gcp_project_required` 422) — the account is excluded from selection for 24h and the request succeeds via another account instead of failing fast; the actionable 422 is surfaced only when no sibling exists (follow-up to the #10424 BYOP fast-fail) ([#10470](https://github.com/diegosouzapw/OmniRoute/pull/10470)) — thanks @rqzbeh
+- fix(mitm): forward passthrough traffic to the actual requested Host instead of misrouting every non-TARGET_HOSTS request to the hardcoded Antigravity sandbox host (#10479)
+- **fix(docker):** point the bifrost sidecar at the real `ghcr.io/maximhq/bifrost:v1.6.11` tag and the cliproxyapi sidecar at the official `docker.io/eceasy/cli-proxy-api:v6.9.7` image (the previously pinned tags never existed), and complete the runtime `OMNIROUTE_BASE_PATH` subpath patch for Next 16 standalone (assetPrefix + client env + baked asset URLs) so prebuilt images respect the webpath env var ([#10482](https://github.com/diegosouzapw/OmniRoute/pull/10482))
+- fix(sse): stop ZWJ-obfuscating the substring "hermes" in user messages and hostnames (#10484)
+- **fix(memory):** auto-check Qdrant health on mount and stop the false-red status badge on `/dashboard/memory?tab=engine` — the badge treated "not yet checked" (`health === null`) as a failure, so a healthy Qdrant showed red after every page refresh until "Test connection" was clicked; settings changes now also invalidate the stale result and re-check after the save persists, so a health check racing the settings PUT can no longer keep the badge red until a manual re-test ([#10489](https://github.com/diegosouzapw/OmniRoute/pull/10489))
+- **test(compression):** align source-contract tests with the merged `release/v3.8.50` base (`aa912c42a`) — accept the multi-line `providerTransport` shape in `omniglyph-chatcore-plumbing` and give the pipeline-circuit-breaker fixture a `metadata.executionStages` (both structural changes landed in the base merge) ([#10489](https://github.com/diegosouzapw/OmniRoute/pull/10489))
+- fix(cli): use 127.0.0.1 for the readiness health-check poll instead of localhost, avoiding Windows DNS-resolution delays that made a healthy server report as never-ready (#10508)
+- **fix(providers):** zed-hosted OAuth now redirects the browser back to the dashboard's own loopback port (auto-completing the login), and the manual paste path accepts Zed's user_id/access_token callback URL instead of erroring with "No authorization code found" ([#10517](https://github.com/diegosouzapw/OmniRoute/pull/10517)) - thanks @phatchau036
+- **fix(providers):** allow token-backed web sessions stored with `authType: "cookie"` to refresh their token through the provider update API ([#10518](https://github.com/diegosouzapw/OmniRoute/pull/10518)) — thanks @Zartharas
+- **fix(providers):** test token-backed web sessions through their provider validator instead of the OAuth path ([#10519](https://github.com/diegosouzapw/OmniRoute/pull/10519)) — thanks @Zartharas
+- **fix(compliance):** redact additional provider API keys from audit-log payloads ([#10521](https://github.com/diegosouzapw/OmniRoute/pull/10521)) — thanks @Zartharas
+- fix(providers): register a real Firefly auth probe under both the `firefly` alias and the `adobe-firefly` canonical id, and normalize the provider id before the generic web-cookie fallback, so a Firefly connection stops always reporting "Provider validation not supported" (#10522)
+- fix(services): isolate probeBeforeSpawn adoption tests on distinct ports to stop the order-dependent flake (#10523)
+- fix(sse): auto-replay a bounded multi-turn trajectory in the DeepSeek Web prompt builder for clients that never send `tools[]`, so agentic clients like Cline stop losing the original task after a couple of turns (#10527)
+- **fix(network):** direct (no-proxy) egress now bounds each attempt's response-start window (default 30s, `OMNIROUTE_DIRECT_HEADERS_TIMEOUT_MS`) and retries once on a fresh no-keep-alive socket, so a silently-dropped pooled keep-alive connection can no longer stall direct providers (opencode-go, command-code) until a service restart ([#10214](https://github.com/diegosouzapw/OmniRoute/issues/10214))
+- **fix(models):** align Codex GPT-5.6 context limits with the Codex catalog and honor model context overrides when advertising combos ([#10530](https://github.com/diegosouzapw/OmniRoute/issues/10530))
+- **fix(deps):** upgrade `@atjsh/llmlingua-2` from 2.0.3 to 2.0.5 and remove `@tensorflow/tfjs` from the LLMLingua SLM stack — 2.0.5 adds official Transformers.js v4 support (peers `@huggingface/transformers` at `^3.5.2 || ^4.0.0`) and 2.0.4+ no longer requires TensorFlow.js, restoring compatibility with OmniRoute's Transformers.js v4 while dropping the largest single contributor to the optional runtime footprint ([#10536](https://github.com/diegosouzapw/OmniRoute/issues/10536))
+- **fix(deepseek):** Advertise `none`, `low`, `high`, and `max` for V4 Pro and Flash, derive OpenCode Go effort aliases from base-model metadata, and route those models through native Responses ([#10540](https://github.com/diegosouzapw/OmniRoute/pull/10540)) — thanks @jackjinke
+- **fix(a2a):** use a constant-time bearer compare in `/api/a2a/tasks` via `crypto.timingSafeEqual`, matching the `tokensMatch` helper already used in `src/app/a2a/route.ts` and removing the last non-constant secret comparison in the repo ([#10544](https://github.com/diegosouzapw/OmniRoute/pull/10544))
+- Preserve portable plaintext reasoning by default across streaming and non-streaming Chat Completions and Responses routes while keeping provider-bound opaque state target-compatible. Direct requests drop incompatible continuation reasoning by default; combos can explicitly skip incompatible targets without mutating the request. Known providers no longer show redundant encrypted-reasoning controls. (#10550, #10959)
+- fix(dashboard): show the real model count on the "List Models" endpoint card instead of a permanent "—" (#10553)
+- **fix(cli):** ignore the operating system `HOSTNAME` when choosing the server bind address on Linux and macOS, preventing startup failures when the shell hostname differs from `os.hostname()`; use `OMNIROUTE_SERVER_HOST` for explicit non-Windows configuration while preserving the legacy `HOSTNAME` fallback on Windows ([#10557](https://github.com/diegosouzapw/OmniRoute/pull/10557), closes [#10492](https://github.com/diegosouzapw/OmniRoute/issues/10492)) — thanks @redzrush101
+- **fix(providers):** OpenCode `x-opencode-session` now derives a stable, conversation-scoped fingerprint via `generateSessionId()` instead of a fresh random UUID per request, so upstream prompt caching can hit across requests in the same conversation; bare `big-pickle`/`*-free` model ids now keep routing to an active opencode-family connection even when its synced catalog is temporarily stale; and bare requests to no-auth catalog providers (e.g. `opencode`) now echo the listing-valid `<alias>/<model>` form in `response.model` so clients validating against `/v1/models` don't warn ([#10571](https://github.com/diegosouzapw/OmniRoute/pull/10571))
+- **fix(mcp):** make GitHub skill tools discoverable through `omniroute_tool_search`
+- fix(providers): remove 10 retired model ids from the crof seed catalog so /v1/models stops advertising models crof.ai no longer serves (#10577)
+- **fix(audio):** when a prefix-matched STT provider has no credentials, retry gateways that list the same nested model id (e.g. `deepgram/nova-3` → `openrouter/deepgram/nova-3`) and mention those ids in the 400; stop documenting bare `deepgram/nova-3` as the default example ([#10583](https://github.com/diegosouzapw/OmniRoute/issues/10583))
+- fix(sse): resolve the short provider-alias prefix (e.g. `el/`) advertised by GET /v1/models for audio speech, transcription and translation model ids (#10586)
+- fix(sse): map OpenAI-compat voice names to real ElevenLabs voice_ids in direct TTS (#10589)
+- fix(dashboard): route the Playground's ChatTab "Send" through the endpoint actually selected in StudioConfigPane (`search`, `web.fetch`, etc.) instead of always POSTing to `/api/v1/chat/completions`, fixing the false "No active credentials for provider" 404 when testing search-only providers (#10592)
+- **fix(providers):** Magnific Mystic is now the canonical provider (`/dashboard/providers/magnific`, `magnific/<model>`). It uses the Magnific API (`api.magnific.com` + `x-magnific-api-key`), dashboard Test Connection validates keys without starting a paid generation, and the old `freepik` slug remains a legacy alias ([#10594](https://github.com/diegosouzapw/OmniRoute/pull/10594))
+- **fix(sse):** Include the redacted upstream error body in the per-target COMBO failure log (`Model X failed, trying next`) so operators can triage a 400/500 without reproducing the request ([#10597](https://github.com/diegosouzapw/OmniRoute/issues/10597))
+- **fix(xai):** trim Chat Completions `messages` and Responses `input` to xAI's 800-item history cap before dispatch, so long tool loops no longer die on `413 Chat history exceeds the 800-message limit` ([#10601](https://github.com/diegosouzapw/OmniRoute/pull/10601))
+- **fix(cli):** derive the machine-id token correctly under plain Node — `await import("node-machine-id")` puts the CJS exports on `.default`, so the destructured `machineIdSync` was `undefined` and the catch blanked the token, sending every management request unauthenticated; `OMNIROUTE_CLI_SALT` rotation is now honored too ([#10612](https://github.com/diegosouzapw/OmniRoute/pull/10612))
+- **fix(cli):** `omniroute setup --add-provider --api-key <key>` no longer aborts with "Provider API key is required" — Commander bound the value to the program-level `--api-key` (the OmniRoute server key), leaving the subcommand's own option undefined; `OMNIROUTE_API_KEY` now works as the error message advertised ([#10613](https://github.com/diegosouzapw/OmniRoute/pull/10613))
+- fix(dashboard): make /api/models agree with /v1/models on synced-catalog coverage instead of reporting stale models as available (#10615)
+- **Combo routing:** await each connection's token limit before reserving quota. The old lookup treated the `Promise` as a connection and dropped `rateLimitOverrides.tpm` ([#10686](https://github.com/diegosouzapw/OmniRoute/pull/10686)).
+- fix(guardrails): resolve the public provider alias before querying credentials in the Vision Bridge router, so command-code/opencode (and any alias!=id provider) are no longer reported as "unusable" despite active connections (#10702)
+- fix(dashboard): filter the Modality Bridge Vision model picker to vision-capable models, matching the sibling Video/Audio tabs (#10703)
+- fix(usage): repair provider-reported input_tokens: 0 on non-trivial requests instead of passing it through unrepaired (#10705)
+- fix(cli): distinguish a CLI-probe timeout from a genuinely absent binary in locateCommand, and resolve the Hermes Agent Apply flow's `keyId` server-side instead of writing the `YOUR_OMNIROUTE_API_KEY_HERE` placeholder (#10710, #10711)
+- fix(cli): pass --allow-scripts for the runtime's own npm-installed dependencies, so npm 12+'s default install-scripts block no longer silently skips better-sqlite3's native build (#10713)
+- fix(db): filter `getProviderMetrics()` to providers with a live `provider_connections` row so a deleted provider stops permanently ghost-haunting the Home "Provider Topology" widget (#10714)
+- fix(proxy): keep password-only proxy credentials instead of dropping them when no username is set (#10720)
+- **fix(executors):** the Meta AI (muse-spark-web) WebSocket send-message timeout now reports the socket's `readyState` at the moment it fires, so a "Meta AI WS timed out" failure can be told apart as either the connection never opening (`readyState=0`) or opening successfully and then going silent (`readyState=1`) — the exact ambiguity that made #10727 undiagnosable from logs alone (#10727).
+- **fix(providers):** copilot-m365-web chat turns no longer surface as `(empty response)` — the type:4 invocation is aligned with the 2026-08 wire shape and now carries its type:1 Metrics follow-up in the same socket write, and the access token pre-flight-refreshes from a stored refresh_token instead of requiring a DevTools re-capture every ~75 minutes ([#10732](https://github.com/diegosouzapw/OmniRoute/pull/10732) — thanks @acc0mplish)
+- **fix(catalog):** stop counting `getTokenLimit()`'s generic 128k catch-all as a known combo window, so `/v1/models` advertises the min of sourced member contexts instead of collapsing a 500k combo to 128k ([#10734](https://github.com/diegosouzapw/OmniRoute/issues/10734))
+- **fix(search):** name `/v1/search` 502s with provider id and sanitized Node cause code, without hostnames ([#10735](https://github.com/diegosouzapw/OmniRoute/issues/10735))
+- **fix(db):** pause call-log rotation and record SQLITE_CORRUPT on `/api/db/health` instead of retrying writes against a malformed pager ([#10736](https://github.com/diegosouzapw/OmniRoute/issues/10736))
+- fix(compression): skip the expensive `createCompressionStats()` pass in RTK when no message was actually compressed, matching every sibling stacked engine (#10765)
+- **fix(api):** `/api/cache/stats` reported the prompt-cache LRU, which no request path ever writes to — it answered `0 hit / 0 miss, size 0` while the semantic cache served real traffic, and the Health and Usage dashboards rendered that as fact. It now reports the semantic cache's in-memory entries, with the same response shape ([#PRNUM](https://github.com/diegosouzapw/OmniRoute/pull/10769)) — thanks @Poid-ZA, who first fixed this in #9446.
+- **fix(logging):** the app log is filterable and readable again. Entries from the tagged logger (`[LEVEL] [TAG] message`) were filed under the level instead of the component, and printf format strings were never applied, so `%s`/`%d` stayed literal with the values trailing behind them unlabelled — including every LiveWS connection line, where the format is deliberate hardening against injected format specifiers ([#PRNUM](https://github.com/diegosouzapw/OmniRoute/pull/10770)).
+- **fix(analytics):** Claude Code (`claude`/`cc`) is a flat-rate subscription, so cost analytics reports `$0` for it instead of estimating Anthropic list prices — the metered `anthropic` API keeps its real cost, and budget/quota/routing still estimate as before ([#10774](https://github.com/diegosouzapw/OmniRoute/pull/10774)) — thanks @electrumguy
+- fix(db): periodically run `wal_checkpoint(TRUNCATE)` so the SQLite WAL file shrinks on long-running servers (default 6h, override with `OMNIROUTE_WAL_TRUNCATE_INTERVAL_MS`, `0` disables) (#10781)
+- fix(sse): replace LiveWS's application-only liveness check with a protocol-level `ws.ping()`/`pong` heartbeat (RFC 6455 §5.5.2) alongside the existing one, so a read-only dashboard subscriber that never sends anything survives the connection timeout — a socket that stops reading frames entirely is still reaped exactly as before (#10782)
+- **fix(open-sse):** declare `supportedThinkingEfforts` (`low`/`medium`/`high`/`max`) on Ollama Cloud's `glm-5.1`, `glm-5.2`, `deepseek-v4-pro` and `deepseek-v4-flash` registry entries so the catalog's `appendSyncedEffortVariants()` pass — which only synthesizes selectable `-low`/`-high`/`-max` model ids from an already-populated `capabilities.effort_tiers` — can expose an effort selector for these reasoning-capable models, matching what `gpt-oss:20b`/`gpt-oss:120b` already had (#10788)
+- **fix(resilience):** scope the same-account transport retry (#9708) out of emergency-fallback and combo hops — it was retrying the free fallback model and combo targets too, doubling upstream calls and corrupting the terminal error status on those paths.
+- **fix(opencode-plugin):** respect log level in provider.models() catalog path so debug/info/warn messages are suppressed when `features.logLevel` is set to `"error"` ([#10798](https://github.com/diegosouzapw/OmniRoute/pull/10798)) — thanks @tientien17
+- **fix(providers):** Keep NVIDIA timeout probes and generic Antigravity/AGY HTTP 400 probes from poisoning credential health while preserving explicit Google geo-block handling ([#10799](https://github.com/diegosouzapw/OmniRoute/pull/10799)) — thanks @Zartharas
+- fix(db): disambiguate `createProviderConnection()`'s OAuth email dedup by `providerSpecificData.profileArn` in addition to `username`, so adding a second Kiro/AWS profile with the same email creates a new connection instead of silently merging into the first (#10815)
+- fix(oauth): stop treating the Kiro profile ARN as an account identity in `findKiroConnectionByIdentity()`, so a second Google/GitHub social login creates a new connection instead of overwriting the first — distinct Builder ID accounts share the same CodeWhisperer profile ARN, and the social token is not a JWT, so no e-mail was available to disambiguate them (#10815)
+- **fix(images):** register OpenAI `dall-e-3` in the image registry so unprefixed `dall-e-3` (and `openai/dall-e-3`) route to OpenAI Images instead of Microsoft Designer Web, and so the chat catalog no longer lists `openai/dall-e-3` as a 128k chat model ([#10832](https://github.com/diegosouzapw/OmniRoute/issues/10832))
+- **fix(security):** Outbound URL guard now resolves IPv4-mapped IPv6 literals to their embedded address, so `[::ffff:169.254.169.254]` is refused by the unconditional cloud-metadata block like its dotted spelling; `[::]` is refused alongside `0.0.0.0` ([#10843](https://github.com/diegosouzapw/OmniRoute/pull/10843)) — thanks @ntdat812
+- fix(config): exclude cookie-auth image bridges (chatgpt-web, gemini-web) from the unprefixed model scan so a bare id never silently binds to an unofficial web bridge (#10848)
+- fix(api): POST /v1/search now replies with a named `Unknown search provider: <id>` error (and field-named validation messages) instead of an opaque `Invalid request` for unrecognized or short-alias provider ids like `brave`/`serper` (#10849)
+- **fix(api):** alias `GET`/`HEAD` `/readyz` to `/healthz` so Kubernetes readiness probes do not 404 ([#10850](https://github.com/diegosouzapw/OmniRoute/issues/10850))
+- Document the conditional management authentication and 401/403 responses for `GET /api/openapi/spec`.
+- **fix(i18n):** The "Disabled" status no longer renders as the noun for a person with a disability in Japanese, Spanish, Hindi, Polish, Telugu, Urdu and both Chinese locales — 24 strings now use each catalog's existing wording (ja 無効, es Deshabilitado, hi अक्षम, pl Wyłączone, te నిలిపివేయబడింది, ur غیر فعال, zh-CN 已禁用, zh-TW 已停用) ([#10812](https://github.com/diegosouzapw/OmniRoute/issues/10812), [#10853](https://github.com/diegosouzapw/OmniRoute/pull/10853)) — thanks @ntdat812
+- **fix(skills):** Marketplace-installed skills are available to API-key-scoped requests, including existing SkillsMP and skills.sh installs ([#10854](https://github.com/diegosouzapw/OmniRoute/pull/10854)) — thanks @kriptoburak
+- **fix(catalog):** `/v1/models` no longer advertises the built-in `auto/*` ids while auto routing is disabled — they were listed but rejected at request time with `Auto routing is disabled` ([#10831](https://github.com/diegosouzapw/OmniRoute/issues/10831), [#10857](https://github.com/diegosouzapw/OmniRoute/pull/10857)) — thanks @ntdat812
+- **fix(context):** Base64 file payloads (OpenAI `file` parts, Responses `input_file`, Claude `document` blocks) are budgeted like the Gemini `inlineData` path instead of being counted as prompt text — a ~1MB PDF estimated at 350k tokens and was rejected on the context limit before reaching the provider's document pipeline ([#10840](https://github.com/diegosouzapw/OmniRoute/issues/10840), [#10858](https://github.com/diegosouzapw/OmniRoute/pull/10858)) — thanks @ntdat812
+- **fix(mcp):** MCP tool calls that wait on a model provider no longer abort after 10 seconds. `omniRouteFetch` applied a single hardcoded `AbortSignal.timeout(10000)` to every internal hop, and `omniroute_route_request` — which posts to `/v1/chat/completions` and waits on the upstream provider, plus auto-combo candidate probing before a provider is even chosen — passed no signal of its own, so it inherited it. Any route slower than 10s failed from the MCP side while the identical request succeeded through the REST API. `omniroute_web_search` and `omniroute_web_fetch` in the same file already carried an explicit 60s signal, so that value is now shared by all three provider-bound calls instead of being repeated as a literal, while management reads (health, resilience, rate limits, combos, quota, usage) keep their fast-fail 10s budget so a stalled local endpoint still cannot hold a tool call open. Both budgets are overridable through `OMNIROUTE_MCP_FETCH_TIMEOUT_MS` and `OMNIROUTE_MCP_UPSTREAM_TIMEOUT_MS`, replacing the reported workaround of patching the compiled `dist/.build/next/server/chunks/*.js`; a malformed or non-positive override falls back to the default rather than disabling the timeout
+- **fix(providers):** importing models with an expired API key now surfaces the credential error instead of reporting "No new models were added". The Import button posts to `/api/providers/{id}/sync-models`, which self-fetches the models route; that route does not fail on an upstream 401 but degrades to a catalog it already has, preferring the cache and using the local catalog only when there is no cache. A provider that imported successfully once therefore has a cache, so an expired key produced `{ source: "cache", warning: "Models probe failed (401) — using cached catalog" }` with HTTP 200 — and the #5460/#5465 degradation guard only recognised the `local_catalog` branch, so model-sync accepted it as a successful discovery, found every cached model already imported, and returned the empty-diff result. Retest does not go through this path, which is why it failed correctly and made the import look like a genuine "nothing to do". The existing rule — a degraded discovery must not be persisted as the synced catalog — is now applied to the branch it missed rather than special-casing 401/403, discriminating on the warning the fallback builder always attaches (an ordinary non-refresh cache hit attaches none, and model-sync always requests `refresh=true`). `isDegradedLocalCatalog` keeps its exact meaning and its existing tests
+- fix(api): reject a combo update that removes every model, and store the copilot's combo targets where the router reads them (#10866)
+- **fix(proxy):** proxy "Test connection" no longer reports an IPv4-only SOCKS5/SSH proxy as dead. #1255 moved every egress probe from `api.ipify.org` to `api64.ipify.org` so proxies with IPv6 egress could be tested, but `api64` is IPv6-first: a tunnel with no IPv6 route has nothing to connect to, so the probe hung until the caller's deadline and a proxy that was carrying live LLM traffic came back as a failure. Swapping the target to `api4` fixes that case and re-breaks the one #1255 fixed, so the probe now tries the targets in order instead — `api64` first, so a proxy with working IPv6 answers on the first attempt and keeps the exact behaviour #1255 introduced, including which of its addresses is reported (the egress IP is used as an identity to detect accounts of one rotation group sharing an address, so the attempts are sequential rather than raced). The attempts split the budget each call site already enforced, so no probe can take longer than it could before, and each attempt gets its own `AbortController` so exhausting the budget on an unreachable target does not abort the next one. `OMNIROUTE_PROXY_ECHO_URL` pins a single target — including a self-hosted echo — replacing the workaround of rewriting the compiled bundle after every upgrade. The relay branch of the test route still targets `api64` through `x-relay-target`, since that request egresses from the relay worker rather than the operator's tunnel
+- fix(cli): warn when a .env line never takes effect, and stop swallowing an unreadable .env (#10870)
+- **fix(db):** Remove stale MiMoCode provider configuration, including the legacy `mcode` alias, left after provider retirement while preserving historical usage and call logs ([#10873](https://github.com/diegosouzapw/OmniRoute/pull/10873)) — thanks @Zartharas
+- **fix(sse):** `getResetAwareProvider()` and the auto-combo quota lookup in `combo.ts` now canonicalize the provider id via `resolveProviderId()` before calling `getQuotaFetcher()`, so a fetcher registered under a provider's canonical id (e.g. `ollama-cloud`, `codex`) is found for combo targets stored under an alias spelling (e.g. `ollamacloud`, `cx`) instead of silently degrading reset-aware/reset-window/auto quota-aware routing to plain priority ordering (#10877)
+- **fix(provider-health):** Keep unsupported 404/405 validation probes neutral so they do not poison stored credential health or scheduler failure state, while still honoring per-connection health-check pacing ([#10878](https://github.com/diegosouzapw/OmniRoute/pull/10878)) — thanks @Zartharas
+- **fix(antigravity):** map Gemini 3.7 Flash tier ids (`gemini-3.7-flash-high/medium/low`, bare `gemini-3.7-flash`) to the upstream `gemini-3.7-flash-tiered` model id Google's Cloud Code endpoint expects, and configure per-tier thinking budgets ([#10882](https://github.com/diegosouzapw/OmniRoute/pull/10882)) — thanks @adevwithpurpose
+- **fix(memory):** enable agent memory save/update via MCP tools (`memory_save`/`update`/`search`/`delete` builtins with per-provider schemas, `apiKeyId` optional with caller-principal fallback) and gate server-side memory builtin injection to non-stream requests only ([#10887](https://github.com/diegosouzapw/OmniRoute/pull/10887)) — thanks @Egorich-print
+- **fix(perplexity-web):** make the built-in-search hint appended to every system message opt-in via `OMNIROUTE_PPLX_SEARCH_HINT` (off by default) — Perplexity's answer engine searches anyway, and the hint leaked into replies as meta-commentary for coding clients ([#10902](https://github.com/diegosouzapw/OmniRoute/pull/10902), extracted from [#8634](https://github.com/diegosouzapw/OmniRoute/pull/8634)) — thanks @danscMax
+- **fix(providers):** the loopback readiness gate no longer memorizes a failed probe — the next caller after 30s starts a fresh probe, and a readiness failure is logged once per probe instead of once per caller ([#10903](https://github.com/diegosouzapw/OmniRoute/pull/10903))
+- **fix(relay):** the Cloudflare proxy-relay worker now resolves `x-relay-path` through the shared `resolveRelayTarget()` guard instead of concatenating it onto the validated target. PR #4643 and its follow-up applied that guard to the Deno and Vercel workers; the Cloudflare generator, ported separately from upstream `decolua/9router` PR #1360, kept `fetch(targetBase + relayPath)`. Validating `x-relay-target` and then concatenating is not sufficient — the path re-points the request past the host that was just checked, through userinfo (`/x@evil.com`), a backslash (`\evil.com`), or a protocol-relative path (`//evil.com/x`). The guard is embedded verbatim under a literal `const resolveRelayTarget =` binding so the hardcoded call site still resolves when the SWC-minified standalone build mangles the source function's own name (#6149), and the new regression test pins that property for this worker by renaming the embedded function and re-evaluating the emitted source. The auth check and the private/loopback target guard are unchanged
+- **fix(build):** the `next` Docker image no longer crashes on boot with `ReferenceError: require is not defined in ES module scope`. The standalone `server.js` is CommonJS, but the `postbuild` colocate step was re-adding `"type":"module"` to the standalone root `package.json` (undoing `assembleStandalone`'s strip) to make its ESM worker bundles load. The `type:module` scope is now written per-worker-directory instead of on the root, so `server.js` stays CommonJS while the workers stay ESM ([#10936](https://github.com/diegosouzapw/OmniRoute/pull/10936), fixes [#10933](https://github.com/diegosouzapw/OmniRoute/issues/10933)) — thanks @arminanton
+- fix(cli): always emit limit.output in generated OpenCode config so schema validation passes for metadata-less models (#10940)
+- **fix(relay):** the private/loopback guard the three proxy-relay workers embed no longer misses four host spellings, and now lives in one place instead of three byte-identical inline copies. Driving `new URL(target).hostname` the way the workers do, the previous guard allowed `::` (the unspecified address, which reaches a service bound to the IPv6 loopback), `localhost.` (the FQDN root dot defeated the exact match and every `.localhost`/`.local`/`.internal` suffix rule, so `svc.internal.` slipped too), `::127.0.0.1` (the deprecated IPv4-compatible form — only `::ffff:` was checked), and `feb0::1` (link-local is `fe80::/10`, spanning `fe80`–`febf`, but only the literal `fe80:` spelling matched). The policy moved to `src/lib/proxyRelay/privateHostname.ts` and is embedded verbatim via `Function#toString` under a literal const name, the same mechanism `resolveRelayTarget` already uses for these workers, so a minified standalone build cannot break the call site (#6149). Nothing previously blocked is now allowed. Severity is low — reaching a worker needs the `x-relay-auth` secret and these are edge runtimes where loopback has nothing listening — but the suffix-rule bypass held regardless of runtime
+- **Account rotation:** make `fallbackStrategy: "least-used"` actually rotate. The strategy sorts on `lastUsedAt` but never wrote it — only the round-robin branch committed — so on a pool where every `last_used_at` was still `NULL` the tie-break fell through to `priority` and returned the same connection on every dispatch ([#10945](https://github.com/diegosouzapw/OmniRoute/issues/10945)).
+- **Desktop auto-update (Windows):** stop the in-app updater 404ing on every release. NSIS used electron-builder's default artifact name, whose spaces GitHub rewrites to `.` on upload while `latest.yml` keeps `-`, so the manifest pointed at `OmniRoute-Setup-X.Y.Z.exe` while the published asset was `OmniRoute.Setup.X.Y.Z.exe`. The name is now set explicitly to the dot form the asset already has, so nothing published changes name ([#10947](https://github.com/diegosouzapw/OmniRoute/issues/10947)).
+- Preserve explicit plaintext reasoning when a Responses reasoning item also carries opaque provider state (rare OpenCode Go `deepseek-v4-flash` responses). Mixed plaintext + opaque input is projected onto the target transport: plaintext targets keep portable text, opaque targets keep provider state. Opaque-only reasoning is dropped when the selected target cannot replay it, allowing cross-model conversations to continue. (#10949, #10959)
+- **fix(catalog):** preserve provider-declared reasoning effort tiers instead of replacing them with generic defaults ([#10953](https://github.com/diegosouzapw/OmniRoute/pull/10953)) — thanks @xz-dev
+- fix(cli): combo create accepts --models and no longer creates empty combos (#10954)
+- fix(cli): resolve $ref path params and add PATCH combos requestBody in generated API commands (#10955)
+- fix(sse): default single-target incompatible reasoning to drop for agentic replay — single-target requests to opaque reasoning targets now gracefully strip incompatible plaintext reasoning history instead of returning HTTP 400, matching combo default behavior while preserving operator and per-request overrides ([#10959](https://github.com/diegosouzapw/OmniRoute/issues/10959))
+- fix(sse): combo diagnostics no longer truncate `exhausted_connection` entries to a hardcoded `provider: "unknown"` with the provider prefix eaten by an 8-char slice — the real provider id is preserved and only the connection id is truncated (#10967)
+- fix(sse): combo terminal failures caused entirely by quota/account-balance exhaustion (including a durable HTTP 403 `insufficient_quota` / `AUTHZ_INSUFFICIENT_BALANCE`) now stamp a stable `quota_exhausted` diagnostics reason with a `switch-combo` recovery hint instead of the misleading default `retry` action (#10966)
+- **fix(search):** skip catalog-default SearXNG `http://localhost:8888/search` so Docker/K8s search does not ECONNREFUSED then 502 into the next provider ([#10976](https://github.com/diegosouzapw/OmniRoute/issues/10976))
+- fix(command-code): surface reasoning-only output as content when a model emits no text-delta (#10986)
+- **fix(ci):** clear inherited `release/v3.8.50` quality-gate reds on the X Search PR: drop the stale `copilot-m365-web.ts:330` public-creds allowlist, document six missing env vars, register four covering Stryker tap tests, prune leftover ESLint suppressions, replace the phantom `@/lib/db/connections` Utilization import with `getProviderConnectionById`, and fix open-sse/dashboard typecheck regressions in freebuff, browser-backed chat, auth, health matrix, and Monaco ([#10988](https://github.com/diegosouzapw/OmniRoute/pull/10988)).
+- **fix(ci):** clear remaining `release/v3.8.50` unit-shard reds on the X Search PR: pin `onnxruntime-node` to the transformers 1.24.3 copy, rebaseline OpenAPI coverage, sync goldens/i18n, honor eye-hidden no-auth models across provider aliases, await rejected-request call-log writes, absorb catalog event-loop shard contention in #9147, and align inherited tests with advisory context estimates, #10501 combo terminal-status aggregation, and current catalog/auth behavior ([#10988](https://github.com/diegosouzapw/OmniRoute/pull/10988)).
+- **Static model catalog for v0-vercel-web:** seed a static catalog for the v0-vercel-web web-cookie provider (v0-1.0-md, v0-1.5-lg, v0-1.5-md) so its dashboard "Available Models" / "Import from /models" UI serves a usable list instead of falling through to the route's 400 "does not support models listing" ([#10990](https://github.com/diegosouzapw/OmniRoute/issues/10990)).
+- fix(providers): mark the blackbox provider deprecated — api.blackbox.ai returns HTTP 404 on every path variant (sweep 2026-08-21), so the public inference surface is dead and the catalog entry now carries a deprecation notice. ([#10997](https://github.com/diegosouzapw/OmniRoute/issues/10997))
+- fix(providers): validate Dify keys against its native /v1/chat-messages endpoint (#11002)
+- **fix(accounts):** `markCooldown` now carries the failure origin (`transient` vs `terminal`) — transient 429/network only cools down, repeated terminal failures evict and are skipped by `pickAccount` until a success or operator clear ([#11008](https://github.com/diegosouzapw/OmniRoute/pull/11008)) — thanks @maxmad64bis
+- **fix(providers):** route terminal `testStatus` writes (`banned`, `deactivated`, `credits_exhausted`) through a single origin-aware passage — probe failures are recorded but never deactivate the connection ([#11009](https://github.com/diegosouzapw/OmniRoute/pull/11009)) — thanks @maxmad64bis
+- **fix(codex):** drop non-standard `codex.*` SSE events by default so OpenAI SDK / Codex CLI `/v1/responses` clients are not 502'd by `event: codex.rate_limits` ([#11014](https://github.com/diegosouzapw/OmniRoute/issues/11014)) — thanks @RaviTharuma
+- **fix(resilience):** count heavyweight `/v1` admission leases in the SIGTERM drain and send `Retry-After` on shutdown 503s so Recreate no longer looks like an empty 502 ([#11015](https://github.com/diegosouzapw/OmniRoute/issues/11015)) — thanks @RaviTharuma
+- **fix(startup):** log `Credential health scheduler disabled` when `OMNIROUTE_DISABLE_CREDENTIAL_HEALTH_CHECK` is set instead of lying with `started` ([#11016](https://github.com/diegosouzapw/OmniRoute/issues/11016)) — thanks @RaviTharuma
+- **docs(api-keys):** document that unset `DEFAULT_RATE_LIMIT_PER_DAY` is unlimited (#2289), not a hidden 1000/day cap ([#11017](https://github.com/diegosouzapw/OmniRoute/issues/11017)) — thanks @RaviTharuma
+- **fix(webhooks):** remove 3 declared-but-never-emitted events (`provider.error`, `provider.recovered`, `combo.switched`) from `WebhookEvent` — catalog now `request.completed | request.failed | quota.exceeded | test.ping`; `POST /api/webhooks` and `PUT /api/webhooks/[id]` reject ghost values with 400; OpenAPI webhook description updated across 43 locales ([11050](https://github.com/diegosouzapw/OmniRoute/pull/11050))
+- fix(providers): filter Perplexity model import to the Sonar family so Agent-API catalog ids stop surfacing as routable chat models (#11060)
+- **fix(claude):** restore canonical tool names (`bash` → `Bash`, `croncreate` → `CronCreate`) on non-streaming OpenAI→Claude conversion and through identity-echo alias maps, so Claude Code stops rejecting tool calls with "No such tool available" ([#11085](https://github.com/diegosouzapw/OmniRoute/pull/11085)) — thanks @linhdmn
+- **fix(resilience):** filter chat connection selection by each connection's *synced* model inventory on multi-host self-hosted providers (`ollama-local`, `lm-studio`, `vllm`, …), so a request for a model only one host advertises is pinned to that host instead of failing over onto a host that never had it ([#11089](https://github.com/diegosouzapw/OmniRoute/issues/11089))
+- fix(install): make the ONNX dependency chain optional so Termux/Android installs succeed again (#11095)
+- **fix(providers):** Reject silent validation degradation on provider connection patch — unknown `rateLimitOverrides` keys (e.g. a typo'd `tpm`) and empty/non-numeric values now return `400` with the rejected key list instead of being silently dropped ([#11101](https://github.com/diegosouzapw/OmniRoute/pull/11101))
+- **Autopilot suggestion counter:** the combo health autopilot summary now reports `suggestionCount` (the real number of suggested actions across all issues) instead of conflating it with link counts, while keeping `actionableCount` as a deprecated alias for backward compatibility. The `run_combo_test` action now links to the dashboard with the combo id (`/dashboard/combos?test=<comboId>`) rather than the read-only API route, so operators can actually trigger a test from the UI ([#11102](https://github.com/diegosouzapw/OmniRoute/pull/11102)).
+- **Config audit persistence:** persist the configuration audit trail to SQLite (`config_audit_log`) instead of an in-memory buffer capped at 1000 volatile entries, and bound its growth with `cleanupConfigAudit()` driven by the `retention.configAudit` setting (default 30 days), wired into `runAutoCleanup` ([#11103](https://github.com/diegosouzapw/OmniRoute/pull/11103)).
+- fix(sse): resume mid-stream recovery after a _completed_ tool call — `finish_reason: "tool_calls"` is now tracked per-call instead of as a general terminal marker, so truncation of trailing prose after a fully-delivered tool call is recoverable while in-flight calls stay blocked ([#11109](https://github.com/diegosouzapw/OmniRoute/pull/11109))
+- **fix(providers):** `reasoning_effort` now learns the accepted values from a provider's own 400/422 response and clamps to the highest one instead of forwarding an unsupported `xhigh`/`max` (or a hardcoded `"high"` fallback) — fixes custom OpenAI-compatible connections and registered providers with no reasoning metadata ([#11116](https://github.com/diegosouzapw/OmniRoute/pull/11116)) — thanks @maxmad64bis
+- **fix(sse):** parallel `function_call` items in a Responses API stream (e.g. several tool calls dispatched in the same turn) now each get a stable, distinct `index`/`id` when translated to Chat Completions streaming deltas, instead of colliding on index 0 and tripping strict stream parsers with `Expected 'id' to be a string.` ([#11144](https://github.com/diegosouzapw/OmniRoute/pull/11144))
+- **fix(analytics):** `opencode-go` is now classified as a flat-rate subscription, so cost analytics shows $0 for it instead of billing every call at the underlying model’s metered rate — it resells GLM, Kimi, Grok, DeepSeek, MiniMax, Qwen and GPT-5.x under one flat monthly fee, which made the overstatement large rather than marginal ([#11149](https://github.com/diegosouzapw/OmniRoute/pull/11149)) — thanks @electrumguy
+- fix(dashboard): keep `open-sse/config/providerRegistry.ts` free of `node:net` so the provider detail client bundle builds again — the host classification moved to a platform-free `src/shared/network/privateHost.ts` with a pure-JS `isIP` equivalent, leaving the #11122 routing behaviour unchanged (#11154)
+- **Combo create:** creating a routing combo without any model is now refused (`400`) — the CLI requires `--models`/`--model` on `combo create`, matching the dashboard which already rejected empty combos.
+- **fix(resilience):** a missing-model `404` on a provider that declares `passthroughModels: true` in the shared registry (novita, uncloseai, orcarouter and 37 others) now locks out only that model instead of cooling the entire connection — `hasPerModelQuota()` previously read only the open-sse registry and the local/self-hosted families ([#11165](https://github.com/diegosouzapw/OmniRoute/pull/11165)) — thanks @yourspraveen
+- **fix(routing):** a custom `openai-compatible-*` / `anthropic-compatible-*` connection pointing at a keyless self-hosted backend (llama.cpp, Ollama, vLLM started without an API key) now stays in the `auto/*` candidate pool instead of being silently dropped by the credential gate — for those IDs "no credential" is the normal configuration, not an unconfigured connection ([#11180](https://github.com/diegosouzapw/OmniRoute/pull/11180)) — thanks @marcs7
+- **fix(routing):** the Routing tab's "last known good provider" toggle now actually takes effect — `lkgpEnabled` was persisted and the `lkgp` strategy guarded on it, but the setting was never forwarded into the `RoutingContext` built in `resolveAutoStrategyOrder()`, so `context.lkgpEnabled` was always `undefined` and the off-switch was unreachable ([#11181](https://github.com/diegosouzapw/OmniRoute/issues/11181))
+- **fix(ollama):** Ollama Local models are no longer flattened to `chat` at sync time — the synced store persists every advertised capability and chat filtering moves to read time, so `/v1/embeddings` and `/v1/images/generations` stop rejecting models the daemon reports as capable ([#11271](https://github.com/diegosouzapw/OmniRoute/pull/11271)) — thanks @yourspraveen
+- **fix(providers):** Antigravity OAuth marks connects with no Cloud Code projectId as degraded instead of a false "Connected"; BYOP detection at connect time, auto-disable of confirmed-missing accounts, and selection-side rotation ([#11284](https://github.com/diegosouzapw/OmniRoute/issues/11284))
+- **fix(translator):** preserve omitted OpenCode `subagent.sessionID` values — optional default-less plain strings now use the Responses `null = omit` sentinel and are stripped before the client sees the tool call, so Codex/Responses no longer invent filler session IDs ([#11297](https://github.com/diegosouzapw/OmniRoute/pull/11297)) — thanks @ofonseca-pyming
+- **fix(db):** group model patterns escape regex metacharacters, so `gpt-4.1*` no longer matches `gpt-4o1-preview` and a pattern like `gpt-4(*` no longer throws `SyntaxError` out of the completion and `/v1/models` paths ([#11311](https://github.com/diegosouzapw/OmniRoute/pull/11311))
+- **fix(db):** the upstream proxy URL check judges the host by address instead of by spelling, so `http://[::ffff:169.254.169.254]`, `[::ffff:10.0.0.5]`, ULA/link-local and CGNAT targets are refused like their dotted equivalents ([#11319](https://github.com/diegosouzapw/OmniRoute/pull/11319))
+- **fix(i18n):** three `pt` strings had dropped their placeholders — the cache tile's subtitle repeated its own label instead of showing `{total}` — and a unit test now enforces placeholder parity with `en` across all locales ([#11325](https://github.com/diegosouzapw/OmniRoute/pull/11325))
+- **fix(kie):** map the remaining `google-imagen/*` KIE Market catalog ids (`nano-banana`, `nano-banana-pro`, `nano-banana-edit`) to their real, KIE-documented upstream `model` values — `#11225`'s fix only covered `nano-banana-2` ([#11326](https://github.com/diegosouzapw/OmniRoute/pull/11326)).
+- **fix(security):** `proxy-authorization` and `proxy-authenticate` are refused as upstream/custom headers, so a proxy credential is no longer forwarded to the model provider — the canonical denylist now matches the RFC 7230 §6.1 set the rest of the codebase already strips ([#11328](https://github.com/diegosouzapw/OmniRoute/pull/11328))
+- **fix(video-bridge):** fall back to the deterministic active-window midpoint when a one-frame scene-aware budget cannot preserve both timeline ends; a real FFmpeg fixture matrix now covers rapid cuts, gradual changes, static and short clips, and detector failure ([#11344](https://github.com/diegosouzapw/OmniRoute/pull/11344)).
+- **fix(translator):** Codex Responses tool calls translated for Claude clients no longer emit a duplicate `tool_use` block with the same ID and an empty name, preventing Claude Code from terminating with `No such tool available` ([#11347](https://github.com/diegosouzapw/OmniRoute/pull/11347))
+- **fix(video-bridge):** burn high-contrast timestamps into every bounded contact-sheet cell and add a real-model A/B harness whose promotion verdict stays `HOLD` until token, latency, and quality evidence is actually executed ([#11350](https://github.com/diegosouzapw/OmniRoute/pull/11350))
+- **fix(video):** fingerprint protected Video Bridge bytes, coalesce concurrent work, and fail open when the bounded TTL/LRU result cache is unavailable or corrupt ([#11362](https://github.com/diegosouzapw/OmniRoute/pull/11362))
+- **fix(catalog):** keep large `/v1/models` builds responsive by reusing the build-local capability snapshot throughout enrichment and Auto-Combo preparation, yielding cooperatively while constructing virtual candidate pools, and avoiding unrelated synchronous database diagnostics on the cache-TTL read path ([#11367](https://github.com/diegosouzapw/OmniRoute/pull/11367))
+- **fix(video):** apply the caption-frame cap after bounded visual deduplication, preserve first/final candidates plus small high-contrast motion and text changes, and version the dedup policy in result-cache identity ([#11382](https://github.com/diegosouzapw/OmniRoute/pull/11382)).
+- **Live dashboard:** honour the WebSocket port reported by `/api/v1/ws?handshake=1` instead of the port compiled into the bundle, so a `LIVE_WS_PORT` override reaches prebuilt Docker/npm images and Combo Studio Live connects behind a reverse proxy ([#11331](https://github.com/diegosouzapw/OmniRoute/issues/11331)).
+- **fix(dashboard):** Model Database sync interval slider ticks now match the thumb position — checkpoint-space slider with magnetic snap on release ([#11394](https://github.com/diegosouzapw/OmniRoute/pull/11394)) — thanks @An0nym0us92
+- **fix(api-manager):** Allowed Combos can now be restricted to zero entries: **All** is stored explicitly as `combo/*`, while **Restrict** with no selection saves an empty allowlist that denies Combo routes without blocking direct models. Existing keys are migrated to preserve their previous allow-all behavior.
+- fix(build): tolerate a same-realpath symlink or stale-typed dest in the standalone bundle assembler, fixing non-deterministic `ERR_FS_CP_EINVAL`/`ERR_FS_CP_DIR_TO_NON_DIR` crashes under heavy concurrent build I/O
+- **fix(auto):** rate-limit `auto/<family> matched no connected models` warnings to once per minute per label (`open-sse/services/autoCombo/virtualFactory.ts`)
+- fix(cli): drop the orphaned `resolveOpencodeConfigDir` re-export from `cliRuntime` — it lost its last consumer in #10246 and diverged from the canonical resolver by one directory level (#9985)
+- fix(ci): make `Build (advisory)` produce a signal again — pinned to a hosted runner with the swap/heap provisioning `Fast Production Build` proves sufficient, and scoped to fork PRs, which are the only ones `build.yml` cannot cover (72 of the last 100 PRs into `release/**`)
+- **fix(api):** hash API keys in the `/v1/models` catalog cache Map key so heap dumps cannot leak bearer tokens (`src/app/api/v1/models/catalogCache.ts`)
+- **fix(providers):** register live OpenRouter Gemini Embedding 2 ids (`google/gemini-embedding-2` and `google/gemini-embedding-2-preview`, 3072-d) in the curated embeddings catalog so `GET /v1/models` and `GET /v1/embeddings` list the ids that already serve — thanks @RaviTharuma
+- **fix(translator):** merge consecutive same-role contents in direct Claude to Gemini request translation to prevent upstream HTTP 400 errors
+- **fix(cli):** `omniroute update` now finds npm on Windows. It called `execFile("npm", …)` with no shell, and on Node ≥ 24 a `.cmd` wrapper cannot be spawned that way (nodejs/node#52554) — while a bare `npm` can also resolve to an extensionless shim `CreateProcess` refuses. The result was `✖ Could not check latest version. Is npm available?` in a terminal where `npm view omniroute version` worked fine, so the updater was unusable on Windows even though nothing was wrong with the install. This is the same class as #5379/#5542, which fixed the server-side calls; the CLI entry points were missed because they are plain `.mjs` and cannot import the TypeScript helper. `bin/cli/npm-exec.mjs` now states the same rule for them: `npm.cmd` plus a shell on win32, no shell anywhere else. Both npm lookups in `update.mjs` (version and changelog) pass a literal argv array, so enabling the shell cannot splice a runtime value into the command line — a test asserts that and fails if a future edit interpolates one. (#11335)
+- **fix(cline):** Preserve client-supplied Cline task IDs and omit the header when clients provide none, preventing request-scoped proxy IDs from being reported as tasks.
+- Hardened the Codex app-server transport after the post-merge security review of #11205: approval prompts from the app-server (its own command/file/permission execution — not the harness tool passthrough) are now auto-denied by default, with opt-in auto-approval via `providerSpecificData.codexAppServerAutoApprove` / `OMNIROUTE_CODEX_APPSERVER_AUTO_APPROVE`; the default codex sandbox changed from `danger-full-access` to `workspace-write` (override per connection or env); env-sourced capability tokens are now only sent to env-sourced URLs or operator-local hosts (loopback/RFC1918/link-local/ULA/localhost/single-label LAN names/*.local/*.ts.net/*.internal), so a connection's providerSpecificData URL can no longer exfiltrate the operator's env token; and the `/readyz` health probe no longer follows redirects while carrying the bearer token.
+- fix(codex): prefer `max_context_window` over the `context_window` pricing tier as the usable input limit in discovery, and raise the static Codex OAuth catalog to the same usable window so the conservative discovery merge no longer caps live values at the 272K pricing tier
+- **fix(catalog):** derive combo reasoning-effort tiers from the exact runtime-selectable connection scope, intersecting dynamic, pinned, allowlisted, and compatible provider-node evidence while failing closed on unknown capabilities.
+- fix(combo): evict in-memory session-stickiness bindings when a combo disables stickiness, so stale pins stop overriding the declared priority order until TTL/restart
+- fix(combo): resolve effort-suffixed command-code variants (e.g. `deepseek-v4-flash-max`) to their base model for capability lookups, so tool-bearing combo requests keep the declared priority order instead of reordering behind models with confirmed capabilities
+- **fix(db):** the `compression_run_telemetry` retention sweep now actually deletes expired rows. Its cutoff was computed in epoch seconds while the column stores epoch milliseconds, so `WHERE timestamp < cutoff` never matched and the table added by #6848 to bound `storage.sqlite` growth was unbounded in practice. Same unit mismatch as #9625, which corrected the sibling `domain_cost_history` sweep and missed this call site
+- **fix(compression):** use `pathToFileURL` in `compressionWorkerPool` so bundlers (Webpack / Turbopack) do not attempt static asset resolution of missing `compressionWorker.js` during build
+- **fix(db):** database settings API no longer returns HTTP 500 on SQLite builds compiled without the optional `dbstat` virtual table (sql.js/WASM); per-table sizes degrade to 0 instead of failing the whole stats call
+- fix(discovery): parse upstream reasoning tiers nested under metadata.reasoning.supported_efforts (neuralwatt /v1/models shape) so synced openai-compatible models advertise effort aliases
+- **fix(ops):** Docker HEALTHCHECK probes lightweight `/healthz` instead of `/api/monitoring/health` so a busy event loop does not mark the container Unhealthy (`scripts/dev/healthcheck.mjs`)
+- **fix(api):** `/v1/embeddings` 400s for native `gemini-embedding-2` now name the working OpenRouter ids (`openrouter/google/gemini-embedding-2` and the preview alias) instead of only `No credentials for embedding provider: gemini` — thanks @RaviTharuma
+- **fix(sse):** keep Codex/Anthropic quota headers under the upstream forwarding budget; drop `x-codex-turn-state` and raise the 768-byte cap (`open-sse/handlers/chatCore/responseHeaders.ts`)
+- **fix(usage):** z.ai/GLM coding-plan subscription keys now render their quota cards again, with absolute credits. Z.ai's `/api/monitor/usage/quota/limit` switched these keys from `TOKENS_LIMIT` to `CREDIT_LIMIT` rows (same `unit`/`number` semantics: unit=3/number=5 → 5-hour window, unit=6/number=1 → weekly), and the parser only matched `TOKENS_LIMIT`/`TIME_LIMIT`, so both rows were dropped and the subscription card rendered empty. `CREDIT_LIMIT` is now accepted alongside `TOKENS_LIMIT`, and when the row carries absolute credit fields (`usage`/`currentValue`/`remaining`) they are preferred over the percent-only scale, so the card shows `3341 / 28000` like z.ai's own dashboard instead of `11 / 100`
+- **fix(auth):** a connection's `lastError` now names the real upstream failure instead of the bare string `Provider error`. `markAccountUnavailable` kept the reason only when it was already a string, so every other shape collapsed to that literal — and the shape that matters most is not a string: a failed `fetch` arrives as `TypeError: fetch failed` with the actionable part on `error.cause.code`, which means a wrong port, a firewall, a DNS failure and a blocked proxy all looked identical in the dashboard and in the console line. `describeUpstreamFailure` (in `src/shared/utils/upstreamError.ts`, reusing the `extractErrorMessage` that already parsed provider bodies) reads Error messages and appends the transport code when the message does not already carry it, reads the usual provider JSON shapes (`error.message`, `message`, string `error`, `detail`, `errors[]`), and falls back to the code alone before giving up. It never serializes the error object wholesale, so a request body or header attached to an error cannot leak into the stored reason — pinned by a test.
+- **fix(live-ws):** the Live dashboard socket can now be pointed at a reverse proxy without rebuilding the image. `NEXT_PUBLIC_*` is inlined at BUILD time, so a prebuilt Docker or npm image never carries an operator's `NEXT_PUBLIC_LIVE_WS_PUBLIC_URL` — which is exactly why the browser discovers the socket through `/api/v1/ws?handshake=1` instead. The server side of that handshake, however, read only the `NEXT_PUBLIC_`-prefixed name, so it had nothing to echo: behind Traefik the dashboard kept dialling `wss://<host>:20132/live-ws` and sat on "Live disabled — WebSocket disconnected. Showing last known state." `LIVE_WS_PUBLIC_URL` is now read at runtime alongside the existing `LIVE_WS_HOST` / `LIVE_WS_PORT`, and the prefixed name stays supported as the fallback, so deployments that already set it are unaffected. Only `ws://` and `wss://` values are accepted, matching the guard the client already applies. (#11331)
+- **fix(sse):** MiniMax music models now generate audio instead of failing with `Unsupported music format: minimax-music` — the provider entry was registered in the music registry (and advertised by `/v1/models`), but `handleMusicGeneration` had no branch for its format, so every `minimax/*` music request fell through the dispatch chain to a 400. Adds the missing dispatch: a single synchronous POST with the `base_resp` envelope check (a non-zero `status_code` arrives on HTTP 200 too), `data.status` handling (an unfinished generation is reported instead of polled — the operation has no task id and no query endpoint), `url` and `hex` output formats (hex normalized to base64), `mp3`/`wav`/`pcm` containers via `audio_setting`, and the regional endpoint through the per-connection base-URL override, which is also the only host that accepts `aigc_watermark`. The registry entry gains the generation and cover model ids it was missing and drops a query URL that does not exist for this operation. Regression guard: `tests/unit/minimax-music-generation.test.ts` (9 tests).
+- **fix(models):** honor `MODELS_DEV_SYNC_ENABLED=0` as a hard kill switch over the dashboard setting so a wedged `/healthz` / UI can be recovered without HTTP (`src/lib/modelsDevSync.ts`)
+- **fix(providers):** when `OPENCODE_SYNTHESIZE_CLI_HEADERS=true`, a non-CLI client User-Agent (e.g. `curl/8.5.0`, SDKs) on opencode-go/opencode-zen/opencode-free requests is now REPLACED with the synthesized `opencode-cli/1.0.0` instead of being honored — opencode.ai's free tier (`/zen/v1`) returns `FreeUsageLimitError` 429 for generic client UAs egressing from datacenter IPs, which made the #5997 CLI-identity synthesis ineffective for non-CLI clients. Client UAs already matching `opencode-cli/…` are preserved (the real CLI's versioned identity stays intact); all other client-supplied `x-opencode-*` headers keep client-wins. Regression guard: `tests/unit/opencode-cli-headers-synthesis-5997.test.ts` (7, incl. non-CLI UA replaced + CLI UA preserved). (#5997 follow-up)
+- **OpenCode config merge:** stop `mergeOpenCodeConfig` splaying a malformed `provider` block into index keys. The root was already guarded against a non-object; the `provider` branch it spreads one level down was not, so an existing `"provider": ["a", "b"]` merged to `{"0": "a", "1": "b", …}`. Its sibling `mergeOpenCodeConfigText` already refuses the same input.
+- **fix(models):** a model synced from a provider's own `/models` discovery is now enforced at its real context window immediately, instead of waiting up to 24h for the Feature 5004 reconciler's next tick. The request-time token-limit chain resolves the window from `auto:discovery` overrides, which previously were only written at startup and on a 24h interval — so any model synced mid-cycle (models.dev not indexing it yet, no static registry entry) fell through to the provider's static `defaultContextLength` (128K for OpenRouter) while `/v1/models` simultaneously advertised the real window from the same discovery data. Measured: `openrouter/stealth/ox-alpha` advertised `context_length: 1048576` but rejected requests over 128K with `context_length_exceeded` for a full day after its sync. The reconcile now also runs opportunistically (debounced, fire-and-forget) right after a synced catalog write changes. Companion fix: discovery now captures the vendor-declared `reasoning.default_effort` (e.g. OpenRouter `stealth/ox-alpha` declares `max`, normalized to `xhigh`) as `defaultThinkingEffort`, and the OpenAI dispatch path injects it when a request carries no reasoning field of any shape — the lowest-priority default behind a `-{effort}` suffix alias and a static `ModelSpec.defaultReasoningEffort` — so a reasoning model that returns an empty response without an explicit effort gets the vendor default instead of `upstream_empty_response`.
+- **fix(providers):** Claude Code / CC-protocol-compatible clients sending `cache_control` with no `ttl` on the native Claude OAuth path (`claude`/`cc`) now default to the 1h extended cache TTL instead of silently falling back to Anthropic's 5-minute default, even though the 1h beta is always negotiated on this path — thanks @jeff-alves
+- **fix(electron):** desktop window stays hidden on Windows because the embedded Next.js server binds to the machine hostname instead of loopback ([#PENDING](https://github.com/diegosouzapw/OmniRoute/pull/PENDING))
+- **fix(executors):** OpencodeExecutor rotates (or retries once on a single-account direct path) on upstream 400 empty-body rejections — malformed completion envelopes with no error field were propagated as success and killed client sessions. Bounded +1 attempt per request; body reads are conditioned on status 400 so successful/streaming responses are never buffered. 400s carrying an error field keep propagating immediately.
+- **fix(cli):** recognize native `opencode.jsonc` files in OpenCode detection, generated-provider setup, and dashboard save/apply flows; preserve unrelated JSONC comments and provider settings, write updates back to the selected file, and refuse to overwrite invalid config ([#10227](https://github.com/diegosouzapw/OmniRoute/issues/10227)) — thanks @tito13kfm
+- fix(i18n): complete Vietnamese translations for recently added UI strings (#9985)
+- fix(api): repair broken `@/lib/db/connections` import in the usage utilization route that failed the production build (#10939 follow-up)
+- chore(docs): regenerate PROVIDER_REFERENCE and refresh README diagram SVGs to the real provider count (347)
+- chore(lint): prune ESLint suppressions orphaned on the release branch
+- **fix(build):** repair the broken Turbopack production build, the red lint gate and a runtime crash on `release/v3.8.50`. Six independent module-level defects, each from a different PR, had accumulated because the `Build` CI job is advisory rather than blocking: a lost closing brace in `modelSelectModalHelpers.ts` that swallowed `PROVIDER_TEST_CHUNK_SIZE` into a function body (#9011); `handleFalVideoGeneration` imported twice in `videoGeneration.ts` after the provider-neutral Fal module superseded the standalone handler (#9982 over #9969); `catalog.ts` still re-exporting and calling the injectable stale-while-revalidate policy that #9199 deliberately replaced with a fixed 30 s bound when it landed on top of #8728 — the consumer and the #8728 test suite were never realigned; two dangling statements left in `catalogCache.ts::scheduleBackgroundRefresh` referencing undeclared `inFlight`/`promise`, which made **every** stale-while-revalidate read throw a `ReferenceError` at runtime (a defect the build never caught, surfaced here by the realigned test); a generated wasm-bindgen sidecar URL in `tinycmsSigner.ts` that Turbopack resolves at build time even though the WASM module ships inlined as base64 (#8736/#10087); `conolDiscovery.ts` importing `getProviderOutboundGuard` from `outboundUrlGuard` instead of the sibling `outboundUrlGuardPolicy` module that actually exports it (#8974) — fixed on the consumer side, since re-exporting it would put a `@/`-aliased import into the module the packaged CLI loads without a tsconfig (#7682); and an unbalanced brace in `tests/unit/db-adapters/driverFactory.test.ts` where a new case was inserted between the preceding test's `finally` block and its `});`, so the whole file stopped parsing and the SQLite driver-cascade coverage silently stopped running since 2026-08-11 (#9173).
+- **fix(security):** harden three secret-leak paths surfaced by an audit of the error/log surface. (1) `upstreamErrorPassthrough` relays an upstream provider's 4xx body verbatim to Claude-Code-format clients (the capability-recovery contract needs the exact wording); it now refuses passthrough when the body actually carries a credential pattern (`Bearer`/`Basic` token, `sk-…`, or an `api_key`/`token`/`authorization`/`cookie`/`secret` assignment) so a provider that echoes the offending request can't relay a key to the client, falling back to the sanitized error path. The credential regex is bounded (ReDoS-safe, verified linear at 60k chars). (2) The OCR and moderations handlers no longer forward an upstream error body byte-for-byte; they run it through the (now exported) structure-preserving `redactSensitiveErrorText` first. (3) `protectPayloadForLog`'s sensitive-key set gains `cookie`/`storageState`/`runtimeKey`/`capability` so web-impersonation credentials (Meta AI `ecto_1_sess`, chatgpt-web `storageState`) that land in a request/response body field are redacted before the call-log artifact is written to disk. No behavior change for secret-free error bodies; the Claude Code verbatim-wording contract is preserved.
+- **fix(db):** the sql.js fallback now publishes the database atomically — temp file in the same directory, `fsync`, then `rename()` — instead of rewriting it in place with `writeFileSync`. sql.js has no incremental write path, so every save rewrote the whole image through an `O_TRUNC` open: for the duration of the write the on-disk database was 0 bytes and then partial, a window that scales with database size and recurs on every save. Unlike better-sqlite3 / node:sqlite, that window is not covered by SQLite's locking protocol, so it was visible to every OTHER process reading the same file (a backup job, a metrics exporter, an operator running `sqlite3`), which got `SQLITE_CORRUPT` — "database disk image is malformed" — while `PRAGMA integrity_check` passed moments later. It also closes a total-loss window: a crash mid-write used to leave the real database truncated, and now only leaves a stale temp file
+
+<!-- reconciliation pass 2 (Phase 0a.1): commits that landed in the cycle without a bullet -->
+
+- **fix(sse):** streaming-integrity cluster — a split `<think` open tag can no longer leak into content ([#10441](https://github.com/diegosouzapw/OmniRoute/issues/10441) — thanks @geek007git); a low-overlap stream-recovery continuation is rejected instead of being concatenated raw ([#11152](https://github.com/diegosouzapw/OmniRoute/issues/11152)) and recovery resumes after a clean stop that produced only reasoning ([#11151](https://github.com/diegosouzapw/OmniRoute/issues/11151)) — thanks @maxmad64bis; OpenAI streams that close with content but no terminal marker are flagged ([#10475](https://github.com/diegosouzapw/OmniRoute/issues/10475) — thanks @HouMinXi); a bare upstream close is surfaced to Responses clients as `response.failed` ([#10980](https://github.com/diegosouzapw/OmniRoute/issues/10980) — thanks @linhdmn); and a graceful silent-close no longer reads as a truncation ([#10805](https://github.com/diegosouzapw/OmniRoute/issues/10805) — thanks @minhlongs)
+- **fix(sse):** tool-call and Responses-item correctness — concatenated `tool_call` arguments are split apart when two calls collide on the same name/index ([#11043](https://github.com/diegosouzapw/OmniRoute/issues/11043)), kept Responses input items get a default summary and lose a malformed id ([#11110](https://github.com/diegosouzapw/OmniRoute/issues/11110)), freshly built Chat→Responses reasoning items get a default summary ([#11129](https://github.com/diegosouzapw/OmniRoute/issues/11129)) — thanks @maxmad64bis — and the synthetic keepalive reasoning item is closed properly with hardened `output_index` allocation ([#10330](https://github.com/diegosouzapw/OmniRoute/issues/10330) — thanks @hartmark), with the synthetic keepalive itself replaced ([#10806](https://github.com/diegosouzapw/OmniRoute/issues/10806) — thanks @xz-dev)
+- **fix(sse):** prompt-shaping fixes for strict upstreams — a synthetic user turn is appended for GLM-family upstreams that reject the shape with `400 [1214]` ([#11209](https://github.com/diegosouzapw/OmniRoute/issues/11209)), the muse-spark output budget is floored so it stops returning empty-content 502s ([#11214](https://github.com/diegosouzapw/OmniRoute/issues/11214)) — thanks @linhdmn; the strict system hoist re-runs after format translation ([#10803](https://github.com/diegosouzapw/OmniRoute/issues/10803) — thanks @Kizuno18); directive-only messages are relocated off `messages[0]` ([#10457](https://github.com/diegosouzapw/OmniRoute/issues/10457) — thanks @HouMinXi); and the `purify_history` compression notice is merged into the leading system message instead of being injected as its own turn ([#11113](https://github.com/diegosouzapw/OmniRoute/issues/11113) — thanks @ggdayup)
+- **fix(sse):** routing and credential edge cases — keyless Pollinations 401s stop poisoning the no-auth pool ([#11194](https://github.com/diegosouzapw/OmniRoute/issues/11194) — thanks @jonlwheat2-gif); `:free` OpenRouter models bypass a connection-wide `credits_exhausted` lock ([#10445](https://github.com/diegosouzapw/OmniRoute/issues/10445) — thanks @killmonger2317-coder); the `OpencodeExecutor` target format resolves through the provider alias ([#11047](https://github.com/diegosouzapw/OmniRoute/issues/11047) — thanks @maxmad64bis); search providers are excluded from the credential-health scheduler sweep ([#10435](https://github.com/diegosouzapw/OmniRoute/issues/10435)); bare `qwen3.8-max` routes to the canonical `-preview` id ([#10632](https://github.com/diegosouzapw/OmniRoute/issues/10632)); the missing `minimax-music` dispatch was added to music generation ([#10650](https://github.com/diegosouzapw/OmniRoute/issues/10650) — thanks @octo-patch); `gemini-3.5-flash` is marked thinking-capable ([#10450](https://github.com/diegosouzapw/OmniRoute/issues/10450)); a generic compatible-provider type id is bridged to the concrete node id during credential lookup ([#10434](https://github.com/diegosouzapw/OmniRoute/issues/10434)); and `localDb` is imported through its real `.ts` extension so the release build stops breaking ([#10691](https://github.com/diegosouzapw/OmniRoute/issues/10691), [#10674](https://github.com/diegosouzapw/OmniRoute/issues/10674))
+- **fix(sse):** Antigravity's static `sessionId` is no longer pinned and DNS failures are classified as retryable ([#11177](https://github.com/diegosouzapw/OmniRoute/issues/11177) — thanks @rqzbeh); prompt-cache usage fields are included on the `message_stop` fallback path ([#10545](https://github.com/diegosouzapw/OmniRoute/issues/10545) — thanks @NahuSaruf); Claude cache breakpoints advance on growing tails ([#10684](https://github.com/diegosouzapw/OmniRoute/issues/10684) — thanks @cryptiklemur); the reasoning-cache write is guarded by the same predicate its readers use ([#10978](https://github.com/diegosouzapw/OmniRoute/issues/10978) — thanks @maxmad64bis); Codex quota headers stay under the forwarding budget ([#10306](https://github.com/diegosouzapw/OmniRoute/issues/10306)) and the substring "hermes" is no longer ZWJ-obfuscated in user text ([#10488](https://github.com/diegosouzapw/OmniRoute/issues/10488)) — thanks @RaviTharuma
+- **fix(sse):** the Adobe Firefly sign-in helper kills the whole process tree on Linux so no orphan browser is left behind ([#11387](https://github.com/diegosouzapw/OmniRoute/issues/11387)), and every aggressive-compression sub-path spares the live user message ([#11386](https://github.com/diegosouzapw/OmniRoute/issues/11386)) — thanks @HouMinXi
+- **fix(providers):** catalog and lifecycle corrections — reserved provider prefixes are rejected on compatible-node create/update ([#11375](https://github.com/diegosouzapw/OmniRoute/issues/11375) — thanks @ggdayup); the **Hack Club AI** provider was removed and purged from the shared catalog ([#11123](https://github.com/diegosouzapw/OmniRoute/issues/11123) — thanks @rqzbeh, [#11262](https://github.com/diegosouzapw/OmniRoute/issues/11262)); Pollinations now requires an API key with corrected optional-key i18n labels ([#11117](https://github.com/diegosouzapw/OmniRoute/issues/11117) — thanks @rqzbeh); `hailuo-web` moved to `chat.minimax.io` ([#11055](https://github.com/diegosouzapw/OmniRoute/issues/11055) — thanks @rqzbeh); the invalid CodeBuddy CN `glm-4.7` entry was dropped and `hy3` added ([#10356](https://github.com/diegosouzapw/OmniRoute/issues/10356) — thanks @rizxfrog); the phantom Gemini 3.5 Flash entry was eliminated (thanks @backryun); OpenRouter Gemini Embedding 2 ids were catalogued ([#10566](https://github.com/diegosouzapw/OmniRoute/issues/10566) — thanks @RaviTharuma); and `bailian-coding-plan` is validated against the Token Plan host ([#10634](https://github.com/diegosouzapw/OmniRoute/issues/10634))
+- **fix(providers):** reasoning-effort handling is consistent — `reasoning_effort` is clamped to the vocabulary a model actually declares ([#11274](https://github.com/diegosouzapw/OmniRoute/issues/11274) — thanks @linhdmn) and learned and declared clamps now share nearest-tier semantics ([#11305](https://github.com/diegosouzapw/OmniRoute/issues/11305))
+- **fix(providers):** hidden models no longer leak into `GET /v1/models` ([#11309](https://github.com/diegosouzapw/OmniRoute/issues/11309)); rate-limit protection is not silently enabled by a `PATCH` unless it is actually persisted ([#11302](https://github.com/diegosouzapw/OmniRoute/issues/11302)); a degraded cached catalog counts as a failed model sync rather than a success ([#10862](https://github.com/diegosouzapw/OmniRoute/issues/10862) — thanks @ntdat812); expired terminal `grok-cli` credentials answer 401 ([#10971](https://github.com/diegosouzapw/OmniRoute/issues/10971) — thanks @RaviTharuma); model target formats are scoped to their provider ([#10072](https://github.com/diegosouzapw/OmniRoute/issues/10072) — thanks @xz-dev); combo names resolve on `/v1/audio/speech` and `/v1/videos/generations` ([#10471](https://github.com/diegosouzapw/OmniRoute/issues/10471) — thanks @sha367); Muse Spark is routed to the Responses API on `opencode-zen` too ([#11049](https://github.com/diegosouzapw/OmniRoute/issues/11049)); and two dead knobs were removed — the `existingConnections` lookups on connection creation ([#10973](https://github.com/diegosouzapw/OmniRoute/issues/10973)) and `ALLOW_MULTI_CONNECTIONS_PER_COMPAT_NODE`, a flag that governed nothing ([#10974](https://github.com/diegosouzapw/OmniRoute/issues/10974)) — thanks @maxmad64bis
+- **fix(resilience):** cooldown and quota-recovery hardening across the cycle — active cooldowns are preserved during recovery and probes ([#11355](https://github.com/diegosouzapw/OmniRoute/issues/11355) — thanks @sprintberlin); an active rate-limit cooldown is not cleared for non-`quota_exhausted` errors ([#11310](https://github.com/diegosouzapw/OmniRoute/issues/11310)); the `quota_exhausted` cooldown is cleared when the real window recovers ([#10534](https://github.com/diegosouzapw/OmniRoute/issues/10534) — thanks @SnCr90); Ollama model-not-found failures stay scoped to per-model lockout instead of disabling the connection ([#11078](https://github.com/diegosouzapw/OmniRoute/issues/11078) — thanks @rqzbeh); dashboard quota snapshots are honored in the `opencode-go` preflight ([#11267](https://github.com/diegosouzapw/OmniRoute/issues/11267)); shared passthrough providers are honored ([#11075](https://github.com/diegosouzapw/OmniRoute/issues/11075) — thanks @yourspraveen); an embed connection is marked terminal on a hard upstream failure so dead accounts stop being re-hit ([#10506](https://github.com/diegosouzapw/OmniRoute/issues/10506)); same-account transport retry is scoped out of emergency fallback and combo hops (thanks @hartmark); and heavyweight SSE is drained on `SIGTERM` ([#11020](https://github.com/diegosouzapw/OmniRoute/issues/11020) — thanks @RaviTharuma)
+- **fix(quota):** absolute ISO datetime reset timestamps are parsed in the weekly quota fallback ([#11353](https://github.com/diegosouzapw/OmniRoute/issues/11353) — thanks @sprintberlin), and `CREDIT_LIMIT` rows are parsed from the z.ai coding-plan quota API ([#11378](https://github.com/diegosouzapw/OmniRoute/issues/11378) — thanks @Neuron-Mr-White)
+- **fix(combo):** targets carrying a persisted connection cooldown are pre-skipped and re-checked on retry ([#11360](https://github.com/diegosouzapw/OmniRoute/issues/11360) — thanks @sprintberlin); combo loops always terminate with an actionable error instead of hanging silently ([#10463](https://github.com/diegosouzapw/OmniRoute/issues/10463)) and auto-combo pools are restricted to user-visible models ([#10456](https://github.com/diegosouzapw/OmniRoute/issues/10456)) — thanks @herjarsa; SSE comment lines (OpenRouter keep-alives) are accepted by response-quality validation ([#11036](https://github.com/diegosouzapw/OmniRoute/issues/11036) — thanks @asorourx); stale sticky pins are cleared when stickiness is disabled ([#10907](https://github.com/diegosouzapw/OmniRoute/issues/10907) — thanks @excessivechaos); an `unhandledRejection` from the per-model-timeout abort is prevented ([#10846](https://github.com/diegosouzapw/OmniRoute/issues/10846) — thanks @HouMinXi); a combo per-model timeout evicts the sticky session pin ([#10016](https://github.com/diegosouzapw/OmniRoute/issues/10016) — thanks @fenix007); local target timeouts are classified as gateway timeouts; and benign empty error fields no longer fail streaming quality validation
+- **fix(auto):** empty auto-family pools warn once per process instead of on every request ([#10820](https://github.com/diegosouzapw/OmniRoute/issues/10820), [#10344](https://github.com/diegosouzapw/OmniRoute/issues/10344) — thanks @RaviTharuma); auto scoring order and the auto-selected first target are preserved ([#11400](https://github.com/diegosouzapw/OmniRoute/issues/11400), [#11399](https://github.com/diegosouzapw/OmniRoute/issues/11399) — thanks @jacobsparts)
+- **fix(routing):** combo precedence is preserved and hidden models are skipped in the alias resolver ([#11107](https://github.com/diegosouzapw/OmniRoute/issues/11107) — thanks @SCys); keyless custom-compatible connections stay in the `auto/*` pool ([#11198](https://github.com/diegosouzapw/OmniRoute/issues/11198)) and `lkgpEnabled` is forwarded into `RoutingContext` so the LKGP toggle actually works ([#11193](https://github.com/diegosouzapw/OmniRoute/issues/11193)) — thanks @pacocartones; unmapped model aliases fall back to the default seeds ([#10124](https://github.com/diegosouzapw/OmniRoute/issues/10124) — thanks @benzntech)
+- **fix(models):** a synced model's real context window and default effort take effect immediately ([#10957](https://github.com/diegosouzapw/OmniRoute/issues/10957) — thanks @Neuron-Mr-White); `apiFormat`, `targetFormat` and `supportsVision` overrides persist for catalog models ([#10898](https://github.com/diegosouzapw/OmniRoute/issues/10898) — thanks @rqzbeh); media endpoint metadata is normalized ([#11397](https://github.com/diegosouzapw/OmniRoute/issues/11397) — thanks @marcelokarval); Ollama Cloud native effort tiers are exposed ([#11307](https://github.com/diegosouzapw/OmniRoute/issues/11307) — thanks @ekinnee); Codex context and combo limit resolution were corrected ([#10533](https://github.com/diegosouzapw/OmniRoute/issues/10533) — thanks @jackjinke); `MODELS_DEV_SYNC_ENABLED=0` wins over the dashboard setting ([#10299](https://github.com/diegosouzapw/OmniRoute/issues/10299)) and `getModelsDevPricing` is memoized so it stops stalling the event loop and `/healthz` ([#10055](https://github.com/diegosouzapw/OmniRoute/issues/10055)) — thanks @RaviTharuma
+- **fix(catalog):** GLM reasoning-effort tiers are declared ([#10963](https://github.com/diegosouzapw/OmniRoute/issues/10963)) and combo reasoning efforts are scoped by connection ([#10723](https://github.com/diegosouzapw/OmniRoute/issues/10723)) — thanks @xz-dev; Stealth Ox Alpha (`stealth/ox-alpha`) was added to the OpenRouter free roster ([#11337](https://github.com/diegosouzapw/OmniRoute/issues/11337) — thanks @stanleytejakusuma)
+- **fix(pricing):** DeepSeek V4 static defaults were stale by four days and off by ~1.6–2.4× ([#10635](https://github.com/diegosouzapw/OmniRoute/issues/10635)), and three dead entries in `LITELLM_PROVIDER_MAP` were silently dropping synced pricing ([#10636](https://github.com/diegosouzapw/OmniRoute/issues/10636)) — thanks @stanleytejakusuma. DeepSeek off-peak pricing is documented as weekdays-only ([#11210](https://github.com/diegosouzapw/OmniRoute/issues/11210) — thanks @xyzs996)
+- **fix(api):** proxy and probe correctness — both proxy health checks share one probe-target resolution ([#10657](https://github.com/diegosouzapw/OmniRoute/issues/10657)), a target that refuses the egress IP is no longer reported as a healthy proxy ([#10654](https://github.com/diegosouzapw/OmniRoute/issues/10654)), `/api/cache/stats` reports the cache requests actually use ([#10769](https://github.com/diegosouzapw/OmniRoute/issues/10769)) — thanks @maxmad64bis; an OAuth probe timeout is classified as `network_error` ([#10663](https://github.com/diegosouzapw/OmniRoute/issues/10663) — thanks @HouMinXi); pool usage snapshot limits scale by pool member count ([#10253](https://github.com/diegosouzapw/OmniRoute/issues/10253) — thanks @dpozimski); the MCP SSE singleton resets on a new client `initialize` ([#10772](https://github.com/diegosouzapw/OmniRoute/issues/10772) — thanks @sadSanta-07); `.opus` uploads are accepted on `/v1/audio/transcriptions` ([#10607](https://github.com/diegosouzapw/OmniRoute/issues/10607) — thanks @pucedoteth); working OpenRouter ids are named when Gemini embed credentials are missing ([#10565](https://github.com/diegosouzapw/OmniRoute/issues/10565) — thanks @RaviTharuma); a routing combo can no longer be created with no model at all ([#11162](https://github.com/diegosouzapw/OmniRoute/issues/11162) — thanks @maxmad64bis); call logs are saved and an endpoint fallback added for local rerank providers ([#11081](https://github.com/diegosouzapw/OmniRoute/issues/11081) — thanks @AndrianBalanescu); and API keys are hashed in the `/v1/models` catalog cache key
+- **fix(security):** four rounds of CodeQL and advisory remediation landed this cycle — cookie domains are matched by suffix rather than substring ([#11429](https://github.com/diegosouzapw/OmniRoute/issues/11429)); the agent-card topology is sanitized, the login rate limiter uses an anti-spoofed peer IP and 429s carry `Retry-After` ([#11418](https://github.com/diegosouzapw/OmniRoute/issues/11418) — thanks @HouMinXi); round-3 advisories were closed ([#11261](https://github.com/diegosouzapw/OmniRoute/issues/11261)) along with rounds 2 and 4 of the code-scanning alerts ([#10888](https://github.com/diegosouzapw/OmniRoute/issues/10888), [#11293](https://github.com/diegosouzapw/OmniRoute/issues/11293)); an eleven-finding advisory batch ([#11040](https://github.com/diegosouzapw/OmniRoute/issues/11040)) and four still-real findings — ACP RCE hardening, the db-backups route tier, an uppercase authz bypass and spawn-veto drift ([#11028](https://github.com/diegosouzapw/OmniRoute/issues/11028)) — were fixed; Adobe Firefly login compares a parsed hostname instead of a substring and its credential-parsing gates were hardened; an SSRF through the `/v1/search` Firecrawl `provider_options.baseUrl` was blocked ([#10738](https://github.com/diegosouzapw/OmniRoute/issues/10738)) and the open CodeQL code-scanning alerts were zeroed out ([#10739](https://github.com/diegosouzapw/OmniRoute/issues/10739)) with the test regex sanitized and the hash false-positives annotated ([#10380](https://github.com/diegosouzapw/OmniRoute/issues/10380)); and Tier 1 local-only route-guard process-spawning endpoints gained test coverage ([#11189](https://github.com/diegosouzapw/OmniRoute/issues/11189) — thanks @rqzbeh)
+- **fix(authz):** exact public routes are matched exactly instead of as prefixes, so `/api/healthz-something` no longer inherits `/api/healthz`'s public tier ([#11417](https://github.com/diegosouzapw/OmniRoute/issues/11417))
+- **fix(auth):** the real upstream reason is kept in `lastError` instead of a generic string ([#11376](https://github.com/diegosouzapw/OmniRoute/issues/11376) — thanks @ntdat812); login navigates with `window.location` instead of `router.push` so the session cookie is picked up ([#11175](https://github.com/diegosouzapw/OmniRoute/issues/11175)) and `opencode`/`opencode-zen` were added to the credential-resolution search pairs ([#10899](https://github.com/diegosouzapw/OmniRoute/issues/10899)) — thanks @rqzbeh; the OIDC authorization URL carries its missing `state` parameter ([#10614](https://github.com/diegosouzapw/OmniRoute/issues/10614) — thanks @MeRezaRezaei)
+- **fix(oauth):** connections stuck on an upstream 400 after token staleness recover ([#11141](https://github.com/diegosouzapw/OmniRoute/issues/11141) — thanks @HouMinXi); the Kiro `profileArn` survives IAM Identity Center logins ([#10725](https://github.com/diegosouzapw/OmniRoute/issues/10725) — thanks @MichaelYcJo) and a Kiro social poll status is treated as an alias of `error` for pending states ([#10620](https://github.com/diegosouzapw/OmniRoute/issues/10620) — thanks @krishna3554)
+- **fix(cli):** Windows support pass — `omniroute update` spawns npm the way Windows needs ([#11374](https://github.com/diegosouzapw/OmniRoute/issues/11374) — thanks @ntdat812); the tray runtime and the DB fallback resolve dynamic imports as `file://` URLs so `--tray` works ([#11332](https://github.com/diegosouzapw/OmniRoute/issues/11332), [#11238](https://github.com/diegosouzapw/OmniRoute/issues/11238) — thanks @pacocartones); the `DEP0190` child-process spawn deprecation is avoided ([#10835](https://github.com/diegosouzapw/OmniRoute/issues/10835) — thanks @adevwithpurpose); and cliproxy platform handling plus the pid probe were completed ([#11263](https://github.com/diegosouzapw/OmniRoute/issues/11263))
+- **fix(cli):** OAuth start no longer shows a blank device code and an undefined verification URL ([#11173](https://github.com/diegosouzapw/OmniRoute/issues/11173)); `setup-opencode` understands the OpenCode V2 config format ([#11079](https://github.com/diegosouzapw/OmniRoute/issues/11079)) and defaults `limit.context` to 128k when unknown ([#11054](https://github.com/diegosouzapw/OmniRoute/issues/11054)) — thanks @rqzbeh; provider tests route through the connection API ([#10572](https://github.com/diegosouzapw/OmniRoute/issues/10572) — thanks @hydraxman); packaged machine-token authentication was restored ([#10468](https://github.com/diegosouzapw/OmniRoute/issues/10468) — thanks @xiaoyaner0201); a non-empty `[STARTUP] Fatal` log is guaranteed when the instrumentation hook throws at boot ([#10447](https://github.com/diegosouzapw/OmniRoute/issues/10447)); real OpenRouter key validation and the auth-export argument wiring were fixed ([#11264](https://github.com/diegosouzapw/OmniRoute/issues/11264)); and a tmpfs mount is no longer taken as proof that a config path reaches the host
+- **fix(dashboard):** custom mode-pack options are exposed ([#11407](https://github.com/diegosouzapw/OmniRoute/issues/11407)) and explicit auto weights are normalized ([#11402](https://github.com/diegosouzapw/OmniRoute/issues/11402)) — thanks @jacobsparts; unique connection names are computed from the array so one no longer overwrites another ([#11067](https://github.com/diegosouzapw/OmniRoute/issues/11067)) and key validation triggers on Enter in the Add API Key modal ([#11056](https://github.com/diegosouzapw/OmniRoute/issues/11056)) — thanks @rqzbeh; a non-string `apiKey` in the CLI tool cards is guarded ([#10872](https://github.com/diegosouzapw/OmniRoute/issues/10872) — thanks @Rahulsharma0810); the live dashboard sends periodic WebSocket heartbeats to stop reconnect churn ([#10452](https://github.com/diegosouzapw/OmniRoute/issues/10452)); provider-card warning indicators actually expose the interaction they advertise ([#10448](https://github.com/diegosouzapw/OmniRoute/issues/10448)); and media-playground cards stop sending the masked API key as a Bearer token ([#10449](https://github.com/diegosouzapw/OmniRoute/issues/10449))
+- **fix(live-ws):** the public socket URL is resolved at runtime instead of baked in at build ([#11377](https://github.com/diegosouzapw/OmniRoute/issues/11377) — thanks @ntdat812), and a `0.0.0.0` dashboard origin is allowed while non-square SVG image warnings are silenced ([#11269](https://github.com/diegosouzapw/OmniRoute/issues/11269) — thanks @Minamaged18)
+- **fix(db):** call-log rotation pauses on `SQLITE_CORRUPT` instead of compounding the damage ([#10979](https://github.com/diegosouzapw/OmniRoute/issues/10979) — thanks @RaviTharuma); a Windows native-driver hang no longer stalls requests ([#10709](https://github.com/diegosouzapw/OmniRoute/issues/10709) — thanks @jonlwheat2-gif); native runtime drivers are preserved in standalone bundles ([#10552](https://github.com/diegosouzapw/OmniRoute/issues/10552) — thanks @excessivechaos); the sql.js database is published atomically instead of rewritten in place ([#10278](https://github.com/diegosouzapw/OmniRoute/issues/10278) — thanks @maxmad64bis); pre-migration backups are pruned so `db_backups` stops growing without bound ([#10423](https://github.com/diegosouzapw/OmniRoute/issues/10423)); and test runs are kept off the operator's real `DATA_DIR` ([#10432](https://github.com/diegosouzapw/OmniRoute/issues/10432))
+- **fix(build):** the postbuild hook spawns esbuild cross-platform ([#11159](https://github.com/diegosouzapw/OmniRoute/issues/11159) — thanks @aliyosufi); the standalone `package.json` declares its module type for Node 24 worker compatibility ([#10836](https://github.com/diegosouzapw/OmniRoute/issues/10836) — thanks @adevwithpurpose); `assembleStandalone` tolerates a same-realpath symlink and a stale-typed destination ([#10776](https://github.com/diegosouzapw/OmniRoute/issues/10776)); pack-boot sql.js expectations align with dependency-based packaging ([#11266](https://github.com/diegosouzapw/OmniRoute/issues/11266)); and the SQLite driver is kept out of the client bundle ([#10695](https://github.com/diegosouzapw/OmniRoute/issues/10695))
+- **fix(docker):** the Next build worker pool is sized for a 16 GB runner ([#11419](https://github.com/diegosouzapw/OmniRoute/issues/11419)); a warning fires when `OMNIROUTE_MEMORY_MB` disagrees with the `NODE_OPTIONS` heap ([#10818](https://github.com/diegosouzapw/OmniRoute/issues/10818) — thanks @RaviTharuma); and cache mount ids are prefixed with the Railway service scope ([#10288](https://github.com/diegosouzapw/OmniRoute/issues/10288) — thanks @anudeepadi)
+- **fix(electron):** the embedded server is pinned to loopback so the window shows on Windows ([#10717](https://github.com/diegosouzapw/OmniRoute/issues/10717) — thanks @echoriver89)
+- **fix(compression):** `pathToFileURL` is used for the worker URL so bundler resolution stops failing ([#11364](https://github.com/diegosouzapw/OmniRoute/issues/11364) — thanks @TheDemonTuan); CCR no longer strands prompts for callers without the retrieve tool ([#11084](https://github.com/diegosouzapw/OmniRoute/issues/11084) — thanks @HouMinXi); the vendored GCF was bumped with numeric-domain and surplus fixes ([#10807](https://github.com/diegosouzapw/OmniRoute/issues/10807) — thanks @blackwell-systems); the RTK raw-output store is bounded and pointer reads are O(bucket) ([#10660](https://github.com/diegosouzapw/OmniRoute/issues/10660) — thanks @stanleytejakusuma); the Lite and Caveman whitespace/artifact cleaners were accelerated with native V8 RegExp ([#10834](https://github.com/diegosouzapw/OmniRoute/issues/10834) — thanks @adevwithpurpose); i18n was added for `less-code` and `terse-prose` ([#10498](https://github.com/diegosouzapw/OmniRoute/issues/10498) — thanks @abhijeetnardele24-hash); and a stage gate with a metadata-less engine no longer brings the pipeline down ([#10655](https://github.com/diegosouzapw/OmniRoute/issues/10655))
+- **fix(translator):** the `functionCall` id survives Gemini→OpenAI request translation ([#11365](https://github.com/diegosouzapw/OmniRoute/issues/11365)) and consecutive same-role contents are merged in the direct `claudeToGeminiRequest` path ([#10658](https://github.com/diegosouzapw/OmniRoute/issues/10658)) — thanks @Siva010; tool-call names are normalized from lowercase to PascalCase when translating upstream responses into the Claude Messages format ([#10392](https://github.com/diegosouzapw/OmniRoute/issues/10392) — thanks @giauphan); and Claude tool-call state is preserved across a translation round-trip
+- **fix(gemini):** a missing `items` schema is injected for array-typed MCP tools ([#10605](https://github.com/diegosouzapw/OmniRoute/issues/10605) — thanks @sadSanta-07)
+- **fix(codex):** `max_context_window` is preferred over `context_window` as the usable input limit ([#11179](https://github.com/diegosouzapw/OmniRoute/issues/11179) — thanks @excessivechaos); remote compaction V2 completes reliably ([#11041](https://github.com/diegosouzapw/OmniRoute/issues/11041) — thanks @jackjinke); completed Codex tool handoffs survive streaming ([#10608](https://github.com/diegosouzapw/OmniRoute/issues/10608) — thanks @JxnLexn); the header budget, Codex failover and `kv_after_text` handling were corrected together ([#10573](https://github.com/diegosouzapw/OmniRoute/issues/10573) — thanks @HouMinXi); Codex image generation retries on a sibling ChatGPT account ([#10838](https://github.com/diegosouzapw/OmniRoute/issues/10838)); and `apiType="chat"` is respected in `forceResponsesUpstream` ([#10946](https://github.com/diegosouzapw/OmniRoute/issues/10946) — thanks @YunyunZhai)
+- **fix(opencode):** Muse Spark 1.2 models route to the OpenAI Responses API ([#10874](https://github.com/diegosouzapw/OmniRoute/issues/10874) — thanks @zoser69); the provider block is guarded when merging an existing config ([#11004](https://github.com/diegosouzapw/OmniRoute/issues/11004) — thanks @ntdat812); Muse Responses streams are closed at completion ([#11385](https://github.com/diegosouzapw/OmniRoute/issues/11385) — thanks @AStupidBear); the `models[0]` default and its guards were restored ([#11133](https://github.com/diegosouzapw/OmniRoute/issues/11133) — thanks @maxmad64bis); bare combo ids stay unprefixed in the OpenCode plugin ([#10821](https://github.com/diegosouzapw/OmniRoute/issues/10821) — thanks @RaviTharuma); and `opencode-go` is classified as a flat-rate subscription in analytics ([#11199](https://github.com/diegosouzapw/OmniRoute/issues/11199) — thanks @pacocartones)
+- **fix(executors):** an account rotates on an upstream 400 with an empty body (opencode) ([#11158](https://github.com/diegosouzapw/OmniRoute/issues/11158)) and on a network throw when the account has a dedicated proxy ([#10402](https://github.com/diegosouzapw/OmniRoute/issues/10402)) — thanks @maxmad64bis; probe-origin failures are isolated from every deactivation site ([#10694](https://github.com/diegosouzapw/OmniRoute/issues/10694) — thanks @maxmad64bis); and the direct-path response-start timeout is bounded (thanks @excessivechaos)
+- **fix(search):** the `blockedProviders` setting is enforced on the search endpoint ([#10901](https://github.com/diegosouzapw/OmniRoute/issues/10901), [#11125](https://github.com/diegosouzapw/OmniRoute/issues/11125) — thanks @rqzbeh); a `/v1/search` 502 names its provider and cause ([#10756](https://github.com/diegosouzapw/OmniRoute/issues/10756)) and the catalog-default SearXNG `localhost:8888` target is skipped ([#10981](https://github.com/diegosouzapw/OmniRoute/issues/10981)) — thanks @RaviTharuma; with no search provider configured the request falls back to `duckduckgo-free` ([#11097](https://github.com/diegosouzapw/OmniRoute/issues/11097) — thanks @Egorich-print)
+- **fix(mcp):** the `mcp:connect` carve-out is honored in the transport route guards ([#11139](https://github.com/diegosouzapw/OmniRoute/issues/11139) — thanks @HouMinXi); provider-bound tool calls get their own fetch budget ([#10860](https://github.com/diegosouzapw/OmniRoute/issues/10860) — thanks @ntdat812); GitHub skill tools are discoverable through `omniroute_tool_search` ([#10575](https://github.com/diegosouzapw/OmniRoute/issues/10575) — thanks @branben); and the web-search provider enum is generated from the registry ([#10209](https://github.com/diegosouzapw/OmniRoute/issues/10209) — thanks @sadSanta-07)
+- **fix(memory):** a mid-conversation system injection is no longer sent to Claude when the preceding turn is not a tool result ([#11303](https://github.com/diegosouzapw/OmniRoute/issues/11303)), and TokenRouter is treated as system-must-be-first — confirmed against a live HTTP 400 ([#11114](https://github.com/diegosouzapw/OmniRoute/issues/11114) — thanks @ggdayup)
+- **fix(embeddings):** an account is cooled down on hard errors (402/401/5xx) ([#10529](https://github.com/diegosouzapw/OmniRoute/issues/10529) — thanks @HouMinXi), and the configured LM Studio connection URL is honored via the `lm-studio` alias ([#11260](https://github.com/diegosouzapw/OmniRoute/issues/11260))
+- **fix(video-bridge):** structural segment sampling is validated, contact sheets render their timestamps, captions route through provider connections, the fetch size broker sizes bodies, and the remote runtime status is clarified; the result-cache identity and bounds were hardened, download flights are keyed with a process HMAC and tenant scope is separated from the download hash
+- **fix(images):** bare `dall-e-3` routes to OpenAI ([#10847](https://github.com/diegosouzapw/OmniRoute/issues/10847) — thanks @RaviTharuma); OpenRouter reference-image edits are supported ([#10363](https://github.com/diegosouzapw/OmniRoute/issues/10363) — thanks @tiangao88); and inline images keep high detail ([#10554](https://github.com/diegosouzapw/OmniRoute/issues/10554) — thanks @rinseaid)
+- **fix(fusion):** the vision-compatibility filter is applied to both the fusion panel and the judge, so a fan-out with images cannot land on a text-only model ([#10737](https://github.com/diegosouzapw/OmniRoute/issues/10737))
+- **fix(proxy):** proxy log batching is non-blocking and asynchronous ([#11182](https://github.com/diegosouzapw/OmniRoute/issues/11182) — thanks @rqzbeh); IPv4-only proxies stop being reported as dead ([#10868](https://github.com/diegosouzapw/OmniRoute/issues/10868) — thanks @ntdat812); a proxy is probed against its assigned provider host instead of a generic target ([#10664](https://github.com/diegosouzapw/OmniRoute/issues/10664) — thanks @maxmad64bis); and local/loopback proxy-subscription fetch URLs are allowed ([#10416](https://github.com/diegosouzapw/OmniRoute/issues/10416))
+- **fix(relay):** one private-host guard is shared across the three relay workers ([#10941](https://github.com/diegosouzapw/OmniRoute/issues/10941)) and `x-relay-path` resolves through that same guard in the Cloudflare worker ([#10935](https://github.com/diegosouzapw/OmniRoute/issues/10935)) — thanks @ntdat812; Bifrost errors are normalized, a credential 404 is remapped and analytics were corrected ([#10797](https://github.com/diegosouzapw/OmniRoute/issues/10797))
+- **fix(logging):** the component field and printf formats are preserved in the app log ([#10770](https://github.com/diegosouzapw/OmniRoute/issues/10770) — thanks @maxmad64bis); early-keepalive bytes are captured in the call-log artifact ([#10331](https://github.com/diegosouzapw/OmniRoute/issues/10331) — thanks @hartmark); and stream-chunk capture, request-shape logging and other diagnostics are opt-in (thanks @benzntech)
+- **fix(logs):** filter predicates are applied to merged in-memory call-log rows ([#11082](https://github.com/diegosouzapw/OmniRoute/issues/11082) — thanks @AndrianBalanescu); auto-routing is queried from the call logs in analytics ([#10685](https://github.com/diegosouzapw/OmniRoute/issues/10685) — thanks @cryptiklemur)
+- **fix(webhooks):** three declared-but-never-emitted ghost events were removed ([#11050](https://github.com/diegosouzapw/OmniRoute/issues/11050)) with follow-up dispatcher tests and vi i18n ([#11130](https://github.com/diegosouzapw/OmniRoute/issues/11130)) — thanks @maxmad64bis
+- **fix(antigravity):** live chat models are discovered dynamically ([#10422](https://github.com/diegosouzapw/OmniRoute/issues/10422) — thanks @JxnLexn); Gemini and Claude reasoning capabilities are unblocked ([#10376](https://github.com/diegosouzapw/OmniRoute/issues/10376) — thanks @Chewji9875); and a trailing model turn is stripped for native Gemini requests too ([#10436](https://github.com/diegosouzapw/OmniRoute/issues/10436))
+- **fix(adobe-firefly):** sessions renew through a durable CDP connection ([#9255](https://github.com/diegosouzapw/OmniRoute/issues/9255) — thanks @artickc), models and media capabilities were synced, and the Topaz catalog models are retained
+- **fix(cline):** proxy task ids are no longer generated ([#10279](https://github.com/diegosouzapw/OmniRoute/issues/10279)) and internal health checks are labelled as such ([#10706](https://github.com/diegosouzapw/OmniRoute/issues/10706)) — thanks @arafatkatze; Cline provider models use a valid `modelType`/`model` format ([#11132](https://github.com/diegosouzapw/OmniRoute/issues/11132) — thanks @rqzbeh)
+- **fix(agentrouter):** the protocol is inferred from the client endpoint, an alternate protocol is honored through the chat pipeline, and both the Claude and Codex protocols are supported
+- **fix(services):** the CLIProxy executable is used on Windows ([#10371](https://github.com/diegosouzapw/OmniRoute/issues/10371) — thanks @tkgo11), and port discovery falls back to `ss` and `netstat` when `lsof` is absent ([#10459](https://github.com/diegosouzapw/OmniRoute/issues/10459) — thanks @aron-intframe)
+- **fix(monitoring):** provider aliases are canonicalized in the health matrix ([#10370](https://github.com/diegosouzapw/OmniRoute/issues/10370) — thanks @tkgo11); the Docker `HEALTHCHECK` probes `/healthz` rather than deep monitoring ([#10307](https://github.com/diegosouzapw/OmniRoute/issues/10307) — thanks @RaviTharuma); a slow `/healthz` event-loop lag warns ([#10827](https://github.com/diegosouzapw/OmniRoute/issues/10827) — thanks @RaviTharuma); and the canary install is judged by the SHA on disk instead of npm's exit code ([#10699](https://github.com/diegosouzapw/OmniRoute/issues/10699))
+- **fix(github):** GitHub access tokens are verified during health checks instead of being assumed valid ([#11320](https://github.com/diegosouzapw/OmniRoute/issues/11320) — thanks @RaviTharuma)
+- **fix(i18n):** locale parity work — the zh-CN/zh-TW CLI locales were completed with a parity guard ([#11339](https://github.com/diegosouzapw/OmniRoute/issues/11339)) and the three missing pt-BR CLI keys added ([#11322](https://github.com/diegosouzapw/OmniRoute/issues/11322)) — thanks @pacocartones; missing routing and compression messages were added ([#10546](https://github.com/diegosouzapw/OmniRoute/issues/10546) — thanks @rizxfrog); HTML entities in UI strings were unescaped and `gatesDescription` restored ([#9721](https://github.com/diegosouzapw/OmniRoute/issues/9721) — thanks @dionjoshualobo); vi parity was completed for the sponsor banner ([#11208](https://github.com/diegosouzapw/OmniRoute/issues/11208)); and the capability-filter messages and web-session guide were translated
+- **fix(chat):** the severity-classifier format is detected in the `claudeClassifierCompat` short-circuit ([#11304](https://github.com/diegosouzapw/OmniRoute/issues/11304)); search providers are guarded from the OpenAI fallback ([#10394](https://github.com/diegosouzapw/OmniRoute/issues/10394) — thanks @azzaouiomar19-sketch); and concurrent requests stop colliding on the dedup hash for non-OpenAI formats ([#10438](https://github.com/diegosouzapw/OmniRoute/issues/10438))
+- **fix(providers):** small per-provider corrections — Groq strips unsupported message metadata ([#11026](https://github.com/diegosouzapw/OmniRoute/issues/11026) — thanks @sanforex24h); `sensenova` clamps max reasoning effort to `xhigh` ([#10733](https://github.com/diegosouzapw/OmniRoute/issues/10733) — thanks @InkshadeWoods); Zed Hosted Models gained connection-test support ([#10810](https://github.com/diegosouzapw/OmniRoute/issues/10810) — thanks @Hsia97); `kilocode` strips an unsupported `response_format` for DeepSeek V4 Flash ([#10458](https://github.com/diegosouzapw/OmniRoute/issues/10458) — thanks @benzntech); `kimi-web` points at the international `www.kimi.ai` ([#11045](https://github.com/diegosouzapw/OmniRoute/issues/11045) — thanks @MeRezaRezaei); "insufficient credits" is classified as credits-exhausted ([#10116](https://github.com/diegosouzapw/OmniRoute/issues/10116) — thanks @Chewji9875); the ChatGPT Web catalog was refreshed ([#10637](https://github.com/diegosouzapw/OmniRoute/issues/10637) — thanks @backryun); Ollama routes models by advertised capability ([#11088](https://github.com/diegosouzapw/OmniRoute/issues/11088) — thanks @yourspraveen); the Perplexity Web built-in-search hint became opt-in ([#10904](https://github.com/diegosouzapw/OmniRoute/issues/10904)); nested STT models fall back when the prefix provider has no credentials ([#10584](https://github.com/diegosouzapw/OmniRoute/issues/10584) — thanks @RaviTharuma); the mimocode provider was retired ([#10186](https://github.com/diegosouzapw/OmniRoute/issues/10186) — thanks @Tushar49); AWS Polly signing credentials were added ([#11207](https://github.com/diegosouzapw/OmniRoute/issues/11207) — thanks @rafacpti23); and `model_not_found` is returned for an unrecognized prefix model when the provider is inactive ([#10894](https://github.com/diegosouzapw/OmniRoute/issues/10894) — thanks @rqzbeh)
+- **fix(radar):** feature availability is separated from opt-in ([#10487](https://github.com/diegosouzapw/OmniRoute/issues/10487)) and stale flag-off responses are bypassed ([#10464](https://github.com/diegosouzapw/OmniRoute/issues/10464)); the aggregate sync body is validated and the remaining client trust boundaries closed — thanks @backryun
+- **fix(usage):** quota windows are ordered chronologically on every provider card ([#11241](https://github.com/diegosouzapw/OmniRoute/issues/11241) — thanks @pacocartones)
+- **fix(files):** the list `limit` query parameter is validated ([#10673](https://github.com/diegosouzapw/OmniRoute/issues/10673) — thanks @pacocartones), and the gamification leaderboard validates `limit`/`offset` before the SQLite bind ([#11059](https://github.com/diegosouzapw/OmniRoute/issues/11059) — thanks @pacocartones)
+- **fix(onboarding):** the setup wizard warns when the password step is skipped ([#10855](https://github.com/diegosouzapw/OmniRoute/issues/10855) — thanks @krishna3554)
+- **fix(settings):** `customSystemPrompt` fields were missing from `updateSettingsSchema` and were silently dropped ([#10890](https://github.com/diegosouzapw/OmniRoute/issues/10890) — thanks @rqzbeh); `debugMode` defaults to false and account rotation is skipped on a model-unsupported 400 ([#10525](https://github.com/diegosouzapw/OmniRoute/issues/10525) — thanks @HouMinXi)
+- **fix(conversations):** the reconnect walk is bounded and turn hashes are memoized ([#10800](https://github.com/diegosouzapw/OmniRoute/issues/10800) — thanks @adevwithpurpose)
+- **fix(reasoning):** compatible response state is preserved across a provider hop ([#10574](https://github.com/diegosouzapw/OmniRoute/issues/10574) — thanks @jackjinke)
+- **fix(agent-bridge):** the regenerate-cert endpoint actually mints a new certificate ([#10715](https://github.com/diegosouzapw/OmniRoute/issues/10715) — thanks @ntdatt812)
+- **fix(api-manager):** empty combo restrictions are allowed instead of rejected ([#10066](https://github.com/diegosouzapw/OmniRoute/issues/10066) — thanks @xz-dev)
+- **fix(db):** the Database settings page no longer answers HTTP 500 when SQLite lacks the optional `dbstat` table ([#10558](https://github.com/diegosouzapw/OmniRoute/issues/10558) — thanks @TechNickAI)
+- **fix(models):** health-check-excluded models are hidden from the `/v1/models` catalog ([#10026](https://github.com/diegosouzapw/OmniRoute/issues/10026) — thanks @ritheshcn25)
+- **fix(skills):** the CLI skills left stale by the quota subcommands are regenerated ([#10698](https://github.com/diegosouzapw/OmniRoute/issues/10698))
+- **fix(mcp):** CLI MCP call protocol issues were resolved ([#10960](https://github.com/diegosouzapw/OmniRoute/issues/10960) — thanks @YunyunZhai)
 
 ### 📝 Maintenance
 
@@ -777,6 +1260,102 @@ _Living section — regenerated 2026-08-12 from all cycle commits (cycle open `e
 - **deps:** bump electron from 43.2.0 to 43.3.0 in /electron ([#10042](https://github.com/diegosouzapw/OmniRoute/pull/10042)) — thanks @app/dependabot
 - **maint(release):** 45 direct pushes to the release branch with no PR ref — base-red and quality-gate repairs, i18n string completion and stream/type fixes (quality ×6, i18n ×5, deps ×3, agentrouter ×3, providers ×2, release ×2, security ×2, logging ×2)
 - **maint(repo):** 29 chore/ci/test/docs commits rolled up — quality baselines, mutation registration, CI re-triggers, doc restructure and repo hygiene (#10187, #10189, #10190, #10193, #10196, #10203, #10204, #10205, #10207, #10210, #10236, #10318)
+- **docs(auth):** distinguish dashboard sessions, `oma_live_…` Access Tokens, manage-scoped API keys, and inference keys ([#7786](https://github.com/diegosouzapw/OmniRoute/issues/7786))
+- **docs(ops):** document Kubernetes probe recommendations — TCP (or soft HTTP) liveness, HTTP `/healthz` readiness, avoid `/api/monitoring/health` as kubelet liveness ([#10297](https://github.com/diegosouzapw/OmniRoute/pull/10297)) — thanks @RaviTharuma
+- **docs(docker):** spell out that `:latest` tracks the highest **published** stable SemVer (not git `main`), and that GitOps should pin `X.Y.Z` ([#10317](https://github.com/diegosouzapw/OmniRoute/issues/10317))
+- **docs(backend):** document that memory extraction, skills injection, and token refresh share the request event loop, plus dashboard kill switches ([#10349](https://github.com/diegosouzapw/OmniRoute/issues/10349))
+- **docs(docker):** document default SQLite as single-replica / HA-unsupported, including Recreate and HEALTHCHECK session blast radius ([#10350](https://github.com/diegosouzapw/OmniRoute/issues/10350))
+- **docs(backend):** document that pre-write SQLite backups (including models.dev pricing) are throttled to once per 60 minutes and can be disabled with `DISABLE_SQLITE_AUTO_BACKUP` ([#10351](https://github.com/diegosouzapw/OmniRoute/issues/10351))
+- **fix(tests):** drain three base-reds on the release branch — the Vietnamese locale regained parity with English (6 keys added), the chatCore SSE test now asserts the comment-free default that #10539 introduced instead of the trailer it replaced, and the Antigravity cloudcode test asserts the missing-messages guard it is named for instead of a `/ok/` regex that only ever matched the "ok" inside `: x-omniroute-tokens-in` ([#10704](https://github.com/diegosouzapw/OmniRoute/pull/10704))
+- chore(security): remove the unused `enforceSecrets()` duplicate of the boot secret check and pin the live `enforceWebRuntimeEnv()` wiring with a regression test (#10775)
+- fix(quality): register GrokBuildToolCard.tsx react-hooks/set-state-in-effect suppression (dropped in #10778's uncommitted fix)
+- **docs:** Custom combos are only invoked by their exact name in the `model` field — `auto` remains a separate zero-config router, and `openrouter/auto` is a paid OpenRouter product, not an alias ([#10779](https://github.com/diegosouzapw/OmniRoute/pull/10779)) — thanks @maxmad64bis
+- chore(startup): remove `src/server-init.ts` (183 lines, never imported — the boot path is `src/instrumentation-node.ts`) and correct four `"called from server-init.ts"` comments left pointing at the dead entry point (#10780)
+- fix(quality): rebaseline file-size for #10859's own modelCapabilities.ts/commandCode.ts growth (missed at merge time)
+- **docs(openapi):** document the `GET` and `PUT` operations on `/api/combos/{id}`, and add an operation-level coverage floor so a missing verb can no longer hide behind a path that already counts as covered ([#10875](https://github.com/diegosouzapw/OmniRoute/pull/10875))
+- fix(quality): bump EXPECTED_FEATURE_FLAG_COUNT to 52 for #10889's own new flag (missed at merge time)
+- **test(db):** replace three empty `test.skip` placeholders in the critical DB-state suite with real assertions — `resetDbInstance` must swap the singleton while the on-disk row survives, the on-disk DB must open in WAL journal mode, and `db_meta` must hold the seeded `schema_version` — so a regression in any of those invariants can no longer pass as silently green ([#10906](https://github.com/diegosouzapw/OmniRoute/pull/10906))
+- **docs(docker):** document runtime RAM for coding-agent `/v1/responses` (image default 1 GiB heap is dashboard-only; 8–12 GiB heap for agents) ([#10982](https://github.com/diegosouzapw/OmniRoute/issues/10982))
+- **docs(database):** align the SQLite cache guide with the 65,536 KiB runtime default, supported 1–1,000,000 KiB range, and live Settings application behavior ([#11018](https://github.com/diegosouzapw/OmniRoute/issues/11018))
+- **docs(docker):** document N independent `DATA_DIR`s as the supported large `/v1/responses` scale-out (one V8 heap ≠ host RAM; do not `replicas>1` on one SQLite file) ([#11024](https://github.com/diegosouzapw/OmniRoute/issues/11024)) — thanks @RaviTharuma
+- fix(quality): rebaseline file-size for modelCapabilities.ts (1016->1072) drift from merged tip fixes (#11034 et al)
+- fix(quality): register `tests/unit/authz/oauth-autoimport-local-only.test.ts` in stryker `tap.testFiles` (residual of #11053)
+- chore(quality): drain two `release/v3.8.50` base-reds — refresh the drifted doc counts (159 migrations, 56 free-forever providers, 40 free-tier pools, incl. the 42 `llm.txt` locale mirrors) and move `uncloseai-noauth.test.ts` to a collected path so the UncloseAI no-auth regression guard actually runs (#11160)
+- **chore(lint):** ratchet `@typescript-eslint/no-unused-vars` scoped to `src/` + `open-sse/` + `tests/` (`args: "all"`, `_`-prefix escape hatch) and freeze the 1393 pre-existing violations via bulk suppressions — same pattern as the #7879 `toNumber` ratchet. New unused bindings now fail lint. ([#11247](https://github.com/diegosouzapw/OmniRoute/pull/11247))
+- **fix(deps):** prevent pnpm from auto-installing the unused `@lobehub/ui` peer subtree of
+  `@lobehub/icons`, keeping six unneeded packages with incompatible or unverifiable license
+  metadata out of production installs ([#11342](https://github.com/diegosouzapw/OmniRoute/pull/11342)).
+- **ci(changelog):** replace the broad removal bypass with an exact, hash-bound reconciliation ledger and bind merge-train checks to their requested release base ([#11345](https://github.com/diegosouzapw/OmniRoute/pull/11345)).
+- **docs(readme):** reconcile live v3.8.50 provider, free-tier, CLI, routing, test,
+  community, sponsor, acknowledgment, and SVG metrics with their audited source
+  denominators, including a deduplicated OmniRoute-in-Action snapshot and distinct
+  contributor rankings for merged pull requests, GitHub-attributed commits, and Git history
+  ([#11356](https://github.com/diegosouzapw/OmniRoute/pull/11356)).
+- **docs(openapi):** document the conditionally management-authenticated, same-origin `POST /api/openapi/try` proxy contract and restore the release branch's operation-coverage ratchet ([#11363](https://github.com/diegosouzapw/OmniRoute/pull/11363))
+- **fix(video-bridge):** make opt-in segment-aware sampling use one bounded structural FFmpeg pass (scene, freeze, blur, exposure, and SI/TI), preserve long trailing segments, fail open to uniform sampling, and add real-media structural-oracle, overhead, post-dedup caption-call, and false-positive evidence while holding unconfigured model quality and gain-versus-cost claims ([#11381](https://github.com/diegosouzapw/OmniRoute/pull/11381)).
+- **docs:** add an embeddings client runbook with live-verified working/broken model ids and Hindsight 0.9.1 / Memorix 1.6.0 notes — thanks @RaviTharuma
+- **chore(ci):** ignore ad-hoc `BOT_TOKEN`/`BOT_URL` in env-doc-sync (scripts/ad-hoc mesh helpers, not runtime config)
+- **test(kimi):** the Kimi background health sweep no longer draws its refresh window inside the assertion. `checkKimiWebConnectionIfNeeded` spreads the refresh over `[60, 240)` seconds before expiry so a fleet of connections does not stampede the token endpoint, and the test used a token expiring in 90 seconds and asserted that a refresh happened — which is true only when the draw lands at 90 or above, i.e. 150 of the 180 possible values. Measured: the test fails 1 run in 6 (16.7% by construction; 4 of 20 local runs), and it is what the Node 26 nightly hit and reported as a Node-compat break (#11361). The spread is now `defaultKimiRefreshJitterSec()` and the window is injectable as `jitterSecFn`, so the test decides it instead of rolling for it; production behaviour is unchanged. Cases were added for a token outside the window and for the default spread's range.
+- chore(test): regenerate the provider/translate-path golden snapshot to reflect freebuff (#10531), fixing a base-red left by that merge (freebuff/freeinference key ordering only, no value changes).
+- **chore(release):** resync the v3.8.50 provider and CLI catalogs, register the existing ChatCore mutation-coverage test, and document the local ZCode handshake identifier so the release quality gates reflect the current tree without changing ratchet baselines.
+- **fix(ci):** route `open-sse/handlers/imageGeneration/providers/geminiWeb.ts`'s b64_json
+  download-failure message through `sanitizeErrorMessage()` instead of embedding a raw
+  `err.message`, clearing the `check:error-helper` base-red on `release/v3.8.50` (#9985).
+- **fix(ci):** drain three more base-reds on `release/v3.8.50` (#9985). ESLint was reporting
+  219 errors locally (vs. 25 in the last CI run) — all from `react-hooks/set-state-in-effect`,
+  `react-hooks/preserve-manual-memoization`, `react-hooks/immutability`,
+  `react-hooks/static-components`, `react-hooks/refs` and `react-hooks/purity`, six React
+  Compiler lint rules that `eslint-plugin-react-hooks` v7 turns on by default and that were
+  never frozen in `config/quality/eslint-suppressions.json` after the dependency bump. Froze
+  the pre-existing violations for those six rules via ESLint's native
+  `--suppress-rule`/`--suppressions-location` mechanism (the same pattern already used for
+  `@next/next/no-location-assign-relative-destination`) — no application code changed, no rule
+  disabled, only genuinely-new violations stay blocking. `check:dead-code` was at 418 against a
+  415 baseline: removed the unused `src/lib/quota/providerCapabilities.ts` file and the unused
+  `ProviderQuotaMonitor` interface in `providerQuotaTelemetry.ts` (both dead since PR #10148,
+  2026-08-18, confirmed via `grep`/knip cross-reference), landing at 416; the residual +1 could
+  not be attributed to a single recent commit after checking every dead-list entry touched
+  since the 2026-08-14 baseline measurement, so it is rebaselined with the investigation
+  recorded in `quality-baseline.json`. `tests/unit/autoCombo/tieredRotation.test.ts`'s
+  "rotates across all 43 Cerebras connection IDs" case was hitting vitest's 5000ms default
+  timeout on a 200-iteration synchronous `selectProvider()` loop under shared-devbox
+  contention (load average 40-60+ observed) — widened its explicit timeout to 20000ms; the
+  assertion itself is unchanged.
+- **fix(tests):** drain two base-reds on the release branch — `auto/glm` now expects the Cloudflare AI Playground backend (its registry advertises `zai-org/glm-5.2` and `zai-org/glm-4.7-flash`, so it belongs in the family pool by the same rule already documented for `auggie`, `devin-cli-agentic` and `zcode`), and the ESLint gate is green again after the GitLab executor test dropped its five `as any` casts for a declared response shape and the CLI OAuth suppression count caught up with the two casts #10491 added.
+- **fix(tests):** realign the two `stream-utils` passthrough cases that still asserted the pre-#10017 SSE framing — the event-boundary case declares the OpenAI Responses client format it actually exercises, and the metadata case now pins that surviving lines stay inside one event instead of expecting the `:`/`id:` control lines that #10473 stopped forwarding to every client format.
+- **fix(tests):** drain several base-reds on `release/v3.8.50` (#9985) that were all instances
+  of the same pattern — a legitimate product change landed without updating the test that
+  asserted the old behavior: `tests/unit/glm-provider-model-import-route.test.ts` (12 tests)
+  and `tests/unit/model-sync-route.test.ts` (2 tests) predate #10603's "upstream model sync is
+  opt-in and manual overrides are preserved" change; `tests/unit/antigravity-model-aliases.test.ts`
+  predated #10537 retiring the collapsed `gemini-3.7-flash` alias in favor of its three tiered
+  ids. Also fixes a real data drift in `open-sse/config/freeModelCatalog.data.ts` (the `qwen-web`
+  free-catalog entry still pointed at the retired `qwen3.8-max-preview` id instead of the
+  current `qwen3.8-max`), corrects the zh-TW `providers.autoFetchModelsTooltip` string to the
+  glossary-canonical 快取 instead of 緩存, and removes an unused default export from
+  `src/lib/oauth/providers/zed-hosted.ts` (the named export already covers every consumer) to
+  shave one symbol off the `check:dead-code` ratchet regression.
+- **chore(release):** synchronize migration-count documentation and document the opt-in `PROXY_LOG_INCLUDE_IPS` logging flag so the v3.8.50 quality gates match the release tree.
+- fix(i18n): translate the 14 `providers.harImport*` keys into Vietnamese (parity gap left by #11069)
+
+<!-- reconciliation pass 2 (Phase 0a.1): commits that landed in the cycle without a bullet -->
+
+- **fix(release):** release pre-flight and base-red drains for v3.8.50 — the build-breaking `localDb` import, stale provider docs and orphaned suppressions ([#11038](https://github.com/diegosouzapw/OmniRoute/issues/11038)); the docs/golden/GLM cluster with a masked assert restored; the volcengine vision metadata and antigravity BYOP contract pair; the #10534 quota-recovery restoration plus volcengine connect-body validation; the onnxruntime dependency contract test; the post-sweep base regressions; the remaining Adobe and typecheck gates; the base-red tail after the latest root lift ([#10964](https://github.com/diegosouzapw/OmniRoute/issues/10964) — thanks @backryun); the agent-skills catalog tests and base quality reds (thanks @adevwithpurpose); a stray conflict leftover in `managedModelImport` was dropped ([#11259](https://github.com/diegosouzapw/OmniRoute/issues/11259) — thanks @hartmark); and the sweep-stale summary counting matches by their real category ([#11338](https://github.com/diegosouzapw/OmniRoute/issues/11338) — thanks @pacocartones)
+- **fix(quality):** quality-gate maintenance — the two Fast Quality Gates base-reds ([#11438](https://github.com/diegosouzapw/OmniRoute/issues/11438)) and the three inventory/coverage base-reds were drained; the gate reports the real failure line and stops double-counting `ci.yml` gates ([#11321](https://github.com/diegosouzapw/OmniRoute/issues/11321) — thanks @pacocartones); file-size baselines were rebaselined for `modelCapabilities.ts`, `imageRegistry.ts`, `AddApiKeyModal` and `combo-routing-engine.test.ts` drift (thanks @hartmark, @adevwithpurpose, @wgordon17); a stale ESLint suppression for `search.ts` was pruned and the `eslintWarnings` baseline tightened to the gate's real measurement (0); the capability gate frozen cap was updated; and the gateway duplication between `chatanywhere` and `regolo` was resolved to unblock typecheck (thanks @backryun)
+- **fix(tests):** stale-assertion and isolation repairs — the compression/kiro/memory/i18n base-red mini-cluster ([#11306](https://github.com/diegosouzapw/OmniRoute/issues/11306)); the auto/GLM family pool and ESLint gate pair ([#10726](https://github.com/diegosouzapw/OmniRoute/issues/10726) — thanks @MichaelYcJo); the `translate-path` golden snapshot for `hailuo-web` ([#11161](https://github.com/diegosouzapw/OmniRoute/issues/11161) — thanks @rqzbeh); the provider count realigned to 230 after a merge-train collision (thanks @hartmark); the stale `ALL_ACCOUNTS_INACTIVE` → `ALL_TARGETS_SKIPPED` assertions and six pre-existing typecheck errors (thanks @wgordon17); an exclusive-connection-lease uniqueness test made self-contained ([#11341](https://github.com/diegosouzapw/OmniRoute/issues/11341)); the DB singleton reset made to survive the full suite, un-skipping three DB-state tests ([#11327](https://github.com/diegosouzapw/OmniRoute/issues/11327)); the CLI suite made to pass on Windows ([#11240](https://github.com/diegosouzapw/OmniRoute/issues/11240)); the Kimi refresh window no longer drawn inside its own assertion ([#11380](https://github.com/diegosouzapw/OmniRoute/issues/11380)); the GLM absolute-ISO-reset regression test given a frozen clock; spawned router-eval CLI children given an explicit `DATA_DIR`; the agent-card route handlers called with a real `NextRequest`; queued call-log writes awaited ([#10683](https://github.com/diegosouzapw/OmniRoute/issues/10683)); the aihorde client browser bundles guarded ([#10682](https://github.com/diegosouzapw/OmniRoute/issues/10682)); the env precondition of the CCR/MCP principal tests declared explicitly ([#10689](https://github.com/diegosouzapw/OmniRoute/issues/10689)); the client-bundle guard widened to every `"use client"` entry point ([#11135](https://github.com/diegosouzapw/OmniRoute/issues/11135), [#10700](https://github.com/diegosouzapw/OmniRoute/issues/10700)); standalone fixture paths resolved from file URLs ([#10451](https://github.com/diegosouzapw/OmniRoute/issues/10451)); and the services adoption tests aligned with the opt-in contract from #11040 ([#11147](https://github.com/diegosouzapw/OmniRoute/issues/11147))
+- **fix(ci):** Windows packaged-smoke process trees are cleaned up ([#10453](https://github.com/diegosouzapw/OmniRoute/issues/10453) — thanks @backryun); the coverage-pack and unit gate regressions were cleared; the OpenCode plugin CI tracks the active release branch and its combo-id fixture was aligned ([#11301](https://github.com/diegosouzapw/OmniRoute/issues/11301)); the ad-hoc `BOT_TOKEN`/`BOT_URL` env-doc-sync ignore was added, reverted and then locked by a test ([#10828](https://github.com/diegosouzapw/OmniRoute/issues/10828)); and the Electron release dependency setup was streamlined ([#10325](https://github.com/diegosouzapw/OmniRoute/issues/10325))
+- **perf(electron):** desktop packaging and startup pass — the Next standalone is built once and natives hydrated per leg ([#10390](https://github.com/diegosouzapw/OmniRoute/issues/10390)), `better-sqlite3` v13 Node-API prebuilds are verified instead of rebuilt from source ([#10367](https://github.com/diegosouzapw/OmniRoute/issues/10367)), optional ML/browser dependencies ship as installable packs ([#10382](https://github.com/diegosouzapw/OmniRoute/issues/10382)), authoring docs are pruned from the packages ([#10359](https://github.com/diegosouzapw/OmniRoute/issues/10359)), hidden-start renderer creation is deferred ([#10327](https://github.com/diegosouzapw/OmniRoute/issues/10327)) with an option to unload the renderer on close ([#10328](https://github.com/diegosouzapw/OmniRoute/issues/10328)), and lightweight readiness polling is bounded ([#10324](https://github.com/diegosouzapw/OmniRoute/issues/10324)) — thanks @backryun
+- **perf(providers):** provider schema validation is lazy and on demand, cutting startup heap ([#11334](https://github.com/diegosouzapw/OmniRoute/issues/11334), [#11220](https://github.com/diegosouzapw/OmniRoute/issues/11220))
+- **refactor(sse):** executor lookup routes through a runtime `ExecutorRegistry` (R0.3) ([#10633](https://github.com/diegosouzapw/OmniRoute/issues/10633)); the six TLS client providers were consolidated into a shared factory with wrappers ([#10910](https://github.com/diegosouzapw/OmniRoute/issues/10910) — thanks @oyi77); the Codex virtual quota pools were isolated ([#8367](https://github.com/diegosouzapw/OmniRoute/issues/8367) — thanks @xz-dev); the xAI authentication entry point was unified ([#10201](https://github.com/diegosouzapw/OmniRoute/issues/10201)); duplicate `opencode-zen`/`opencode-go` model entries were deduped ([#11051](https://github.com/diegosouzapw/OmniRoute/issues/11051)); the Radar catalog MCP tool was modularized; and the Video Bridge broker extract route moved to the structured pino logger
+- **refactor(dashboard):** custom provider quota keys are formatted into title-cased labels ([#11188](https://github.com/diegosouzapw/OmniRoute/issues/11188)), and the Add API Key modal's Enter handler mirrors the check button's disabled state ([#11156](https://github.com/diegosouzapw/OmniRoute/issues/11156))
+- **chore(security):** the self-hosted operator security tier and its blockers were integrated ([#10952](https://github.com/diegosouzapw/OmniRoute/issues/10952) — thanks @arminanton), and test fixtures were sanitized with developer `.env` guidance plus a gitleaks pass ([#10411](https://github.com/diegosouzapw/OmniRoute/issues/10411) — thanks @blarovse)
+- **chore(deps):** Dependabot batches landed across the cycle — production and development groups ([#10931](https://github.com/diegosouzapw/OmniRoute/issues/10931), [#10932](https://github.com/diegosouzapw/OmniRoute/issues/10932), [#10625](https://github.com/diegosouzapw/OmniRoute/issues/10625), [#10626](https://github.com/diegosouzapw/OmniRoute/issues/10626), [#10403](https://github.com/diegosouzapw/OmniRoute/issues/10403)), Electron 43.3.0 → 43.4.0 ([#10622](https://github.com/diegosouzapw/OmniRoute/issues/10622)) and `github/codeql-action` 4.37.4 → 4.37.7 ([#10405](https://github.com/diegosouzapw/OmniRoute/issues/10405), [#10406](https://github.com/diegosouzapw/OmniRoute/issues/10406), [#10407](https://github.com/diegosouzapw/OmniRoute/issues/10407), [#10928](https://github.com/diegosouzapw/OmniRoute/issues/10928), [#10929](https://github.com/diegosouzapw/OmniRoute/issues/10929), [#10930](https://github.com/diegosouzapw/OmniRoute/issues/10930)). Security bumps also went out directly: nanoid, DOMPurify, mermaid and js-yaml, plus transitive lifts closing 20 and then 6 more Dependabot CVE alerts
+- **fix(deps):** `@atjsh/llmlingua-2` was upgraded to 2.0.5 and `@tensorflow/tfjs` dropped ([#10610](https://github.com/diegosouzapw/OmniRoute/issues/10610) — thanks @jonlwheat2-gif), and `onnxruntime-node` is pinned to the exact version `@huggingface/transformers` requires ([#10543](https://github.com/diegosouzapw/OmniRoute/issues/10543) — thanks @dcox79)
+- **docs:** documentation pass across the cycle — a VS Code Copilot Chat guide with the `/v1/models` prefix modes ([#10648](https://github.com/diegosouzapw/OmniRoute/issues/10648)) and its platform-table entry ([#10512](https://github.com/diegosouzapw/OmniRoute/issues/10512)); an embeddings client runbook for Gemini 2 and Jina omni ([#10569](https://github.com/diegosouzapw/OmniRoute/issues/10569)); a free-provider rate-limiting troubleshooting guide ([#10112](https://github.com/diegosouzapw/OmniRoute/issues/10112)); the compression output-style catalog and its extension point ([#10649](https://github.com/diegosouzapw/OmniRoute/issues/10649)); Docker `latest` tag semantics ([#10816](https://github.com/diegosouzapw/OmniRoute/issues/10816)) and SQLite single-replica HA limits ([#10817](https://github.com/diegosouzapw/OmniRoute/issues/10817)); the distinction between access tokens, API keys and management credentials ([#10823](https://github.com/diegosouzapw/OmniRoute/issues/10823)); throttled pre-write SQLite backups ([#10824](https://github.com/diegosouzapw/OmniRoute/issues/10824)); the memory/skills/token-refresh event-loop cost ([#10825](https://github.com/diegosouzapw/OmniRoute/issues/10825)); runtime RAM for the coding-agent `/v1/responses` path ([#10983](https://github.com/diegosouzapw/OmniRoute/issues/10983)); `DEFAULT_RATE_LIMIT_PER_DAY` unset meaning unlimited ([#11031](https://github.com/diegosouzapw/OmniRoute/issues/11031)); the management-auth requirement on the spec endpoint ([#11299](https://github.com/diegosouzapw/OmniRoute/issues/11299)); embedded services explained for beginners ([#11204](https://github.com/diegosouzapw/OmniRoute/issues/11204)); the ChatGPT Web session credential guide with a canonical Cookie Editor install link; the Radar Intel/CLI contract, guided combos, supporter key recovery and end-to-end activation; the Video Bridge fusion telemetry, drill-down byte budget, cache-key dimensions and contact sheets; the OpenCode 128k context fallback JSDoc ([#11157](https://github.com/diegosouzapw/OmniRoute/issues/11157)); and the post-relay CLI documentation audit (run/configure surface, Gemini launcher, smoke harness). Drifted counts were corrected and the free-forever number gated ([#10433](https://github.com/diegosouzapw/OmniRoute/issues/10433)), the accepted doc-drift backlog closed, and the provider count synced to 343
+- **docs(i18n):** localization contributions — a complete Persian user guide ([#11254](https://github.com/diegosouzapw/OmniRoute/issues/11254)), improved and completed Turkish documentation ([#11237](https://github.com/diegosouzapw/OmniRoute/issues/11237)), the Italian README restored ([#11246](https://github.com/diegosouzapw/OmniRoute/issues/11246)), a Farsi README ([#10777](https://github.com/diegosouzapw/OmniRoute/issues/10777) — thanks @farshidrezaei), a `SETUP_GUIDE.md` correction ([#10490](https://github.com/diegosouzapw/OmniRoute/issues/10490) — thanks @realize000), a `python_requests.py` example fix ([#10731](https://github.com/diegosouzapw/OmniRoute/issues/10731) — thanks @pandaaaa1990), and a retranslation of the CLI reference and integrations guide across all 42 locales
+- **chore(repo):** repository hygiene — the self-referential `_tasks` symlink was untracked and `.gitignore` anchored so a `_tasks` symlink can never be tracked again, `.source/dynamic.ts`, `.source`, `/output/` and the Playwright CLI artifact directory were ignored, an initial `.cbmignore` was added for codebase-memory indexing, unused `.source/dynamic.ts` and `source.config.mjs` files were removed, the stray unresolved conflict marker in `ENVIRONMENT.md` was cleaned up, and the Open Collective sponsorship link was removed from the README
+- **chore(release):** localized `llm.txt` mirrors and the v3.8.50 base quality docs were synchronized, and the 363 `changelog.d` fragments were aggregated into this section
+
 
 ### 🙌 Contributors
 
@@ -785,7 +1364,10 @@ Thanks to everyone whose work landed in v3.8.50:
 | Contributor | PRs / Issues |
 | --- | --- |
 | [@AbdullahFageeh](https://github.com/AbdullahFageeh) | #9087 |
-| [@adevwithpurpose](https://github.com/adevwithpurpose) | #9790, #10118, #10222 |
+| [@abhijeetnardele24-hash](https://github.com/abhijeetnardele24-hash) | #10498 |
+| [@Abhishek4512009](https://github.com/Abhishek4512009) | #10494 |
+| [@acc0mplish](https://github.com/acc0mplish) | #10732, #10948 |
+| [@adevwithpurpose](https://github.com/adevwithpurpose) | #9790, #10118, #10222, #10800, #10834, #10835, #10836, #10882 |
 | [@adrianojiu](https://github.com/adrianojiu) | #8438 |
 | [@agisota](https://github.com/agisota) | #9837 |
 | [@AgnesRiber](https://github.com/AgnesRiber) | #9718, #9976 |
@@ -793,93 +1375,137 @@ Thanks to everyone whose work landed in v3.8.50:
 | [@AIB1TAL0S](https://github.com/AIB1TAL0S) | #9284 |
 | [@AlanSyue](https://github.com/AlanSyue) | direct commit / report |
 | [@alex-jordan547](https://github.com/alex-jordan547) | #9235, #9245, #9813 |
+| [@aliyosufi](https://github.com/aliyosufi) | #11159 |
 | [@amartinawi](https://github.com/amartinawi) | #10090, #10091, #10092, #10097, #10101 |
-| [@AndrianBalanescu](https://github.com/AndrianBalanescu) | #8888, #8889, #8890, #8891, #8892, #8893, #8894, #8895 |
+| [@An0nym0us92](https://github.com/An0nym0us92) | #11394 |
+| [@AndrianBalanescu](https://github.com/AndrianBalanescu) | #8888, #8889, #8890, #8891, #8892, #8893, #8894, #8895, #11081, #11082 |
 | [@AnhLead](https://github.com/AnhLead) | #9722 |
 | [@aniketshukla1](https://github.com/aniketshukla1) | #9148 |
 | [@Anjielon](https://github.com/Anjielon) | #8776 |
+| [@anudeepadi](https://github.com/anudeepadi) | #10288 |
 | [@apoapostolov](https://github.com/apoapostolov) | #8916 |
+| [@app](https://github.com/app) | #10042, #10043 |
+| [@arafatkatze](https://github.com/arafatkatze) | #10706 |
 | [@ARC345](https://github.com/ARC345) | #9628, #10050, #10051 |
-| [@artickc](https://github.com/artickc) | #8571, #8578, #8791, #8843, #8870, #8927, #8974, #9097, #9549 |
+| [@arminanton](https://github.com/arminanton) | #10933, #10952, #11166 |
+| [@aron-intframe](https://github.com/aron-intframe) | #10459 |
+| [@artickc](https://github.com/artickc) | #8571, #8578, #8791, #8843, #8870, #8927, #8974, #9097, #9255, #9549 |
 | [@Arul-](https://github.com/Arul-) | #9761 |
-| [@AStupidBear](https://github.com/AStupidBear) | #10180 |
+| [@asorourx](https://github.com/asorourx) | #11036 |
+| [@AStupidBear](https://github.com/AStupidBear) | #10180, #11385 |
+| [@azzaouiomar19-sketch](https://github.com/azzaouiomar19-sketch) | #10394 |
 | [@b1nhm1nh](https://github.com/b1nhm1nh) | direct commit / report |
-| [@backryun](https://github.com/backryun) | #8228, #8451, #8627, #8809, #8818, #9084, #9086, #9090, #9091, #9092, #9093, #9114, #9119, #9120, #9122, #9135, #9136, #9137, #9138, #9139, #9141, #9561, #9562, #9563, #9564, #9565, #9566, #9742, #9747, #9748, #9751, #9753, #9755, #9791, #9792, #9793, #9795, #9796, #9797, #9798, #9920, #9972, #9973, #9974, #9975, #9977, #9978, #9979, #9984, #9986, #9987, #9988, #9989, #9990, #9998, #10087, #10088, #10134, #10178, #10175, #10254, #10255, #10256, #10257, #10258, #10339 |
+| [@backryun](https://github.com/backryun) | #8228, #8451, #8627, #8809, #8818, #9084, #9086, #9090, #9091, #9092, #9093, #9114, #9119, #9120, #9122, #9135, #9136, #9137, #9138, #9139, #9141, #9561, #9562, #9563, #9564, #9565, #9566, #9742, #9747, #9748, #9751, #9753, #9755, #9791, #9792, #9793, #9795, #9796, #9797, #9798, #9920, #9972, #9973, #9974, #9975, #9977, #9978, #9979, #9984, #9986, #9987, #9988, #9989, #9990, #9998, #10087, #10088, #10134, #10175, #10178, #10195, #10254, #10255, #10256, #10257, #10258, #10324, #10339, #10453, #10464, #10483, #10637, #10964 |
 | [@Benson-mk](https://github.com/Benson-mk) | #8369 |
-| [@benzntech](https://github.com/benzntech) | #9810, #9812, #9939 |
+| [@benzntech](https://github.com/benzntech) | #9810, #9812, #9939, #10124, #10126, #10458 |
 | [@Bl0ck154](https://github.com/Bl0ck154) | #9231 |
+| [@blackwell-systems](https://github.com/blackwell-systems) | #10807 |
+| [@blarovse](https://github.com/blarovse) | #10411 |
 | [@bortolidiego](https://github.com/bortolidiego) | #10058 |
-| [@branben](https://github.com/branben) | #9940 |
-| [@Chewji9875](https://github.com/Chewji9875) | #9257, #9420, #9821, #9994, #10160 |
-| [@chirag127](https://github.com/chirag127) | #6674 |
+| [@branben](https://github.com/branben) | #9940, #10575 |
+| [@Chewji9875](https://github.com/Chewji9875) | #9257, #9420, #9821, #9994, #10116, #10160, #10305, #10376 |
+| [@chirag127](https://github.com/chirag127) | #6674, #10071 |
 | [@chloeassistant](https://github.com/chloeassistant) | #9675, #9746 |
 | [@configurowebmax](https://github.com/configurowebmax) | #8877 |
 | [@corefusiion](https://github.com/corefusiion) | #8285 |
 | [@costaeder](https://github.com/costaeder) | #8626, #8629, #8630 |
+| [@cryptiklemur](https://github.com/cryptiklemur) | #10684, #10685 |
 | [@csoftware-arigpt](https://github.com/csoftware-arigpt) | #3440 |
 | [@DaDecky](https://github.com/DaDecky) | direct commit / report |
+| [@danscMax](https://github.com/danscMax) | #8634 |
 | [@DarkEsteves](https://github.com/DarkEsteves) | #10250 |
+| [@dcox79](https://github.com/dcox79) | #10543 |
 | [@ddarkr](https://github.com/ddarkr) | #9035, #9036, #10177 |
-| [@diegosouzapw](https://github.com/diegosouzapw) | maintainer |
 | [@Dingding-leo](https://github.com/Dingding-leo) | #7987, #8640, #8678, #8704, #8774, #8790, #8808, #8817 |
 | [@DinonowDev](https://github.com/DinonowDev) | #8804 |
+| [@dionjoshualobo](https://github.com/dionjoshualobo) | #9721 |
+| [@dpozimski](https://github.com/dpozimski) | #10253 |
 | [@Dragost](https://github.com/Dragost) | #8339 |
 | [@dsitmilis](https://github.com/dsitmilis) | direct commit / report |
-| [@Egorich-print](https://github.com/Egorich-print) | #9001, #9020, #9058 |
+| [@echoriver89](https://github.com/echoriver89) | #10717 |
+| [@Egorich-print](https://github.com/Egorich-print) | #9001, #9020, #9058, #10881, #10887, #11097 |
+| [@ekinnee](https://github.com/ekinnee) | #11307 |
+| [@electrumguy](https://github.com/electrumguy) | #10774, #11149 |
 | [@engmarcosjr](https://github.com/engmarcosjr) | #9993 |
 | [@epsilonode](https://github.com/epsilonode) | #8871 |
 | [@ervareza](https://github.com/ervareza) | direct commit / report |
-| [@excessivechaos](https://github.com/excessivechaos) | #10062, #10138 |
+| [@excessivechaos](https://github.com/excessivechaos) | #10062, #10138, #10552, #10883, #10884, #10907, #11179 |
 | [@fajarhide](https://github.com/fajarhide) | #9191, #9198 |
-| [@fenix007](https://github.com/fenix007) | #9618 |
+| [@farshidrezaei](https://github.com/farshidrezaei) | #10777 |
+| [@fenix007](https://github.com/fenix007) | #9618, #10016 |
+| [@freudantunes](https://github.com/freudantunes) | #10623 |
 | [@Gecky2102](https://github.com/Gecky2102) | #9280 |
-| [@ggdayup](https://github.com/ggdayup) | #10199 |
+| [@geek007git](https://github.com/geek007git) | #10441 |
+| [@ggdayup](https://github.com/ggdayup) | #10199, #11113, #11114, #11375 |
+| [@Gi99lin](https://github.com/Gi99lin) | #10342 |
+| [@giauphan](https://github.com/giauphan) | #10392 |
 | [@Gioxaa](https://github.com/Gioxaa) | #9162, #9171 |
 | [@HaoNgo232](https://github.com/HaoNgo232) | direct commit / report |
 | [@Hariprajwal](https://github.com/Hariprajwal) | #9922 |
-| [@hartmark](https://github.com/hartmark) | #9635, #9704, #9711, #9712, #9727, #9734, #9735, #9738, #9741, #9744, #9745, #9822, #10025, #10034, #10037, #10038, #10041, #10121, #10217 |
+| [@harkaranbrar7](https://github.com/harkaranbrar7) | #10281 |
+| [@hartmark](https://github.com/hartmark) | #9635, #9704, #9711, #9712, #9727, #9734, #9735, #9738, #9741, #9744, #9745, #9822, #10025, #10034, #10037, #10038, #10041, #10121, #10217, #10262, #10263, #10330, #10331, #11259 |
 | [@Hdiaktoros](https://github.com/Hdiaktoros) | #8930 |
 | [@HectorBernstorff](https://github.com/HectorBernstorff) | direct commit / report |
 | [@HellFiveOsborn](https://github.com/HellFiveOsborn) | #9248 |
-| [@herjarsa](https://github.com/herjarsa) | #9714, #9816, #9937, #9946, #10128 |
+| [@herjarsa](https://github.com/herjarsa) | #9714, #9816, #9937, #9946, #10128, #10456 |
+| [@hgaib](https://github.com/hgaib) | #10722 |
 | [@horacecar](https://github.com/horacecar) | #7679 |
-| [@HouMinXi](https://github.com/HouMinXi) | #8886, #8904, #8905, #8976, #8984, #9079, #9106, #9207, #9242, #9328, #9340, #9342, #9351, #9365, #9380, #9381, #9392, #9449, #9482, #9483, #9509, #9510, #9572, #9631, #9634, #9695, #9929 |
+| [@HouMinXi](https://github.com/HouMinXi) | #8886, #8904, #8905, #8976, #8984, #9079, #9106, #9207, #9242, #9328, #9340, #9342, #9351, #9365, #9380, #9381, #9392, #9449, #9482, #9483, #9509, #9510, #9572, #9631, #9634, #9695, #9929, #10457, #10475, #10525, #10529, #10573, #10663, #10846, #11084, #11139, #11140, #11141, #11386, #11418 |
 | [@hppsc1215](https://github.com/hppsc1215) | #8970 |
-| [@hydraxman](https://github.com/hydraxman) | #10137 |
+| [@Hsia97](https://github.com/Hsia97) | #10810 |
+| [@hydraxman](https://github.com/hydraxman) | #10137, #10572 |
 | [@Iammilansoni](https://github.com/Iammilansoni) | #9353, #9397 |
+| [@ignamiranda](https://github.com/ignamiranda) | #11206 |
 | [@ikelvingo](https://github.com/ikelvingo) | #8591, #8872, #9053 |
 | [@infinit-X](https://github.com/infinit-X) | #9095 |
+| [@InkshadeWoods](https://github.com/InkshadeWoods) | #10733 |
 | [@isaaclb98](https://github.com/isaaclb98) | #9730 |
-| [@jackjinke](https://github.com/jackjinke) | #9556, #9601, #10005, #10045 |
+| [@jackjinke](https://github.com/jackjinke) | #9556, #9601, #10005, #10045, #10248, #10533, #10540, #10574, #11041 |
+| [@jacobsparts](https://github.com/jacobsparts) | #11399, #11400, #11402 |
 | [@jax-novita](https://github.com/jax-novita) | #8913 |
 | [@jeff-alves](https://github.com/jeff-alves) | #10221 |
 | [@jeyhunfaslanov](https://github.com/jeyhunfaslanov) | #10259 |
 | [@jhordanjw123](https://github.com/jhordanjw123) | #8736 |
 | [@jktan0504](https://github.com/jktan0504) | #9025 |
 | [@joachimBrindeau](https://github.com/joachimBrindeau) | #9200 |
+| [@jonlwheat2-gif](https://github.com/jonlwheat2-gif) | #10610, #10709, #11194 |
 | [@JoshimOfficial](https://github.com/JoshimOfficial) | #9011 |
 | [@jowimila](https://github.com/jowimila) | #9325 |
-| [@JxnLexn](https://github.com/JxnLexn) | #8933, #8940, #8944, #8949 |
+| [@JxnLexn](https://github.com/JxnLexn) | #8933, #8940, #8944, #8949, #10422, #10608 |
 | [@Kaedo17](https://github.com/Kaedo17) | #8922 |
+| [@KaspaPulse](https://github.com/KaspaPulse) | #10362 |
 | [@khoazero123](https://github.com/khoazero123) | #9272 |
+| [@killmonger2317-coder](https://github.com/killmonger2317-coder) | #10445 |
 | [@KittisakT](https://github.com/KittisakT) | #9423 |
+| [@Kizuno18](https://github.com/Kizuno18) | #10803 |
 | [@KooshaPari](https://github.com/KooshaPari) | #7329 |
+| [@kriptoburak](https://github.com/kriptoburak) | #10854 |
+| [@krishna3554](https://github.com/krishna3554) | #10620, #10855 |
+| [@lamchun1110](https://github.com/lamchun1110) | #10372, #10397 |
 | [@larin-vas](https://github.com/larin-vas) | #9828 |
 | [@lazysaltyfish](https://github.com/lazysaltyfish) | direct commit / report |
 | [@LeonG606](https://github.com/LeonG606) | #9457 |
+| [@linhdmn](https://github.com/linhdmn) | #10980, #11085, #11214, #11274 |
 | [@Llliao1113](https://github.com/Llliao1113) | #8921 |
 | [@lucasalx](https://github.com/lucasalx) | #9919 |
 | [@lucasmellos](https://github.com/lucasmellos) | #8925 |
 | [@lukiod](https://github.com/lukiod) | #8828 |
 | [@luoyide](https://github.com/luoyide) | direct commit / report |
+| [@maci0](https://github.com/maci0) | #11279 |
 | [@mad-gooze](https://github.com/mad-gooze) | #9052 |
 | [@maisdesign](https://github.com/maisdesign) | #8858 |
+| [@marcelokarval](https://github.com/marcelokarval) | #11397 |
 | [@marchlhw](https://github.com/marchlhw) | #9050 |
+| [@marcs7](https://github.com/marcs7) | #11180 |
 | [@matiasbaglieri](https://github.com/matiasbaglieri) | #9707 |
-| [@maxmad64bis](https://github.com/maxmad64bis) | #9150, #9246, #9291, #9414 |
+| [@maxmad64bis](https://github.com/maxmad64bis) | #9150, #9246, #9291, #9414, #10278, #10402, #10652, #10662, #10664, #10694, #10769, #10770, #10779, #10876, #10885, #10974, #10978, #11008, #11009, #11047, #11116, #11129, #11130, #11133, #11151, #11162, #11252 |
 | [@McLuck](https://github.com/McLuck) | #8914 |
+| [@megamen32](https://github.com/megamen32) | #10184 |
+| [@MeRezaRezaei](https://github.com/MeRezaRezaei) | #10174, #10614, #10944, #11042, #11045 |
 | [@Michael-Rocco-Goldmann](https://github.com/Michael-Rocco-Goldmann) | #9770, #9773, #9777, #9787 |
-| [@MichaelYcJo](https://github.com/MichaelYcJo) | #8244 |
+| [@MichaelYcJo](https://github.com/MichaelYcJo) | #8244, #10725, #10726 |
+| [@Minamaged18](https://github.com/Minamaged18) | #11269 |
+| [@minhlongs](https://github.com/minhlongs) | #10805 |
 | [@minhnhat166](https://github.com/minhnhat166) | direct commit / report |
 | [@MohitRawat017](https://github.com/MohitRawat017) | #8718, #8772, #9605 |
 | [@Momen4444](https://github.com/Momen4444) | #9612 |
@@ -887,64 +1513,103 @@ Thanks to everyone whose work landed in v3.8.50:
 | [@mtb-ninja](https://github.com/mtb-ninja) | #10114 |
 | [@MumuTW](https://github.com/MumuTW) | #8839 |
 | [@mvanhorn](https://github.com/mvanhorn) | #9542 |
+| [@mymusicmyspace](https://github.com/mymusicmyspace) | #10965 |
 | [@Mynacol](https://github.com/Mynacol) | #9733 |
+| [@NahuSaruf](https://github.com/NahuSaruf) | #10545 |
+| [@Neuron-Mr-White](https://github.com/Neuron-Mr-White) | #10228, #10230, #10957, #11378 |
 | [@nguyenha935](https://github.com/nguyenha935) | #9044, #9215 |
 | [@nordz0r](https://github.com/nordz0r) | #10170 |
 | [@nosolosoft](https://github.com/nosolosoft) | #8900 |
-| [@oyi77](https://github.com/oyi77) | #8299, #8752, #9158, #9818 |
-| [@pacocartones](https://github.com/pacocartones) | #10216 |
+| [@ntdat812](https://github.com/ntdat812) | #10843, #10853, #10857, #10858, #10860, #10862, #10868, #10935, #11004, #11374, #11376, #11377 |
+| [@ntdatt812](https://github.com/ntdatt812) | #10715, #11076 |
+| [@octo-patch](https://github.com/octo-patch) | #10650 |
+| [@ofonseca-pyming](https://github.com/ofonseca-pyming) | #11297 |
+| [@oyi77](https://github.com/oyi77) | #8299, #8752, #9158, #9818, #10910, #10942 |
+| [@pacocartones](https://github.com/pacocartones) | #10216, #10673, #11059, #11193, #11199, #11238, #11241, #11321, #11322, #11332, #11338 |
+| [@pandaaaa1990](https://github.com/pandaaaa1990) | #10731 |
+| [@phatchau036](https://github.com/phatchau036) | #10517 |
+| [@phuongddx](https://github.com/phuongddx) | #11415 |
 | [@PixmaNts](https://github.com/PixmaNts) | #9432 |
 | [@pizzav-xyz](https://github.com/pizzav-xyz) | #9077 |
 | [@Poid-ZA](https://github.com/Poid-ZA) | #9467 |
 | [@Prudhvivuda](https://github.com/Prudhvivuda) | #8807, #9014, #9015, #9016 |
+| [@pucedoteth](https://github.com/pucedoteth) | #10607 |
 | [@qianze0628](https://github.com/qianze0628) | #9038 |
+| [@rafacpti23](https://github.com/rafacpti23) | #11207, #11213 |
 | [@raflyazf](https://github.com/raflyazf) | direct commit / report |
-| [@Rahulsharma0810](https://github.com/Rahulsharma0810) | #8961 |
-| [@rinseaid](https://github.com/rinseaid) | #8945, #9037, #9932, #9933, #9969, #9982 |
+| [@Rahulsharma0810](https://github.com/Rahulsharma0810) | #8961, #10872 |
+| [@RaviTharuma](https://github.com/RaviTharuma) | #10055, #10297, #10307, #10344, #10352, #10488, #10565, #10566, #10568, #10584, #10771, #10814, #10818, #10820, #10821, #10822, #10827, #10847, #10971, #10979, #10981, #11014, #11015, #11016, #11017, #11020, #11024, #11314, #11318, #11320 |
+| [@realize000](https://github.com/realize000) | #10490 |
+| [@redzrush101](https://github.com/redzrush101) | #10492 |
+| [@rengaryang](https://github.com/rengaryang) | #11333 |
+| [@rinseaid](https://github.com/rinseaid) | #8945, #9037, #9932, #9933, #9969, #9982, #10554 |
+| [@ritheshcn25](https://github.com/ritheshcn25) | #10026 |
 | [@rixzkiye](https://github.com/rixzkiye) | direct commit / report |
+| [@rizxfrog](https://github.com/rizxfrog) | #10356, #10546 |
 | [@RobertsXML](https://github.com/RobertsXML) | direct commit / report |
 | [@royanrosyad85](https://github.com/royanrosyad85) | direct commit / report |
+| [@rqzbeh](https://github.com/rqzbeh) | #10415, #10420, #10424, #10430, #10465, #10470, #10890, #10894, #10898, #10899, #10901, #11039, #11054, #11055, #11056, #11078, #11117, #11123, #11125, #11132, #11155, #11161, #11177, #11182, #11189, #11262 |
 | [@rushsinging](https://github.com/rushsinging) | #8947 |
 | [@ryan-brosas](https://github.com/ryan-brosas) | #9693 |
 | [@ryanngit](https://github.com/ryanngit) | direct commit / report |
-| [@sadSanta-07](https://github.com/sadSanta-07) | #9938 |
+| [@sadSanta-07](https://github.com/sadSanta-07) | #9938, #10209, #10605, #10772 |
 | [@SalyyS1](https://github.com/SalyyS1) | direct commit / report |
 | [@Sam280903](https://github.com/Sam280903) | #9274, #9278, #9281, #9283, #9448 |
+| [@sanforex24h](https://github.com/sanforex24h) | #11026 |
+| [@SCys](https://github.com/SCys) | #11107 |
 | [@seakleangnhak](https://github.com/seakleangnhak) | direct commit / report |
 | [@seanford](https://github.com/seanford) | #8523 |
 | [@SemonCat](https://github.com/SemonCat) | direct commit / report |
+| [@sha367](https://github.com/sha367) | #10471 |
 | [@shixi-li](https://github.com/shixi-li) | #9022, #9513, #10001 |
+| [@Siva010](https://github.com/Siva010) | #10658 |
+| [@SnCr90](https://github.com/SnCr90) | #10534 |
 | [@soulhakr](https://github.com/soulhakr) | #8799 |
-| [@stanleytejakusuma](https://github.com/stanleytejakusuma) | #9610 |
+| [@sprintberlin](https://github.com/sprintberlin) | #11353, #11355, #11360 |
+| [@stanleytejakusuma](https://github.com/stanleytejakusuma) | #9610, #10636, #10660, #10730, #11337 |
 | [@Stazyu](https://github.com/Stazyu) | #9007, #9226, #9438 |
 | [@SupremeNexas](https://github.com/SupremeNexas) | #9913 |
-| [@swingtempo](https://github.com/swingtempo) | #9307 |
+| [@swingtempo](https://github.com/swingtempo) | #9307, #10354 |
 | [@szzhoujiarui](https://github.com/szzhoujiarui) | #9218 |
 | [@tald26](https://github.com/tald26) | #9959 |
 | [@taltas](https://github.com/taltas) | direct commit / report |
-| [@TechNickAI](https://github.com/TechNickAI) | #9251 |
+| [@TechNickAI](https://github.com/TechNickAI) | #9251, #10558 |
 | [@TengSivtean](https://github.com/TengSivtean) | #10000, #10002, #10086 |
+| [@TheDemonTuan](https://github.com/TheDemonTuan) | #11364 |
 | [@TheFrenchGhosty](https://github.com/TheFrenchGhosty) | #9326 |
-| [@tiangao88](https://github.com/tiangao88) | #10046 |
+| [@tiangao88](https://github.com/tiangao88) | #10046, #10363 |
+| [@tientien17](https://github.com/tientien17) | #10798 |
+| [@tito13kfm](https://github.com/tito13kfm) | #10227 |
+| [@tkgo11](https://github.com/tkgo11) | #10370, #10371 |
+| [@tuandinh0801](https://github.com/tuandinh0801) | #10804, #10830, #11230 |
+| [@Tushar49](https://github.com/Tushar49) | #10186 |
 | [@tuxmonteiro](https://github.com/tuxmonteiro) | #9065 |
 | [@vinogradovnet](https://github.com/vinogradovnet) | #9581 |
 | [@VXNCXNX](https://github.com/VXNCXNX) | #9111, #9783 |
 | [@wgordon17](https://github.com/wgordon17) | #8909, #9233, #9441, #9619 |
 | [@Witroch4](https://github.com/Witroch4) | #8713 |
 | [@witt3rd](https://github.com/witt3rd) | #9962, #9963 |
+| [@wpec](https://github.com/wpec) | #10839 |
 | [@XDayonline](https://github.com/XDayonline) | #10053 |
-| [@xiaoyaner0201](https://github.com/xiaoyaner0201) | #8757, #8869, #8876, #8883, #8906, #8931, #9021, #9027, #9452, #9042, #9316 |
-| [@xz-dev](https://github.com/xz-dev) | #8908, #9199, #9205, #9262, #9290, #9313, #9555, #9569, #9629, #9788, #9983, #10079, #10243 |
-| [@yansigit](https://github.com/yansigit) | #9834, #9911, #9917, #9921, #10065 |
+| [@xiaoyaner0201](https://github.com/xiaoyaner0201) | #8757, #8869, #8876, #8883, #8906, #8931, #9021, #9027, #9042, #9316, #9452, #10468 |
+| [@xyzs996](https://github.com/xyzs996) | #11210 |
+| [@xz-dev](https://github.com/xz-dev) | #8367, #8908, #9199, #9205, #9262, #9290, #9313, #9555, #9569, #9629, #9788, #9983, #10066, #10072, #10079, #10162, #10243, #10247, #10437, #10712, #10716, #10723, #10806, #10953 |
+| [@yansigit](https://github.com/yansigit) | #9834, #9909, #9911, #9917, #9921, #10065 |
 | [@yidecode](https://github.com/yidecode) | direct commit / report |
+| [@yourspraveen](https://github.com/yourspraveen) | #11075, #11088, #11165, #11271 |
 | [@yulinlina](https://github.com/yulinlina) | #10013 |
+| [@YunyunZhai](https://github.com/YunyunZhai) | #10946, #10960 |
 | [@yutuknown](https://github.com/yutuknown) | #8999 |
 | [@zabrodschiipavel-sketch](https://github.com/zabrodschiipavel-sketch) | #9312 |
-| [@Zartharas](https://github.com/Zartharas) | #9161, #9164, #9181, #9182, #9184, #9185, #9186, #9189, #9294, #9825, #9833, #9936, #9965, #9992, #10218 |
+| [@zannen7](https://github.com/zannen7) | #10077 |
+| [@Zartharas](https://github.com/Zartharas) | #9161, #9164, #9181, #9182, #9184, #9185, #9186, #9189, #9294, #9825, #9833, #9936, #9965, #9992, #10202, #10218, #10272, #10329, #10518, #10519, #10521, #10799, #10873, #10878 |
 | [@Zenlyte](https://github.com/Zenlyte) | #9005 |
 | [@zhiru](https://github.com/zhiru) | #9099, #9101 |
-| [@ziuus](https://github.com/ziuus) | #8912 |
+| [@ziuus](https://github.com/ziuus) | #8912, #11372 |
+| [@zmf963](https://github.com/zmf963) | direct commit / report |
+| [@zoser69](https://github.com/zoser69) | #10874 |
 | [@zuckdorsey](https://github.com/zuckdorsey) | #9723 |
+| [@diegosouzapw](https://github.com/diegosouzapw) | maintainer |
 
 ---
 

Dockerfile

@@ -59,6 +59,12 @@ RUN set -eux; \
 # ── Builder ────────────────────────────────────────────────────────────────
 FROM base AS builder
 
+# No telemetry, anywhere. Disable Next.js's anonymous build-time telemetry
+# (it otherwise pings Vercel during `next build`). Set on the builder stage so
+# every image build is silent; the runtime never builds, so this covers the
+# only phase Next telemetry can fire.
+ENV NEXT_TELEMETRY_DISABLED=1
+
 # Build tools for native module compilation
 # apt-get update needed here because base's rm -rf clears the shared cache
 RUN --mount=type=cache,id=s/92ca8a61-c1ba-421f-a389-d48ac7258c2d-apt-cache,target=/var/cache/apt,sharing=locked \
@@ -166,14 +172,38 @@ ENV OMNIROUTE_MITM_STUB=1
 # child (build-next-isolated.mjs → resolveNextBuildEnv spreads process.env).
 # Build-only; the runtime heap is set separately on the runner stage
 # (OMNIROUTE_MEMORY_MB). Override: `--build-arg OMNIROUTE_BUILD_MEMORY_MB=6144`.
-ARG OMNIROUTE_BUILD_MEMORY_MB=4096
+# Default raised 4096 → 6144 (#10060): the Next 16 production pass on a codebase
+# this size intermittently OOMs a build worker at 4 GB on memory-tight hosts.
+ARG OMNIROUTE_BUILD_MEMORY_MB=6144
 ENV NODE_OPTIONS="--max-old-space-size=${OMNIROUTE_BUILD_MEMORY_MB}"
 
+# Cap Next.js build worker pools. Next 16 defaults to `os.cpus().length - 1`
+# workers for page-data collection (31 on a 32-core builder); on memory-tight
+# hosts 31 workers + webpack's multi-GB heap blow past RAM and a worker dies
+# with SIGSEGV at teardown ("worker exited with code: null and signal: SIGSEGV"),
+# silently leaving no standalone bundle. Next derives the worker count from
+# CIRCLE_NODE_TOTAL (workers = N-1). (#10060)
+#
+# Lowered 8 → 3 (7 workers → 2). Every page-data worker inherits NODE_OPTIONS
+# above, so the ceiling is per PROCESS, not per build: 7 workers on a 16 GB
+# GitHub runner (ubuntu-24.04 / ubuntu-24.04-arm, 4 vCPU) exhausted the host and
+# buildkit failed the whole step with `ResourceExhausted: ... cannot allocate
+# memory`. The compile phase always finished ("✓ Compiled successfully in
+# 4.2min"); the kernel killed the build right after "Collecting page data using
+# 7 workers". It was intermittent for a while and went 100% on 2026-08-22, which
+# is what a threshold being crossed by ordinary codebase growth looks like.
+# tests/unit/docker-build-memory-budget.test.ts does the arithmetic and fails if
+# either knob is raised past what a 16 GB runner holds. 2 workers also stops
+# oversubscribing the runner's 4 vCPU, which 7 did. Override for a big builder:
+# `--build-arg OMNIROUTE_BUILD_WORKERS=8`.
+ARG OMNIROUTE_BUILD_WORKERS=3
+ENV CIRCLE_NODE_TOTAL=${OMNIROUTE_BUILD_WORKERS}
+
 COPY . ./
 RUN --mount=type=cache,id=s/92ca8a61-c1ba-421f-a389-d48ac7258c2d-next-cache,target=/app/.build/next/cache \
   mkdir -p /app/data \
   && npm run build \
-  && node --input-type=module -e "import { createRequire } from 'node:module'; import { pathToFileURL } from 'node:url'; const standaloneRoot = '/app/.build/next/standalone/node_modules/'; const require = createRequire('/app/.build/next/standalone/package.json'); for (const pkg of ['@atjsh/llmlingua-2', '@huggingface/transformers', '@tensorflow/tfjs', 'js-tiktoken']) { const resolved = require.resolve(pkg); if (!resolved.startsWith(standaloneRoot)) throw new Error(pkg + ' resolved outside standalone: ' + resolved); await import(pathToFileURL(resolved).href); } const onnxRuntime = require.resolve('onnxruntime-node'); if (!onnxRuntime.startsWith(standaloneRoot)) throw new Error('onnxruntime-node resolved outside standalone: ' + onnxRuntime); await import(pathToFileURL(onnxRuntime).href);"
+  && node --input-type=module -e "import { createRequire } from 'node:module'; import { pathToFileURL } from 'node:url'; const standaloneRoot = '/app/.build/next/standalone/node_modules/'; const require = createRequire('/app/.build/next/standalone/package.json'); for (const pkg of ['@atjsh/llmlingua-2', '@huggingface/transformers', 'js-tiktoken']) { const resolved = require.resolve(pkg); if (!resolved.startsWith(standaloneRoot)) throw new Error(pkg + ' resolved outside standalone: ' + resolved); await import(pathToFileURL(resolved).href); } const onnxRuntime = require.resolve('onnxruntime-node'); if (!onnxRuntime.startsWith(standaloneRoot)) throw new Error('onnxruntime-node resolved outside standalone: ' + onnxRuntime); await import(pathToFileURL(onnxRuntime).href);"
 
 # ── Runner base ────────────────────────────────────────────────────────────
 FROM base AS runner-base

Dockerfile.bun

@@ -0,0 +1,146 @@
+# ── Multi-stage Dockerfile for Native Bun Runtime (web-latest-bun) ───────────
+FROM oven/bun:1.3.14-slim AS base
+WORKDIR /app
+
+RUN apt-get update \
+  && apt-get upgrade -y \
+  && apt-get install -y --no-install-recommends \
+     build-essential \
+     python3 \
+     python-is-python3 \
+     make \
+     g++ \
+     libsecret-1-0 \
+     ca-certificates \
+     curl \
+  && rm -rf /var/lib/apt/lists/*
+
+# ── Builder stage (100% Bun Native Install & Build) ─────────────────────────
+FROM base AS builder
+WORKDIR /app
+
+COPY . .
+
+# Fast Bun native package install
+RUN bun install --include=optional --quiet
+
+# Compile native better-sqlite3 Node-API addon under Bun
+RUN if [ -d "node_modules/better-sqlite3" ]; then \
+      (cd node_modules/better-sqlite3 && bunx node-gyp rebuild); \
+    fi
+
+# Fetch tls-client-node native binary if script exists
+RUN if [ -f "node_modules/tls-client-node/scripts/postinstall.js" ]; then \
+      bun node_modules/tls-client-node/scripts/postinstall.js || true; \
+    fi
+
+# Disable Turbopack for Bun builder stage (Turbopack V8 internal worker bindings require Node)
+ENV OMNIROUTE_USE_TURBOPACK=0
+
+ARG OMNIROUTE_BASE_PATH=""
+ENV OMNIROUTE_BASE_PATH=$OMNIROUTE_BASE_PATH
+
+ARG DASHBOARD_ALLOW_EMBED=""
+ENV DASHBOARD_ALLOW_EMBED=$DASHBOARD_ALLOW_EMBED
+
+ENV NEXT_TELEMETRY_DISABLED=1
+ENV NODE_ENV=production
+
+# Bun native Next.js build execution
+RUN bun run --quiet build
+
+# ── Runner Base stage (100% Bun Native Production Runtime) ──────────────────
+FROM oven/bun:1.3.14-slim AS runner-base
+
+LABEL org.opencontainers.image.title="omniroute" \
+  org.opencontainers.image.description="Unified AI proxy — route any LLM through one endpoint (Bun Native)" \
+  org.opencontainers.image.url="https://omniroute.online" \
+  org.opencontainers.image.source="https://github.com/diegosouzapw/OmniRoute" \
+  org.opencontainers.image.licenses="MIT"
+
+WORKDIR /app
+
+RUN apt-get update \
+  && apt-get install -y --no-install-recommends \
+     libsecret-1-0 \
+     ca-certificates \
+     curl \
+  && rm -rf /var/lib/apt/lists/*
+
+ENV NODE_ENV=production
+ENV PORT=20128
+ENV HOSTNAME=0.0.0.0
+ENV OMNIROUTE_MEMORY_MB=1024
+
+ENV DATA_DIR=/app/data
+RUN mkdir -p /app/data
+
+COPY --from=builder /app/.build/next/standalone ./
+COPY --from=builder /app/node_modules/better-sqlite3 ./node_modules/better-sqlite3
+ENV OMNIROUTE_MIGRATIONS_DIR=/app/migrations
+
+COPY --from=builder /app/scripts/dev/healthcheck.mjs ./healthcheck.mjs
+
+EXPOSE 20128
+
+HEALTHCHECK --interval=30s --timeout=5s --start-period=15s --retries=3 \
+  CMD bun healthcheck.mjs || exit 1
+
+ENTRYPOINT ["bun", "dev/run-standalone.mjs"]
+
+# ── Runner Web stage (Bun Native + Chromium/Playwright for Web providers) ───
+FROM runner-base AS runner-web
+
+USER root
+
+RUN apt-get update \
+  && apt-get install -y --no-install-recommends \
+     chromium \
+     chromium-driver \
+     fonts-liberation \
+     libasound2t64 \
+     gconf-service \
+     libatk-bridge2.0-0 \
+     libatk1.0-0 \
+     libc6 \
+     libcairo2 \
+     libcups2 \
+     libdbus-1-3 \
+     libexpat1 \
+     libfontconfig1 \
+     libgbm1 \
+     libgcc-s1 \
+     libglib2.0-0 \
+     libgtk-3-0 \
+     libnspr4 \
+     libnss3 \
+     libpango-1.0-0 \
+     pangocairo-1.0-0 \
+     stdc++6 \
+     libx11-6 \
+     libx11-xcb1 \
+     libxcb1 \
+     libxcomposite1 \
+     libxcursor1 \
+     libxdamage1 \
+     libxext6 \
+     libxfixes3 \
+     libxi6 \
+     libxrandr2 \
+     libxrender1 \
+     libxss1 \
+     libxtst6 \
+     ca-certificates \
+     fonts-gargi \
+     fonts-ipafont-gothic \
+     fonts-kacst \
+     fonts-thai-tlwg \
+     fonts-wqy-zenhei \
+  && rm -rf /var/lib/apt/lists/*
+
+ENV PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD=1
+ENV PLAYWRIGHT_CHROMIUM_EXECUTABLE_PATH=/usr/bin/chromium
+
+# Return to the base image non-root user after the apt install (mirrors the
+# Node Dockerfile runner-web stage, which re-asserts USER node).
+USER bun

PROVIDER_REFERENCE.md

@@ -0,0 +1,447 @@
+---
+title: "Provider Reference"
+version: 3.8.50
+lastUpdated: 2026-08-21
+---
+
+# Provider Reference
+
+> **Auto-generated** from `src/shared/constants/providers.ts` — do not edit by hand.
+> Regenerate with: `npm run gen:provider-reference`
+> **Last generated:** 2026-08-21
+
+Total providers: **349**. See category breakdown below.
+
+## Categories
+
+- **Free** — free tier with API key (configured via dashboard)
+- **No-auth** — public endpoints that require no key or sign-in at all
+- **OAuth** — sign-in flow handled by OmniRoute, no API key needed
+- **Web cookie** — wraps the provider's web app via cookie auth
+- **API key** — paid provider configured via API key (free credits may apply)
+- **Local** — runs on the user's machine (Ollama, LM Studio, vLLM, etc.)
+- **Search** — web search providers
+- **Audio** — audio-only providers (TTS/STT)
+- **Upstream proxy** — providers that proxy to other providers
+- **Cloud agent** — long-running coding agents (Codex Cloud, Devin, Jules)
+- **System** — OmniRoute-internal providers (loopback, etc.)
+
+Additional tags: `image`, `video`, `aggregator`, `enterprise`, `embed/rerank`, `self-hosted`.
+
+`Tool calling` (where shown): `native` — real function-calling API; `emulated` — the `tools` array is prompt-emulated via `webTools.ts` (regex-parsed `<tool>{...}</tool>` blocks); `none` — `tools` is currently silently dropped. See #7286.
+
+Use the dashboard at `/dashboard/providers` to enable, configure, and test each provider.
+
+---
+
+## No-auth Providers (no key required) (11)
+
+| ID | Alias | Name | Tags | Website | Notes | Tool calling |
+|----|-------|------|------|---------|-------|--------------|
+| `aihorde` | `horde` | AI Horde | No-auth | [link](https://aihorde.net) | No API key required — uses AI Horde's documented anonymous key. Adding a free aihorde.net key is optional and only buys higher queue priority (kudos). | — |
+| `auggie` | `aug` | Augment (Auggie CLI) | No-auth | [link](https://augmentcode.com) | No API key stored by OmniRoute. Install the Auggie CLI and run `auggie login` on this machine, then OmniRoute spawns it locally for each request. | — |
+| `chipotle` | `pepper` | Chipotle Pepper AI (Free) | No-auth | [link](https://amelia.chipotle.com) | No credentials required. Uses Chipotle's public support chatbot via reverse-engineered SockJS/STOMP protocol. | — |
+| `cloudflare-playground` | `cfp` | Cloudflare AI Playground | No-auth | [link](https://playground.ai.cloudflare.com) | No credentials required — anonymous browser sessions over a reverse-engineered cf_agent WebSocket protocol (Playwright transport). | — |
+| `devin-cli-agentic` | `dva` | Devin CLI Agentic Bridge | No-auth | [link](https://docs.devin.ai/work-with-devin/devin-cli) | Authentication is owned by the official Devin CLI in its isolated bridge volume. | emulated |
+| `duckduckgo-web` | `ddgw` | DuckDuckGo AI Chat | No-auth | [link](https://duckduckgo.com/duckchat) | No credentials required — DuckDuckGo AI Chat is anonymous and free. | emulated |
+| `felo-web` | `felo` | Felo | No-auth | [link](https://felo.ai) | No credentials required — Felo is a free, no-signup chat/search aggregator. | — |
+| `opencode` | `oc` | OpenCode Free | No-auth | [link](https://opencode.ai) | No API key required — uses OpenCode's public free endpoint. | — |
+| `theoldllm` | `tllm` | The Old LLM (Free) | No-auth | [link](https://theoldllm.vercel.app) | No credentials required. The executor auto-generates access tokens via an embedded Playwright browser instance. | — |
+| `veoaifree-web` | `veo-free` | Veo AI Free | No-auth, video | [link](https://veoaifree.com) | No auth required. Rate limited to 6 requests/hour per IP. | — |
+| `zcode` | `zc` | ZCode (GLM Coding Plan) | No-auth | [link](https://zcode.z.ai) | No API key stored by OmniRoute. The local ZCode app-server uses the existing builtin:zai-coding-plan login. | — |
+
+## OAuth Providers (25)
+
+| ID | Alias | Name | Tags | Website | Notes |
+|----|-------|------|------|---------|-------|
+| `agy` | `agy` | Antigravity CLI | OAuth | [link](https://antigravity.google) | Import your Antigravity CLI (`agy`) login (paste/upload its token file), auto-detect a local CLI login, or sign in with Google. Shares the Antigravity backend (incl. Claude models). |
+| `amazon-q` | `aq` | Amazon Q | OAuth | [link](https://aws.amazon.com/q/developer/) | Uses the same AWS Builder ID or imported refresh-token flow as Kiro, but keeps Amazon Q connections separate. |
+| `antigravity` | — | Antigravity | OAuth | — | — |
+| `claude` | `cc` | Claude Code | OAuth | — | — |
+| `cline` | `cl` | Cline | OAuth | — | — |
+| `clinepass` | `cp` | ClinePass | OAuth | [link](https://cline.bot/cline-pass) | ClinePass is Cline's $9.99/mo subscription bundling 10 open coding models. Sign in with your Cline account (same login as the Cline CLI/IDE), or paste a direct ClinePass API key (app.cline.bot → Settings → API Keys). A ClinePass subscription unlocks the cline-pass/* models. Reuses the Cline WorkOS OAuth flow. |
+| `codebuddy-cn` | `cbcn` | CodeBuddy CN | OAuth | [link](https://copilot.tencent.com) | Tencent CodeBuddy CN (copilot.tencent.com). Sign in via the official CLI device-code flow, or paste a direct API key (sent as Authorization: Bearer). Catalog: GLM / Kimi / MiniMax / DeepSeek / Hunyuan. |
+| `codex` | `cx` | OpenAI Codex | OAuth | — | — |
+| `cursor` | `cu` | Cursor IDE | OAuth | — | — |
+| `devin-cli` | `dv` | Devin CLI | OAuth | [link](https://cli.devin.ai) | Requires the Devin CLI binary. Run `devin auth login` to authenticate, or provide your WINDSURF_API_KEY. Install: https://cli.devin.ai |
+| `devin-desktop` | — | Devin Desktop | OAuth | [link](https://devin.ai) | Paste an existing Devin API key from an authenticated Devin session. Key export availability and steps vary by Devin version and account. |
+| `ghe-copilot` | `ghe-copilot` | GitHub Enterprise Copilot | OAuth | — | Enter your GHE instance URL (e.g., https://ghe.company.com) in provider settings, then authenticate via device flow. |
+| `github` | `gh` | GitHub Copilot | OAuth | — | — |
+| `gitlab-duo` | `gitlab-duo` | GitLab Duo | OAuth | [link](https://docs.gitlab.com/user/duo_agent_platform/code_suggestions/) | GitLab Duo OAuth is not configured. Register an OAuth application at https://gitlab.com/-/profile/applications with redirect URI http://localhost:20128/callback and scopes "ai_features read_user", then set GITLAB_DUO_OAUTH_CLIENT_ID (and optionally GITLAB_DUO_OAUTH_CLIENT_SECRET) and restart. |
+| `grok-cli` | `gc` | Grok Build | OAuth | — | Sign in with your browser, or paste your ~/.grok/auth.json (or the JWT access token) from the Grok Build CLI; refresh_token is rotated automatically either way. |
+| `kilocode` | `kc` | Kilo Code | OAuth | — | — |
+| `kimi-coding` | `kmc` | Kimi Code CLI | OAuth | [link](https://www.kimi.com/code?aff=omniroute) | Sign in with the same Kimi account used by Kimi Code CLI. OmniRoute uses the CLI OAuth flow and Kimi Coding Plan endpoints. |
+| `kiro` | `kr` | Kiro AI | OAuth | — | Free tier: 50 credits/month (~25K–100K tokens). ⚠️ Kiro ToS prohibits third-party proxy/harness use. |
+| `openference` | `of` | Openference | OAuth | [link](https://openference.com) | Sign in with your Openference account to route requests through api.openference.com. An active plan is required for inference — OAuth may authenticate but return 402 without one. |
+| `qoder` | `if` | Qoder | OAuth | — | — |
+| `raycast` | `rc` | Raycast Pro AI | OAuth | [link](https://raycast.com/ai) | Unofficial integration — uses your Raycast Pro subscription via credentials from the macOS app (Auto-Import or manual capture). May break on Raycast updates. Not for redistribution; personal use only. |
+| `trae` | `tr` | Trae | OAuth | [link](https://trae.ai) | Trae is an AI-native IDE by ByteDance (SOLO remote agent). Authorize via trae.ai in the popup, or sign in at solo.trae.ai and paste the Cloud-IDE-JWT (sent as 'Authorization: Cloud-IDE-JWT <token>', ~14-day lifetime) as the access token; web_id/biz_user_id/user_unique_id/scope/tenant/region propagate via providerSpecificData. No headless refresh for pasted tokens — re-paste on expiry. |
+| `xai-oauth` | `xao` | xAI OAuth (Grok) | OAuth | [link](https://x.ai) | Sign in with xAI to use api.x.ai models such as Grok 4.5. This is separate from Grok Build JWT sessions, which use cli-chat-proxy.grok.com and grok-build model aliases. |
+| `zed` | `zd` | Zed IDE | OAuth | [link](https://zed.dev) | Zed stores LLM provider credentials (OpenAI, Anthropic, Google, Mistral, xAI) in the OS keychain. Use the Import button below to discover and import them automatically. |
+| `zed-hosted` | — | Zed Hosted Models | OAuth | [link](https://zed.dev) | Sign in with your Zed account (native-app sign-in). OmniRoute generates a one-time RSA keypair and opens zed.dev to authorize it — on a remote/headless install, copy the resulting 127.0.0.1 callback URL from your browser's address bar and paste it back here. Distinct from the 'Zed IDE' credential-import entry above: this proxies chat completions through Zed's own hosted model aggregator (cloud.zed.dev), fronting Anthropic/OpenAI/Google/xAI models under your Zed plan. |
+
+## Web Cookie Providers (35)
+
+| ID | Alias | Name | Tags | Website | Notes | Tool calling |
+|----|-------|------|------|---------|-------|--------------|
+| `adapta-web` | `adp-web` | Adapta.org (Adapta One Web) | Web cookie | [link](https://agent.adapta.one) | Paste your __client cookie value from .clerk.agent.adapta.one (DevTools → Application → Cookies) | emulated |
+| `adobe-firefly` | `firefly` | Adobe Firefly (Image/Video) | Web cookie | [link](https://firefly.adobe.com) | RECOMMENDED: firefly.adobe.com signed-in → F12 → Network → click firefly-3p.ff.adobe.io (generate-async or models/discovery) → Request Headers → Authorization → copy the token AFTER 'Bearer ' (starts with eyJ…). Cookie-only from firefly.adobe.com mints a GUEST token → 401/403; only multi-domain IMS cookies (adobelogin.com) or that Bearer JWT work. Unofficial/experimental media + Limits. | — |
+| `blackbox-web` | `bb-web` | Blackbox Web (Subscription) | Web cookie | [link](https://app.blackbox.ai) | Paste your __Secure-authjs.session-token value or full cookie header from app.blackbox.ai | emulated |
+| `chatgpt-web` | `cgpt-web` | ChatGPT Web (Plus/Pro) | Web cookie | [link](https://chatgpt.com) | Paste your __Secure-next-auth.session-token cookie value from chatgpt.com | emulated |
+| `chatgpt-web-codex` | `cgpt-codex` | ChatGPT Web (Codex) | Web cookie | [link](https://chatgpt.com) | Paste the full ChatGPT Cookie header. OmniRoute verifies it in an isolated headless browser profile. | native |
+| `claude-web` | `cw` | Claude Web | Web cookie | [link](https://claude.ai) | Paste your session cookie from claude.ai | none |
+| `conol-web` | `cnl` | Conol (Unofficial/Experimental) | Web cookie | [link](https://conol.ai) | Use browser sign-in, or paste the full Cookie header from conol.ai. The __Secure-better-auth.session_token cookie is required. | — |
+| `copilot-m365-web` | `m365copilot` | Microsoft 365 Copilot (BizChat) | Web cookie | [link](https://m365.cloud.microsoft/chat) | Sign in at m365.cloud.microsoft/chat, then open DevTools → Network → filter 'WS' → click the Chathub WebSocket connection. Copy both the access_token query parameter AND the account-specific Chathub path segment from its request URL (wss://…/Chathub/<path>?…&access_token=…). It is NOT an Authorization: Bearer header on an XHR/Fetch request. The token is short-lived; this is an unofficial integration. Optional: store a refresh_token in providerSpecificData.refreshToken (any Microsoft device-code/refresh flow for the substrate.office.com/sydney scopes) and OmniRoute pre-flight-refreshes the access token itself — otherwise re-capture after every ~75 min expiry. | — |
+| `copilot-web` | `copilot` | Microsoft Copilot Web | Web cookie | [link](https://copilot.microsoft.com) | Paste the access_token from an authenticated copilot.microsoft.com request (DevTools → Network → Authorization), or export a HAR while logged in | — |
+| `deepseek-web` | `ds-web` | DeepSeek Web | Web cookie | [link](https://chat.deepseek.com) | Paste your userToken from chat.deepseek.com — DevTools → Application → Local Storage → userToken | emulated |
+| `doubao-web` | `db` | Dola Web (ByteDance) | Web cookie | [link](https://www.dola.com) | Paste the full Cookie header from www.dola.com. It should include sessionid, ttwid, and s_v_web_id. If s_v_web_id is unavailable, fp=verify_... from a chat/completion request URL can be used as a fallback. | — |
+| `gemini-business` | `gembiz` | Gemini Business (Enterprise) | Web cookie | [link](https://business.gemini.google) | From your enterprise account: open business.gemini.google/home/cid/{your-cid}, then copy __Secure-1PSID and __Secure-1PSIDTS cookies from DevTools → Application → Cookies. Paste as a cookie header below. | — |
+| `gemini-web` | `gweb` | Gemini Web (Free) | Web cookie | [link](https://gemini.google.com) | Paste your __Secure-1PSID cookie value from gemini.google.com. Optionally add __Secure-1PSIDTS separated by semicolon. | emulated |
+| `grok-web` | `gw` | Grok Web (Subscription) | Web cookie | [link](https://grok.com) | Paste the full grok.com cookie line from DevTools → Application → Cookies. Include both `sso` and `sso-rw` (e.g. `sso=...; sso-rw=...`) — Grok's anti-bot rejects `sso` on its own. | — |
+| `hailuo-web` | `hailuo-web` | Hailuo Web (MiniMax) | Web cookie | [link](https://hailuo.ai) | Open hailuo.ai, log in, then open DevTools → Application → Local Storage → copy the "_token" value. device_id/uuid fingerprint fields are derived automatically; if requests fail, re-capture _token (sessions can expire). | — |
+| `huggingchat` | `huggingchat` | HuggingChat (Free) | Web cookie | [link](https://huggingface.co/chat) | Paste the full Cookie header from huggingface.co/chat (DevTools → Network → /chat/conversation → Request Headers → Cookie). It should include hf-chat and may also include token / aws-waf-token. | — |
+| `hyperagent` | `ha` | HyperAgent (Unofficial/Experimental) | Web cookie | [link](https://hyperagent.com) | Paste the full Cookie header from hyperagent.com (DevTools → Network → any request → Request Headers → Cookie). Session cookies power chat + billing usage. | — |
+| `inner-ai` | `in-ai` | Inner.ai (Subscription) | Web cookie | [link](https://app.innerai.com) | Paste your token cookie and email separated by a space: open DevTools → Application → Cookies → .innerai.com, copy the token value, then append a space and your Inner.ai login email. Example: eyJhbG... user@example.com | emulated |
+| `kimi-web` | `kimi-web` | Kimi Web | Web cookie | [link](https://www.kimi.com/code?aff=omniroute) | Paste access_token from www.kimi.com DevTools → Application → Local Storage. A legacy kimi-auth cookie is also accepted. | — |
+| `lmarena` | `lma` | Arena (Free) | Web cookie | [link](https://arena.ai) | Paste the full Cookie header from arena.ai (DevTools → Network → request → Cookie). Include arena-auth-prod-v1.0/.1… and cf_clearance/__cf_bm when present. OmniRoute uses Chrome TLS impersonation; if Arena still 403s, set providerSpecificData.recaptchaV3Token from a live browser session. | — |
+| `microsoft-designer-web` | `msdesigner` | Microsoft Designer (Image Generation) | Web cookie | [link](https://designer.microsoft.com) | Sign in at designer.microsoft.com, then open DevTools → Network, generate an image, and find the request to DallE.ashx?action=GetDallEImagesCogSci. Copy the value of its Authorization: Bearer header (the access_token — no 'Bearer ' prefix). The token is short-lived; this is an unofficial, reverse-engineered integration. | — |
+| `muse-spark-web` | `ms-web` | Muse Spark Web (Meta AI) | Web cookie | [link](https://www.meta.ai) | Paste your ecto_1_sess cookie AND the ecto1:... WS auth token from meta.ai. Capture the ecto1: token in DevTools → Network → WS → the clippy request's Authorization query param. Example: ecto_1_sess=4240a308...NVDg0; ecto1:ABCD... | emulated |
+| `notion-web` | `nw` | Notion AI Web (Unofficial/Experimental) | Web cookie | [link](https://www.notion.so) | Paste only the token_v2 cookie VALUE from app.notion.com (DevTools → Application → Cookies → token_v2). Do not paste token_v2= or the full Cookie header. Workspace is auto-detected; space_id / notion_user_id are optional. | — |
+| `perplexity-web` | `pplx-web` | Perplexity Web (Pro/Max) | Web cookie | [link](https://www.perplexity.ai) | Paste your __Secure-next-auth.session-token cookie value from perplexity.ai | emulated |
+| `poe-web` | `poe` | Poe Web (Subscription) | Web cookie | [link](https://poe.com) | Paste your p-b cookie value from poe.com (DevTools → Application → Cookies → p-b) | — |
+| `promptql` | `pql` | PromptQL (Unofficial/Experimental) | Web cookie | [link](https://prompt.ql.app) | Paste the Bearer JWT from prompt.ql.app DevTools → Network → graphql → Authorization (token only). Optional projectId + session Cookie for refresh. | — |
+| `qwen-web` | `qwen-web` | Qwen Web (Free) | Web cookie | [link](https://chat.qwen.ai) | Open chat.qwen.ai, log in, then open DevTools → Application → Local Storage → copy the "token" value (or use tongyi_sso_ticket cookie as Bearer token). | emulated |
+| `t3-web` | `t3chat` | t3.chat (Pro/Free) | Web cookie | [link](https://t3.chat) | Open t3.chat in your browser, log in, then open DevTools → Application → Local Storage → https://t3.chat. Copy the value of 'convex-session-id'. Also open DevTools → Network, copy the Cookie header from any request. Paste both values here. See provider setup docs for a step-by-step guide. | emulated |
+| `tencent-aistudio-web` | `tasw` | Tencent AI Studio (Free) | Web cookie | [link](https://aistudio.tencent.ai) | Log in to aistudio.tencent.ai, open DevTools -> Network, copy any request Cookie header containing session tokens. | — |
+| `tinycms-web` | `tcw` | TinyCMS Web (Free/Sub) | Web cookie | [link](https://site.tinycms.xyz) | Go to site.tinycms.xyz, open DevTools → Application → Local Storage, copy the value of 'app-config-uuid' (starts with 'R'), and paste it here. | — |
+| `v0-vercel-web` | `v0-vercel-web` | v0 Vercel Web (Code Gen) | Web cookie | [link](https://v0.dev) | Paste your session cookie from v0.dev (DevTools → Application → Cookies) | — |
+| `venice-web` | `ven` | Venice Web (Privacy) | Web cookie | [link](https://venice.ai) | Paste your session cookie from venice.ai (DevTools → Application → Cookies) | — |
+| `yuanbao-web` | `ybw` | Tencent Yuanbao (Free) | Web cookie | [link](https://yuanbao.tencent.com) | Log in to yuanbao.tencent.com, then paste the full Cookie header (DevTools → Network → any /api request → Request Headers → Cookie). It must contain hy_user and hy_token. | — |
+| `zai-web` | `zw` | Z.ai Web | Web cookie | [link](https://chat.z.ai) | Copy the "token" value from chat.z.ai → DevTools → Application → Local Storage. Do not copy cookies; OmniRoute handles the per-request CAPTCHA through its browser transport. | — |
+| `zenmux-free` | `zmf` | ZenMux Free (Web) | Web cookie | [link](https://zenmux.ai) | Login at zenmux.ai, then export all cookies using EditThisCookie or Cookie-Editor and paste the full Cookie header string here. Refresh every ~30 days. | — |
+
+## API Key Providers (paid / paid-with-free-credits) (233)
+
+| ID | Alias | Name | Tags | Website | Notes |
+|----|-------|------|------|---------|-------|
+| `360ai` | `360ai` | 360 AI | API key | [link](https://ai.360.cn) | Get API key at ai.360.cn |
+| `agentrouter` | `agentrouter` | AgentRouter | API key, aggregator | [link](https://agentrouter.org) | $200 free credits on signup - multi-model routing gateway |
+| `agnes` | `agnes` | Agnes AI | API key, video | [link](https://agnes-ai.com) | Get API key at agnes-ai.com |
+| `ai21` | `ai21` | AI21 Labs | API key | [link](https://www.ai21.com) | $10 trial credits on signup (valid 3 months), no credit card required |
+| `aimlapi` | `aiml` | AI/ML API | API key, aggregator | [link](https://aimlapi.com) | Free tier paused (2026) — AI/ML API is now pay-as-you-go only (min $20 top-up); no recurring free credits. |
+| `ainative` | `ainative` | AINative Studio | API key | [link](https://ainative.studio) | Create a free API key at ainative.studio (no card), then paste it here as a Bearer token. |
+| `aion` | `aion` | Aion Labs | API key | [link](https://www.aionlabs.ai) | Create a free API key at aionlabs.ai (no card), then paste it here as a Bearer token. |
+| `alibaba` | `ali` | Alibaba Cloud Model Studio | API key | [link](https://bailian.console.alibabacloud.com/) | — |
+| `alibaba-cn` | `ali-cn` | Alibaba (China) | API key | [link](https://dashscope.console.aliyun.com/) | — |
+| `ant-ling` | `ling` | Ant Ling / Ring (inclusionAI) | API key | [link](https://developer.ant-ling.com/en/docs/) | Register and create an API key at the Ant Ling API console (https://chat.ant-ling.com/open), then paste it here. OmniRoute routes chat traffic to https://api.ant-ling.com/v1/chat/completions; the provider is OpenAI-compatible and also exposes an Anthropic-compatible surface. |
+| `anthropic` | `anthropic` | Anthropic | API key | [link](https://platform.claude.com) | — |
+| `anyapi` | `anyapi` | AnyAPI AI | API key, aggregator | [link](https://anyapi.ai) | Free plan: 100,000 ANY Tokens/day and 100 RPM for eligible Free/Basic models; no credit card required. |
+| `api-airforce` | `af` | Api.airforce | API key | [link](https://api.airforce) | 55 free tier models including Grok-3, Claude 3.7, Qwen3, Kimi-K2, Gemini 2.5 Flash, DeepSeek-V3 |
+| `arcee-ai` | `arcee` | Arcee AI | API key | [link](https://arcee.ai) | Get API key at arcee.ai |
+| `auriko` | `auriko` | Auriko | API key, aggregator | [link](https://www.auriko.ai) | Free plan publishes 1,000 Platform RPM and 10,000 BYOK RPM. Platform inference still passes through provider cost; this is not a free-token pool or unlimited free inference. |
+| `azure-ai` | `azure-ai` | Azure AI Foundry | API key, enterprise | [link](https://learn.microsoft.com/azure/ai-foundry) | Use your Azure AI Foundry key. Base URL can be https://<resource>.services.ai.azure.com/openai/v1/ or https://<resource>.openai.azure.com/openai/v1/. |
+| `azure-openai` | `azure` | Azure OpenAI | API key, enterprise | [link](https://azure.microsoft.com/products/ai-services/openai-service) | Use your Azure OpenAI API key. Base URL should be your resource endpoint, for example https://my-resource.openai.azure.com. |
+| `bai` | `bai` | b.ai | API key | [link](https://b.ai) | Bearer API key for the b.ai OpenAI-compatible LLM gateway (distinct from TheB.AI). Create a key at https://docs.b.ai, then use https://api.b.ai/v1 as the OpenAI-compatible base URL. |
+| `baichuan` | `baichuan` | Baichuan | API key | [link](https://www.baichuan-ai.com/) | Get API key at platform.baichuan-ai.com |
+| `baidu` | `baidu` | Baidu (ERNIE) | API key | [link](https://ernie.baidu.com/) | Get API key at console.bce.baidu.com |
+| `bailian-coding-plan` | `bcp` | Alibaba Token Plan | API key | [link](https://www.alibabacloud.com/help/en/model-studio/token-plan-overview) | — |
+| `baseten` | `baseten` | Baseten | API key | [link](https://baseten.co) | $30 free trial credits for GPU inference |
+| `bazaarlink` | `bzl` | BazaarLink | API key | [link](https://bazaarlink.ai) | Use your BazaarLink API key (starts with sk-bl-) in Authorization: Bearer <key>. OpenAI SDK works with base URL https://bazaarlink.ai/api/v1. Models use provider/model-name format. |
+| `bedrock` | `bedrock` | Amazon Bedrock | API key, enterprise | [link](https://aws.amazon.com/bedrock) | Use your Amazon Bedrock API key and configure the AWS region where your models are enabled (for example eu-west-2). OmniRoute calls Bedrock's native Converse API directly. |
+| `black-forest-labs` | `bfl` | Black Forest Labs | API key, image | [link](https://blackforestlabs.ai) | — |
+| `blackbox` | `bb` | Blackbox AI | API key | [link](https://blackbox.ai) | Limited free access is available through Blackbox; model availability and account limits apply |
+| `bluesminds` | `bm` | BluesMinds | API key | [link](https://www.bluesminds.com) | Free daily pi credits — supports 200+ models including GPT-4o, GPT-4.1, Claude Sonnet 4.5, Gemini 2.0 Flash, DeepSeek V4, Qwen, Kimi K2 |
+| `byteplus` | `bpm` | BytePlus ModelArk | API key | [link](https://console.byteplus.com/ark) | — |
+| `bytez` | `bytez` | Bytez | API key | [link](https://bytez.com) | $1 free credits, refreshes every 4 weeks |
+| `cerebras` | `cerebras` | Cerebras | API key | [link](https://inference.cerebras.ai) | Free Trial: 1M tokens/day, 30K TPM, 5 RPM — no credit card. |
+| `charm-hyper` | `charm-hyper` | Charm Hyper | API key | [link](https://hyper.charm.land) | 100 free monthly Hypercredits on signup |
+| `chat-oripe` | `chat-oripe` | Chat Oripe | API key, aggregator | [link](https://api.oriper.com) | Official metadata advertises 2M tokens/month, but the public site and documentation were blocked during audit; treat the quota and brand mapping as unconfirmed. |
+| `chatanywhere` | `chatanywhere` | ChatAnywhere | API key, aggregator | [link](https://chatanywhere.tech) | Personal, educational or research use only: public documentation cites 10,000 points/day and 200 requests/day per IP/key; do not use for commercial traffic. |
+| `cheaperinference` | `cinf` | Cheaper Inference | API key | [link](https://cheaperinference.com/?utm_source=omniroute) | — |
+| `chenzk` | `chenzk` | Chenzk API | API key | [link](https://chenzk.top) | — |
+| `chutes` | `chutes` | Chutes.ai | API key, aggregator | [link](https://chutes.ai) | Bearer API key for the Chutes OpenAI-compatible gateway. |
+| `clarifai` | `clarifai` | Clarifai | API key, enterprise | [link](https://docs.clarifai.com) | Use your Clarifai PAT or app-specific API key. OmniRoute targets the OpenAI-compatible endpoint at https://api.clarifai.com/v2/ext/openai/v1 and authenticates with Authorization: Key <token>. |
+| `cloudcode-one` | `cloudcode-one` | CloudCode.ONE | API key, aggregator | [link](https://cloudcode.one) | Published free models include glm-4.7-flash and glm-4.6v-flash; no numeric quota is published, and key creation may require credit or a coupon. |
+| `cloudflare-ai` | `cf` | Cloudflare Workers AI | API key | [link](https://developers.cloudflare.com/workers-ai) | Requires API Token AND Account ID (found at dash.cloudflare.com) |
+| `clova-studio` | `clova` | Naver CLOVA Studio | API key | [link](https://api.ncloud-docs.com/docs/en/ai-naver-clovastudio-summary) | — |
+| `codestral` | `codestral` | Codestral | API key | [link](https://mistral.ai) | — |
+| `cohere` | `cohere` | Cohere | API key | [link](https://cohere.com) | Free Trial: 1,000 API calls/month for testing, no credit card required |
+| `command-code` | `cmd` | Command Code | API key | [link](https://commandcode.ai/) | Use a Command Code API key. Requests are sent to Command Code's /alpha/generate endpoint. |
+| `coze` | `coze` | Coze | API key | [link](https://coze.com) | Get API key at coze.com/open/api |
+| `crof` | `crof` | CrofAI | API key | [link](https://crof.ai) | — |
+| `cursor-api` | `cua` | Cursor API | API key | [link](https://cursor.com/dashboard/api) | Paste a Cursor user API key (crsr_...) from cursor.com/dashboard/api. OmniRoute exchanges it for a session token on demand; no IDE or cursor-agent install is needed. Usage bills to the Cursor plan that owns the key. |
+| `dahl` | `dahl` | Dahl | API key | [link](https://inference.dahl.global) | Click 'Add Account' to auto-generate a token, or add a manual API key. |
+| `databricks` | `databricks` | Databricks | API key, enterprise | [link](https://www.databricks.com) | — |
+| `datarobot` | `datarobot` | DataRobot | API key, enterprise | [link](https://docs.datarobot.com) | Use your DataRobot API token. Optional Base URL can be the account root (for LLM Gateway) or a deployment URL under /api/v2/deployments/<id>. |
+| `deepai` | `deepai` | DeepAI | API key, image | [link](https://deepai.org) | Use your DeepAI API key. Get one at deepai.org — requires a Pro subscription ($9.99/mo). |
+| `deepinfra` | `deepinfra` | DeepInfra | API key | [link](https://deepinfra.com) | Free signup credits for API testing and model exploration |
+| `deepseek` | `ds` | DeepSeek | API key | [link](https://platform.deepseek.com) | 5M free tokens on signup - no credit card required |
+| `dgrid` | `dgrid` | DGrid | API key | [link](https://dgrid.ai) | DGrid Free Models Router: 10 requests/minute and 100 requests/day. A $5 lifetime top-up unlocks up to 20 requests/minute and 1,000 requests/day. |
+| `dify` | `dify` | Dify | API key | [link](https://dify.ai) | Get API key from your Dify instance. |
+| `digitalocean` | `digitalocean` | DigitalOcean | API key | [link](https://docs.digitalocean.com/products/ai-platform/) | — |
+| `dit` | `dai` | DIT.ai | API key | [link](https://dit.ai) | Use your dit.ai API key in Authorization: Bearer <key>. Fully OpenAI-compatible — a drop-in replacement, just change the base URL to https://api.dit.ai/v1. |
+| `doubao` | `doubao` | Doubao | API key | [link](https://doubao.com) | Get API key at console.volcengine.com |
+| `dxnt` | `dxnt` | DXNT / DX Token | API key, aggregator | [link](https://www.dxnt.com) | Free accounts are documented at 100 calls/day; the quota may increase through invitations and can vary by account. |
+| `electronhub` | `electronhub` | Electron Hub | API key, aggregator | [link](https://www.electronhub.ai) | Free plan: 5 RPM, $0.25 weekly credits and 10 Neutrinos/day for :free models; family budgets also apply. |
+| `empower` | `empower` | Empower | API key, aggregator | [link](https://docs.empower.dev) | Bearer API key for the Empower OpenAI-compatible endpoint. |
+| `factory` | `factory` | Factory | API key | [link](https://factory.ai) | Bearer API key for the Factory OpenAI-compatible gateway. |
+| `fal-ai` | `fal` | Fal.ai | API key, image | [link](https://fal.ai) | — |
+| `fastrouter` | `fastrouter` | FastRouter | API key, aggregator | [link](https://fastrouter.ai) | Models with the :free suffix allow 10 requests/day per organization and model; availability may change. |
+| `featherless-ai` | `featherless` | Featherless AI | API key | [link](https://featherless.ai) | Free tier available — no credit card required |
+| `fenayai` | `fenayai` | FenayAI | API key, aggregator | [link](https://fenayai.com) | Bearer API key for the FenayAI OpenAI-compatible gateway. |
+| `fireworks` | `fireworks` | Fireworks AI | API key | [link](https://fireworks.ai) | $1 free starter credits on signup for API testing |
+| `free-ai` | `free-ai` | Free.ai | API key, aggregator | [link](https://free.ai) | 30,000 tokens/day cover self-hosted models after email verification. Usage beyond the pool can bill at raw cost, and premium external models are paid. |
+| `freeaiapikey` | `faik` | FreeAIAPIKey | API key | [link](https://freeaiapikey.com) | — |
+| `freebuff` | `freebuff` | Freebuff | API key | [link](https://freebuff.com) | Enter Freebuff / Codebuff Auth Token (obtained via CLI login or automated harvester). |
+| `freeinference` | `freeinference` | FreeInference | API key, aggregator | [link](https://freeinference.org) | Free research access without a card; non-Harvard applicants require manual approval and no numeric quota is publicly guaranteed. |
+| `freemodel-dev` | `fmd` | FreeModel.dev | API key | [link](https://freemodel.dev) | $300 free credits on signup — no credit card required. Access GPT-5.4 and GPT-5.5 (OpenAI's latest flagship models) through an OpenAI-compatible API. |
+| `freetheai` | `fta` | FreeTheAi | API key, aggregator | [link](https://freetheai.xyz) | Join the FreeTheAi Discord to get your free API key. |
+| `friendliai` | `friendli` | FriendliAI | API key | [link](https://friendli.ai) | Free tier for serverless inference — no credit card required |
+| `g4f-gemini` | `g4fgem` | g4f.space — Gemini | API key, aggregator | [link](https://g4f.space) | No auth required. Free tier is limited to 5 requests/minute — sign up at g4f.dev/members.html for higher limits. |
+| `g4f-groq` | `g4fgroq` | g4f.space — Groq | API key, aggregator | [link](https://g4f.space) | No auth required. Free tier is limited to 5 requests/minute — sign up at g4f.dev/members.html for higher limits. |
+| `g4f-nvidia` | `g4fnv` | g4f.space — NVIDIA | API key, aggregator | [link](https://g4f.space) | No auth required. Free tier is limited to 5 requests/minute — sign up at g4f.dev/members.html for higher limits. |
+| `g4f-ollama` | `g4foll` | g4f.space — Ollama | API key, aggregator | [link](https://g4f.space) | No auth required. Free tier is limited to 5 requests/minute — sign up at g4f.dev/members.html for higher limits. |
+| `g4f-pollinations` | `g4fpol` | g4f.space — Pollinations | API key, aggregator | [link](https://g4f.space) | No auth required. Free tier is limited to 5 requests/minute — sign up at g4f.dev/members.html for higher limits. |
+| `galadriel` | `galadriel` | Galadriel | API key | [link](https://galadriel.com) | ⚠️ **DEPRECATED.** api.galadriel.ai no longer resolves (sweep 2026-06-19); the inference API appears discontinued. |
+| `gemini` | `gemini` | Gemini (Google AI Studio) | API key | [link](https://aistudio.google.com) | Free tier available through Google AI Studio; current per-model quotas and regional limits apply |
+| `getgoapi` | `ggo` | GoAPI | API key, aggregator | [link](https://api.getgoapi.com) | — |
+| `gigachat` | `gigachat` | GigaChat (Sber) | API key | [link](https://developers.sber.ru) | — |
+| `gitlab` | `gitlab` | GitLab Duo PAT | API key | [link](https://docs.gitlab.com/user/duo_agent_platform/code_suggestions/) | GitLab personal access token for the public Code Suggestions API. Configure a self-hosted base URL when not using gitlab.com. |
+| `gitlawb` | `glb` | Gitlawb Opengateway (MiMo) | API key | [link](https://opengateway.gitlawb.com) | Free MiMo (xiaomi/mimo-v2.5) revoked 2026-05 — Opengateway is now a pay-as-you-go credit gateway; no recurring free model. |
+| `gitlawb-gmi` | `glb-gmi` | Gitlawb Opengateway (GMI Cloud) | API key | [link](https://opengateway.gitlawb.com) | Free Nemotron promo ended 2026-06 — the GMI Cloud route is now pay-as-you-go credit only. |
+| `glm` | `glm` | GLM Coding | API key | [link](https://z.ai/subscribe) | — |
+| `glm-cn` | `glmcn` | GLM Coding (China) | API key | [link](https://open.bigmodel.cn) | — |
+| `glmt` | `glmt` | GLM Thinking | API key | [link](https://open.bigmodel.cn) | — |
+| `groq` | `groq` | Groq | API key | [link](https://groq.com) | Free tier: 30 RPM / 14.4K RPD — no credit card |
+| `hackclub` | `hc` | Hackclub AI | API key, aggregator | [link](https://ai.hackclub.com) | Sign in with your Hack Club account at ai.hackclub.com. |
+| `haiper` | `hp` | Haiper | API key, video | [link](https://haiper.ai) | Get API key at haiper.ai/haiper-api |
+| `hcnsec` | `hcnsec` | Huancheng Public API | API key | [link](https://api.hcnsec.cn) | Get API key at api.hcnsec.cn |
+| `helixmind` | `helixmind` | HelixMind | API key, aggregator | [link](https://helixmind.online) | Previously circulated 3 RPM/50 RPD and no-card claims were not confirmed during the 2026-08-02 audit; current quota and billing require account verification. |
+| `helyxai` | `helyxai` | Helyx AI | API key, aggregator | [link](https://helyxai.space) | Operational Free plan documents 100,000 tokens/day; the site's separate 2M+ marketing claim conflicts and is not treated as a quota guarantee. |
+| `heroku` | `heroku` | Heroku AI | API key, enterprise | [link](https://www.heroku.com) | — |
+| `huggingface` | `hf` | HuggingFace | API key | [link](https://huggingface.co) | Free Inference API for thousands of models (Whisper, VITS, SDXL…) |
+| `hyperbolic` | `hyp` | Hyperbolic | API key | [link](https://hyperbolic.xyz) | $1-5 trial credits on signup for serverless inference |
+| `ideogram` | `ideo` | Ideogram | API key | [link](https://ideogram.ai) | Get API key at ideogram.ai/docs/api |
+| `iflytek` | `iflytek` | iFlytek Spark | API key | [link](https://xinghuo.xfyun.cn) | Get API key at console.xfyun.cn |
+| `inception` | `inception` | Inception | API key | [link](https://docs.inceptionlabs.ai) | 10M free tokens on signup, no credit card required. |
+| `inference-net` | `inet` | Inference.net | API key | [link](https://inference.net) | $25 free credits on signup plus research grants available |
+| `internlm` | `internlm` | InternLM (Intern-S1) | API key | [link](https://internlm.intern-ai.org.cn/) | Free monthly quota ~1M input / 3M output tokens (~10 RPM) |
+| `jina-ai` | `jina` | Jina AI (Foundation API) | API key, embed/rerank | [link](https://jina.ai) | Bearer API key for api.jina.ai — embeddings, rerank, classify, segment, and search. Dashboard keys take precedence over JINA_AI_API_KEY. This is not the Reader / r.jina.ai card and does not fetch URLs. |
+| `jina-reader` | `jr` | Jina Reader (r.jina.ai) | API key | [link](https://jina.ai/reader) | Bearer API key for r.jina.ai URL-to-markdown (/v1/web/fetch only). Does not serve /v1/embeddings or /v1/rerank. The same Jina token as Foundation API works; OmniRoute reuses a jina-ai dashboard key or JINA_AI_API_KEY when this card is empty. |
+| `kenari` | `kenari` | Kenari | API key | [link](https://kenari.id) | Use your Kenari API key (kn-...) in Authorization: Bearer <key>. Fully OpenAI-compatible. API base URL: https://kenari.id/v1. |
+| `kie` | `kie` | KIE.AI | API key | [link](https://kie.ai) | — |
+| `kilo-gateway` | `kg` | Kilo Gateway | API key, aggregator | [link](https://kilo.ai) | — |
+| `kimi` | `kimi` | Kimi (Legacy Moonshot API) | API key | [link](https://platform.kimi.ai?aff=omniroute) | — |
+| `kimi-coding-apikey` | `kmca` | Kimi Code API Key | API key | [link](https://www.kimi.com/code?aff=omniroute) | — |
+| `lambda-ai` | `lambda` | Lambda AI | API key | [link](https://lambda.ai) | — |
+| `laozhang` | `lz` | LaoZhang AI | API key, aggregator | [link](https://api.laozhang.ai) | — |
+| `leonardo` | `leo` | Leonardo AI | API key, video | [link](https://leonardo.ai) | Get API key at leonardo.ai/developer |
+| `liquid` | `liquid` | Liquid AI | API key | [link](https://liquid.ai) | Get API key at liquid.ai |
+| `literouter` | `literouter` | LiteRouter | API key, aggregator | [link](https://literouter.com) | Free model variants use the :free suffix; daily credit limits vary by model and free input is capped at 5,000 tokens. |
+| `llamagate` | `llamagate` | LlamaGate | API key | [link](https://llamagate.ai) | — |
+| `llm-kiwi` | `llmkiwi` | LLM.Kiwi | API key, aggregator | [link](https://llm.kiwi) | Free plan exposes auto and hrLLM; the published 40 requests/hour limit applies to hrLLM. |
+| `llm7` | `llm7` | LLM7.io | API key | [link](https://llm7.io) | Use any non-empty key (for example 'unused'). If older built-in models return model_unavailable, use Available Models → Import from /models or Auto-Sync; verified live model: gemini-3.1-flash-lite. |
+| `llmgateway` | `llmgateway` | LLM Gateway | API key, aggregator | [link](https://llmgateway.io) | Hosted Free plan: free-priced models are limited to 5 requests per 10 minutes when the account has no credits. |
+| `logfare` | `logfare` | Logfare | API key, aggregator | [link](https://logfare.ai) | Create a free account at https://logfare.ai/register (username/password, no email verification) to get an instant API key, then paste it here as a Bearer token. |
+| `longcat` | `lc` | LongCat AI | API key | [link](https://longcat.chat/platform/docs) | Free: one-time 10M-token grant after account signup + KYC verification (LongCat-2.0). One-time only — not a recurring daily/monthly allowance. |
+| `magnific` | `freepik` | Magnific | API key, image | [link](https://www.magnific.com) | Get an API key at magnific.com/user/api-keys (header x-magnific-api-key). Legacy Freepik developer keys still work. |
+| `maritalk` | `maritalk` | Maritalk | API key | [link](https://www.maritaca.ai) | — |
+| `meganova-ai` | `meganova-ai` | MegaNova AI | API key, aggregator | [link](https://meganova.ai) | Free signup without a card. Published Tier 1 per-model quotas total 550 requests/day; they are not a shared global pool, and paid overage can apply if enabled. |
+| `meta-llama` | `meta` | Meta Llama API | API key | [link](https://llama.developer.meta.com) | — |
+| `minimax` | `minimax` | Minimax Coding | API key, video | [link](https://www.minimax.io) | — |
+| `minimax-cn` | `minimax-cn` | Minimax (China) | API key | [link](https://www.minimaxi.com) | — |
+| `mistral` | `mistral` | Mistral | API key | [link](https://mistral.ai) | Free Experiment tier: rate-limited access to all models, no credit card required |
+| `mixedbread` | `mxbai` | Mixedbread AI | API key | [link](https://www.mixedbread.com) | Bearer API key for the Mixedbread embeddings API. |
+| `mixlayer` | `mixlayer` | Mixlayer | API key, aggregator | [link](https://www.mixlayer.com) | The qwen/qwen3.5-4b-free model is free for prototyping and rate-limited; no fixed public RPM or daily quota is confirmed. |
+| `mnn-ai` | `mnn-ai` | MNN AI | API key, aggregator | [link](https://mnnai.ru) | Free plan: $1 monthly credits, 10 RPM and access only to models marked Free. |
+| `modal` | `mdl` | Modal | API key, enterprise | [link](https://modal.com/docs) | Use the bearer token that protects your Modal deployment, if enabled. Base URL should point to your OpenAI-compatible Modal app, for example https://<workspace>--<app>.modal.run/v1. |
+| `modelscope` | `ms` | ModelScope | API key | [link](https://modelscope.cn) | Free tier via ModelScope API-Inference — Alibaba account required. |
+| `monsterapi` | `monster` | MonsterAPI | API key | [link](https://monsterapi.ai) | ⚠️ **DEPRECATED.** Monster API shuttered operations on 2026-06-30. Use alternative OpenAI-compatible providers. |
+| `moonshot` | `moonshot` | Kimi | API key | [link](https://platform.kimi.ai?aff=omniroute) | — |
+| `morph` | `morph` | Morph | API key | [link](https://morphllm.com) | Free tier: 250K credits/month, $0 |
+| `muse-code` | `mc` | Muse Code (Meta) | API key | [link](https://github.com/meta-llama/llama-stack) | Use your META_API_KEY env var as a Bearer token. Muse Code CLI uses the OpenAI Responses API wire format (POST /responses). |
+| `naga-ac` | `naga` | Naga.ac | API key, aggregator | [link](https://naga.ac) | Get API key at naga.ac — Google/GitHub/Discord signup available. |
+| `naga-ai` | `naga-ai` | Naga AI | API key, aggregator | [link](https://naga.ac) | Models marked :free are publicly listed, but no numeric quota is confirmed. Naga's policy warns that free-tier prompts and outputs may be collected or used for training. |
+| `nanogpt` | `nanogpt` | NanoGPT | API key | [link](https://nano-gpt.com) | — |
+| `nara` | `nara` | NaraRouter | API key | [link](https://bynara.id) | Get a free API key via NaraRouter's Telegram channel, then paste it here as a Bearer token. |
+| `navy` | `navy` | NavyAI | API key | [link](https://api.navy) | Create a free API key from the NavyAI dashboard, then paste it here as a Bearer token. |
+| `nebius` | `nebius` | Nebius AI | API key | [link](https://nebius.com) | ~$1 trial credits on signup for API testing |
+| `nlpcloud` | `nlpc` | NLP Cloud | API key | [link](https://docs.nlpcloud.com) | Use your NLP Cloud API key in Authorization: Token <key>. OmniRoute targets the chatbot endpoint on https://api.nlpcloud.io/v1/gpu/<model>/chatbot by default. |
+| `nomic` | `nomic` | Nomic | API key | [link](https://nomic.ai) | Get API key at atlas.nomic.ai |
+| `nous-research` | `nous` | Nous Research | API key | [link](https://portal.nousresearch.com/help) | Use your Nous Portal API key. OmniRoute targets the official OpenAI-compatible inference endpoint at https://inference-api.nousresearch.com/v1. |
+| `novita` | `novita` | Novita AI | API key, video, aggregator | [link](https://novita.ai) | $0.50 trial credits on signup (valid about 1 year) |
+| `nscale` | `nscale` | nScale | API key | [link](https://nscale.com) | $5 free credits on signup for inference testing |
+| `nube` | `nube` | Nube.sh | API key | [link](https://nube.sh) | — |
+| `nvidia` | `nvidia` | NVIDIA NIM | API key | [link](https://build.nvidia.com) | Free dev access: ~40 RPM, 70+ models (Kimi K2.5, GLM 4.7, DeepSeek V3.2...) |
+| `oci` | `oci` | OCI Generative AI | API key, enterprise | [link](https://www.oracle.com/artificial-intelligence/generative-ai) | Use your OCI Generative AI API key or IAM bearer token. Base URL can be https://inference.generativeai.<region>.oci.oraclecloud.com/openai/v1/. |
+| `ofoxai` | `ofoxai` | OfoxAI | API key, aggregator | [link](https://ofox.ai) | The current catalog advertises 10+ free models without a public numeric quota; review upstream provenance, retention and training terms before production use. |
+| `ollama-cloud` | `ollamacloud` | Ollama Cloud | API key | [link](https://ollama.com/settings/keys) | — |
+| `openadapter` | `oad` | OpenAdapter | API key | [link](https://openadapter.dev) | Use your OpenAdapter API key in Authorization: Bearer sk-cv-<key>. Fully OpenAI-compatible. API base URL: https://api.openadapter.in/v1. |
+| `openai` | `openai` | OpenAI | API key | [link](https://platform.openai.com) | — |
+| `opencode-go` | `opencode-go` | OpenCode Go | API key | [link](https://opencode.ai/go) | — |
+| `opencode-zen` | `opencode-zen` | OpenCode Zen | API key | [link](https://opencode.ai/zen) | — |
+| `openference-api` | `ofa` | Openference API | API key | [link](https://openference.com) | Free plan: 3-day trial with open-source models — no credit card required |
+| `openrouter` | `openrouter` | OpenRouter | API key, aggregator | [link](https://openrouter.ai) | Free models at $0/token with :free suffix - 20 RPM / 200 RPD |
+| `openvecta` | `openvecta` | OpenVecta | API key | [link](https://openvecta.com) | Free credits on signup for OpenAI-compatible inference across LLMs, embeddings, and reasoning models |
+| `orcarouter` | `orcarouter` | OrcaRouter | API key | [link](https://www.orcarouter.ai) | — |
+| `ovhcloud` | `ovh` | OVHcloud AI | API key | [link](https://www.ovhcloud.com) | — |
+| `perplexity` | `pplx` | Perplexity | API key | [link](https://www.perplexity.ai) | — |
+| `piapi` | `pi` | PiAPI | API key, aggregator | [link](https://piapi.ai) | — |
+| `pioneer` | `pn` | Pioneer AI | API key | [link](https://pioneer.ai) | $75 free usage credits — no credit card required |
+| `plamo` | `plamo` | PLaMo | API key | [link](https://plamo.preferredai.jp/api) | — |
+| `poe` | `poe` | Poe | API key, aggregator | [link](https://creator.poe.com/api-reference) | Bearer API key for the Poe OpenAI-compatible API. |
+| `poixe-ai` | `poixe-ai` | Poixe AI | API key, aggregator | [link](https://poixe.com) | Current public free limits are small and model-group specific: 2 RPM/5 RPD for large-cup models and 20 RPM/50 RPD for small-cup models. |
+| `pollinations` | `pol` | Pollinations AI | API key, video | [link](https://pollinations.ai) | Anonymous/keyless access to the documented free models is best-effort. Local v3.8.50 verification (2026-07-31) returned 401 via OmniRoute and Cloudflare 1010 on direct upstream probes from the same network. Premium models still require a Pollinations API key from enter.pollinations.ai. |
+| `poolside` | `poolside` | Poolside | API key | [link](https://poolside.ai) | Laguna S 2.1 and XS 2.1 are free during Preview; no public numeric quota is published. |
+| `predibase` | `predibase` | Predibase | API key | [link](https://predibase.com) | ⚠️ **DEPRECATED.** serving.app.predibase.com no longer resolves (sweep 2026-06-19); the managed serving API appears discontinued. |
+| `publicai` | `publicai` | PublicAI | API key | [link](https://publicai.co) | Requires an API key — one-time signup credit, then paid |
+| `qianfan` | `qianfan` | Baidu Qianfan | API key | [link](https://cloud.baidu.com/product-s/qianfan_home) | — |
+| `qiniu` | `qiniu` | Qiniu | API key | [link](https://www.qiniu.com) | — |
+| `qwen-cloud` | `qwc` | Qwen Cloud | API key | [link](https://www.qwencloud.com/) | — |
+| `qwen-cloud-token-plan` | `qct` | Qwen Cloud Token Plan | API key | [link](https://www.qwencloud.com/pricing/token-plan) | — |
+| `recraft` | `recraft` | Recraft | API key, image | [link](https://recraft.ai) | — |
+| `regolo` | `regolo` | Regolo AI | API key | [link](https://regolo.ai) | Get your Regolo API key from regolo.ai, then paste it here as a Bearer token. |
+| `reka` | `reka` | Reka | API key | [link](https://docs.reka.ai/chat/overview) | Use your Reka API key. OmniRoute supports the OpenAI-compatible base URL https://api.reka.ai/v1 and sends both Authorization and X-Api-Key headers for compatibility. |
+| `requesty` | `requesty` | Requesty | API key | [link](https://requesty.ai) | Free tier ~200 requests/day - multi-model routing gateway (300+ models) |
+| `routeway` | `routeway` | Routeway | API key | [link](https://routeway.ai) | Create a free API key at routeway.ai, then paste it here as a Bearer token. |
+| `runwayml` | `runway` | Runway | API key, video | [link](https://docs.dev.runwayml.com) | Use your Runway API key in Authorization: Bearer <key>. OmniRoute targets the current Runway API at https://api.dev.runwayml.com/v1 and sends the required X-Runway-Version header automatically. |
+| `sambanova` | `samba` | SambaNova | API key | [link](https://sambanova.ai) | $5 free credits on signup (30-day validity), no credit card required |
+| `sap` | `sap` | SAP Generative AI Hub | API key, enterprise | [link](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/generative-ai-hub-in-sap-ai-core) | Use your SAP AI Core bearer token. Base URL can be your AI_API_URL root or a deploymentUrl from Generative AI Hub. |
+| `sarvam` | `sarvam` | Sarvam AI | API key | [link](https://docs.sarvam.ai) | ₹1,000 in free signup credits — never expire |
+| `scaleway` | `scw` | Scaleway AI | API key | [link](https://www.scaleway.com/en/docs/ai-data/generative-apis/) | 1M free tokens for new accounts — EU/GDPR compliant (Paris), Qwen3 235B & Llama 70B |
+| `sealion` | `sealion` | SEA-LION | API key | [link](https://sea-lion.ai) | Sign in at sea-lion.ai with Google (no card, no region wall), create an API key, then paste it here. |
+| `segmind` | `segmind` | Segmind | API key, image, video | [link](https://segmind.com) | Use your Segmind API key in the x-api-key header. OmniRoute targets https://api.segmind.com/v1/<model> and returns the generated image/video bytes directly. |
+| `sensenova` | `sensenova` | SenseNova | API key | [link](https://platform.sensenova.cn) | Get API key at platform.sensenova.cn |
+| `siliconflow` | `siliconflow` | SiliconFlow | API key | [link](https://cloud.siliconflow.com) | $1 free credits plus currently listed $0 models after identity verification; availability and limits may change |
+| `snowflake` | `snowflake` | Snowflake Cortex | API key, enterprise | [link](https://www.snowflake.com) | — |
+| `sparkdesk` | `sparkdesk` | SparkDesk | API key | [link](https://xinghuo.xfyun.cn) | Get API key at console.xfyun.cn |
+| `speka` | `speka` | Speka AI | API key, aggregator | [link](https://speka.me) | Free plan: $1 monthly usage, 10 RPM, one API key and access to open models and the playground; no card required. |
+| `stability-ai` | `stability` | Stability AI | API key, image | [link](https://stability.ai) | — |
+| `stepfun` | `stepfun` | StepFun | API key | [link](https://stepfun.com) | Get API key at platform.stepfun.com |
+| `sumopod` | `sumopod` | SumoPod | API key | [link](https://ai.sumopod.com) | Use your SumoPod API key (sk-...) in Authorization: Bearer <key>. Fully OpenAI-compatible. API base URL: https://ai.sumopod.com/v1. |
+| `suno` | `suno` | Suno | API key | [link](https://suno.ai) | Paste session cookie from suno.ai (Clerk auth) |
+| `synthetic` | `synthetic` | Synthetic | API key, aggregator | [link](https://synthetic.new) | — |
+| `tabitoken` | `tabitoken` | TabiToken | API key, aggregator | [link](https://tabitoken.com) | — |
+| `tencent` | `tencent` | Tencent Hunyuan | API key | [link](https://hunyuan.tencent.com) | Get API key at console.cloud.tencent.com |
+| `thebai` | `thebai` | TheB.AI | API key, aggregator | [link](https://theb.ai) | Bearer API key for the TheB.AI OpenAI-compatible gateway. |
+| `tinyfish` | `tf` | TinyFish Fetch | API key | [link](https://docs.tinyfish.ai/fetch-api) | X-API-Key from agent.tinyfish.ai/api-keys |
+| `together` | `together` | Together AI | API key, video | [link](https://www.together.ai) | — |
+| `token-kiosk` | `tk` | Token Kiosk | API key | [link](https://agent-router.gaib.ai) | Use your Token Kiosk API key in Authorization: Bearer <key>. Fully OpenAI-compatible gateway. API base URL: https://agent-router.gaib.ai/v1. |
+| `tokenreply` | `tokenreply` | TokenReply | API key, aggregator | [link](https://www.tokenreply.com) | Free-tagged models have model- and campaign-specific daily limits; no fixed global free quota is published. |
+| `tokenrouter` | `trk` | TokenRouter | API key | [link](https://tokenrouter.com) | Use your TokenRouter API key in Authorization: Bearer <key>. Fully OpenAI-compatible. API base URL: https://api.tokenrouter.com/v1. |
+| `topaz` | `topaz` | Topaz | API key, image | [link](https://topazlabs.com) | — |
+| `typhoon` | `typhoon` | Typhoon | API key | [link](https://docs.opentyphoon.ai) | Free API key with a 5 req/s and 200 req/m rate limit. |
+| `udio` | `udio` | Udio | API key | [link](https://udio.com) | Paste session cookie from udio.com (Supabase auth) |
+| `uncloseai` | `unc` | UncloseAI | API key | [link](https://uncloseai.com) | No auth required. API accepts any non-empty string as key for identification. If older built-in models return 404, use Available Models → Import from /models or Auto-Sync; verified live model: solidrust/Hermes-3-Llama-3.1-8B-AWQ. |
+| `unorouter` | `unorouter` | UnoRouter | API key, aggregator | [link](https://unorouter.ai) | Models with the :free suffix do not debit balance; limit is 1 request/minute per free model per user. |
+| `upstage` | `upstage` | Upstage | API key | [link](https://www.upstage.ai) | — |
+| `v0-vercel` | `v0` | v0 (Vercel) | API key | [link](https://v0.dev) | — |
+| `venice` | `venice` | Venice.ai | API key | [link](https://venice.ai) | — |
+| `vercel-ai-gateway` | `vag` | Vercel AI Gateway | API key, aggregator | [link](https://vercel.com/docs/ai-gateway) | — |
+| `vertex` | `vertex` | Vertex AI | API key, enterprise | [link](https://cloud.google.com/vertex-ai) | Provide Service Account JSON or OAuth access_token |
+| `vertex-partner` | `vp` | Vertex AI Partners | API key, enterprise | [link](https://cloud.google.com/vertex-ai) | Provide the same Service Account JSON used for Vertex AI partner models. |
+| `void-ai` | `void-ai` | Void AI | API key, aggregator | [link](https://voidai.app) | The public model catalog marks some models with a free plan requirement, but access is conditional and no numeric quota is confirmed. |
+| `volcengine` | `volcengine` | Volcengine | API key | [link](https://www.volcengine.com) | — |
+| `voyage-ai` | `voyage` | Voyage AI | API key, embed/rerank | [link](https://www.voyageai.com) | Bearer API key for Voyage AI embeddings and rerank APIs. |
+| `wafer` | `wafer` | Wafer AI | API key | [link](https://wafer.ai) | — |
+| `wandb` | `wandb` | Weights & Biases Inference | API key | [link](https://wandb.ai) | — |
+| `watsonx` | `watsonx` | IBM watsonx.ai Gateway | API key, enterprise | [link](https://www.ibm.com/products/watsonx-ai) | Use your watsonx bearer token. Base URL can be https://<region>.ml.cloud.ibm.com/ml/gateway/v1/ or a self-managed /ml/gateway/v1 endpoint. |
+| `writer` | `writer` | Writer | API key | [link](https://dev.writer.com) | — |
+| `x5lab` | `x5lab` | X5Lab | API key | [link](https://x5lab.dev) | Use your X5Lab API key (x5-...) in Authorization: Bearer <key>. Fully OpenAI-compatible. API base URL: https://api.x5lab.dev/v1. |
+| `xai` | `xai` | xAI (Grok) | API key | [link](https://x.ai) | Use an official xAI API key, or sign in with xAI OAuth. Grok Build JWT sessions remain a separate provider. |
+| `xiaomi-mimo` | `mimo` | Xiaomi MiMo | API key | [link](https://mimo.mi.com) | — |
+| `xiaomi-mimo-token-plan` | `mimotp` | Xiaomi MiMo Token Plan | API key | [link](https://mimo.mi.com) | — |
+| `yi` | `yi` | Yi (01.AI) | API key | [link](https://01.ai) | Get API key at platform.lingyiwanwu.com |
+| `yolo-auto` | `yolo-auto` | Yolo-Auto | API key, aggregator | [link](https://yolo-auto.com) | Free API access is request-limited and intended for testing; no numeric daily quota is published and free access is not promised indefinitely. |
+| `zai` | `zai` | Z.AI | API key | [link](https://open.bigmodel.cn) | — |
+| `zenmux` | `zm` | ZenMux | API key | [link](https://zenmux.ai) | Use your ZenMux API key in Authorization: Bearer <key>. ZenMux is fully OpenAI-compatible. Base URL: https://zenmux.ai/api/v1. |
+| `zerolimitai` | `zerolimitai` | ZeroLimitAI | API key, aggregator | [link](https://www.zerolimitai.com) | Temporary free trial is advertised, but official pages conflict between 3 and 7 days; a 100-calls/day claim is not treated as permanent. |
+| `zylo-api` | `zylo` | Zylo API | API key, aggregator | [link](https://zyloai.net) | Basic plan: 10 RPM, 7,200 requests/day and 200,000 tokens/day; limited to Basic text models. |
+
+## Local Providers (14)
+
+| ID | Alias | Name | Tags | Website | Notes |
+|----|-------|------|------|---------|-------|
+| `comfyui` | `comfyui` | ComfyUI | Local | [link](https://github.com/comfyanonymous/ComfyUI) | No API key required. Configure the local ComfyUI base URL (default: http://localhost:8188). |
+| `docker-model-runner` | `dmr` | Docker Model Runner | Local, self-hosted | [link](https://docs.docker.com/ai/model-runner/) | API key optional. Configure the local Docker Model Runner OpenAI-compatible base URL (default: http://localhost:12434/v1). |
+| `lemonade` | `lemonade` | Lemonade Server | Local, self-hosted | [link](https://lemonade-server.ai) | API key optional. Configure the local Lemonade OpenAI-compatible base URL (default: http://localhost:13305/api/v1). |
+| `llama-cpp` | `llamacpp` | llama.cpp | Local, self-hosted | [link](https://github.com/ggml-org/llama.cpp) | API key optional (use any value, e.g. sk-no-key-required). Configure the llama-server OpenAI-compatible base URL (default: http://127.0.0.1:8080/v1). Note: if Llamafile is also installed, both default to port 8080 — run only one at a time or override the port. |
+| `llamafile` | `llamafile` | Llamafile | Local, self-hosted | [link](https://github.com/Mozilla-Ocho/llamafile) | API key optional. Configure the local Llamafile OpenAI-compatible base URL (default: http://127.0.0.1:8080/v1). |
+| `lm-studio` | `lmstudio` | LM Studio | Local, self-hosted | [link](https://lmstudio.ai) | API key optional. Configure the local LM Studio OpenAI-compatible base URL (default: http://localhost:1234/v1). |
+| `mlx-gemma` | `mlx-gemma` | MLX Gemma 26B | Local, self-hosted | [link](https://github.com/ml-explore/mlx) | No API key required. Runs mlx-lm server locally on port 11435. Requires uv and mlx-lm installed. Model: mlx-community/gemma-4-26B-A4B-it-qat-q4_0-mlx-aligned (~15.9GB peak memory). |
+| `mlx-qwen` | `mlx-qwen` | MLX Qwen 3.8 27B | Local, self-hosted | [link](https://github.com/ml-explore/mlx) | No API key required. Runs mlx-lm server locally on port 11436. Requires uv and mlx-lm installed. Model: maglun/Qwen3.8-27B-MLX-Mixed-3.80bpw (~13.1GB peak memory). |
+| `ollama-local` | `ollama` | Ollama | Local, self-hosted | [link](https://ollama.com) | No API key required. Ollama runs locally — configure its OpenAI-compatible base URL (default: http://localhost:11434/v1) and make sure Ollama is running before connecting. |
+| `oobabooga` | `ooba` | oobabooga | Local, self-hosted | [link](https://github.com/oobabooga/text-generation-webui) | API key optional. Configure the local oobabooga OpenAI-compatible base URL (default: http://localhost:5000/v1). |
+| `sdwebui` | `sdwebui` | SD WebUI | Local | [link](https://github.com/AUTOMATIC1111/stable-diffusion-webui) | No API key required. Configure the local WebUI base URL (default: http://localhost:7860). |
+| `triton` | `triton` | NVIDIA Triton | Local, self-hosted | [link](https://developer.nvidia.com/triton-inference-server) | API key optional. Configure the Triton OpenAI-compatible base URL (default: http://localhost:8000/v1). |
+| `vllm` | `vllm` | vLLM | Local, self-hosted | [link](https://github.com/vllm-project/vllm) | API key optional. Configure the local vLLM OpenAI-compatible base URL (default: http://localhost:8000/v1). |
+| `xinference` | `xinference` | XInference | Local, self-hosted | [link](https://inference.readthedocs.io) | API key optional. Configure the local XInference OpenAI-compatible base URL (default: http://localhost:9997/v1). |
+
+## Search Providers (13)
+
+| ID | Alias | Name | Tags | Website | Notes |
+|----|-------|------|------|---------|-------|
+| `brave-search` | `brave-search` | Brave Search | Search | [link](https://brave.com/search/api) | Subscription token from Brave Search API dashboard |
+| `exa-search` | `exa-search` | Exa Search | Search | [link](https://exa.ai) | API key from dashboard.exa.ai |
+| `firecrawl` | `fc` | Firecrawl | Search | [link](https://firecrawl.dev) | API key from firecrawl.dev/app/api-keys (or set your self-hosted Firecrawl base URL) |
+| `google-pse-search` | `google-pse` | Google Programmable Search | Search | [link](https://developers.google.com/custom-search/v1/overview) | Requires a Google API key and your Programmable Search Engine ID (cx) |
+| `linkup-search` | `linkup` | Linkup Search | Search | [link](https://docs.linkup.so) | Bearer API key from the Linkup dashboard |
+| `ollama-search` | `ollama-search` | Ollama Search | Search | [link](https://ollama.com/settings/keys) | Same API key as Ollama Cloud (from ollama.com/settings/keys) |
+| `perplexity-search` | `pplx-search` | Perplexity Search | Search | [link](https://docs.perplexity.ai/guides/search-quickstart) | Same API key as Perplexity (pplx-...) |
+| `searchapi-search` | `searchapi` | SearchAPI | Search | [link](https://www.searchapi.io/docs/google) | API key from SearchAPI (query param or Bearer auth) |
+| `searxng-search` | `searxng` | SearXNG Search | Search | [link](https://docs.searxng.org) | API key is optional. Set your SearXNG base URL. Some instances may require a bearer token for access. |
+| `serper-search` | `serper-search` | Serper Search | Search | [link](https://serper.dev) | API key from serper.dev dashboard |
+| `tavily-search` | `tavily-search` | Tavily Search | Search | [link](https://tavily.com) | API key from app.tavily.com (format: tvly-...) |
+| `x-search` | `x_search` | X Search (Grok) | Search | [link](https://docs.x.ai/developers/tools/x-search) | SuperGrok OAuth (xai-oauth) or xAI API key. This is Grok X Search, not the X Developer MCP. |
+| `youcom-search` | `youcom-search` | You.com Search | Search | [link](https://you.com/business/api/) | X-API-Key from the You.com platform dashboard |
+
+## Audio-only Providers (12)
+
+| ID | Alias | Name | Tags | Website | Notes |
+|----|-------|------|------|---------|-------|
+| `assemblyai` | `aai` | AssemblyAI | Audio | [link](https://assemblyai.com) | — |
+| `aws-polly` | `polly` | AWS Polly | Audio | [link](https://aws.amazon.com/polly/) | Use AWS Secret Access Key as API key; set providerSpecificData.accessKeyId and optional region. |
+| `cartesia` | `cartesia` | Cartesia | Audio | [link](https://cartesia.ai) | — |
+| `deepgram` | `dg` | Deepgram | Audio | [link](https://deepgram.com) | — |
+| `elevenlabs` | `el` | ElevenLabs | Audio | [link](https://elevenlabs.io) | — |
+| `fishaudio` | `fishaudio` | Fish Audio | Audio | [link](https://fish.audio) | — |
+| `gladia` | `gladia` | Gladia | Audio | [link](https://gladia.io) | — |
+| `inworld` | `inworld` | Inworld | Audio | [link](https://inworld.ai) | — |
+| `playht` | `playht` | PlayHT | Audio | [link](https://play.ht) | — |
+| `rev-ai` | `revai` | Rev AI | Audio | [link](https://www.rev.ai) | — |
+| `soniox` | `sx` | Soniox | Audio | [link](https://soniox.com) | — |
+| `speechmatics` | `sm` | Speechmatics | Audio | [link](https://www.speechmatics.com) | Free tier — 8 hours/month, no credit card required. Batch (async) mode only. |
+
+## Upstream Proxy Providers (2)
+
+| ID | Alias | Name | Tags | Website | Notes |
+|----|-------|------|------|---------|-------|
+| `9router` | `nr` | 9router | Upstream proxy | [link](https://www.npmjs.com/package/9router) | — |
+| `cliproxyapi` | `cpa` | CLIProxyAPI | Upstream proxy | [link](https://github.com/router-for-me/CLIProxyAPI) | — |
+
+## Cloud Agent Providers (3)
+
+| ID | Alias | Name | Tags | Website | Notes |
+|----|-------|------|------|---------|-------|
+| `codex-cloud` | `codex-cloud` | Codex Cloud | Cloud agent | [link](https://openai.com/codex) | OpenAI API key with Codex Cloud task access. |
+| `devin` | `devin` | Devin | Cloud agent | [link](https://devin.ai) | Devin API key for cloud agent sessions. |
+| `jules` | `jules` | Google Jules | Cloud agent | [link](https://jules.google) | Jules API key for creating and managing cloud coding tasks. |
+
+## System Providers (1)
+
+| ID | Alias | Name | Tags | Website | Notes |
+|----|-------|------|------|---------|-------|
+| `auto` | `auto` | Auto (Zero-Config) | System | — | — |
+
+## Sources of truth
+
+- Catalog: [`src/shared/constants/providers.ts`](../../src/shared/constants/providers.ts)
+- Registry (per-model details): [`open-sse/config/providerRegistry.ts`](../../open-sse/config/providerRegistry.ts)
+- Executors: [`open-sse/executors/`](../../open-sse/executors/) (106 implementations)
+- Translators: [`open-sse/translator/`](../../open-sse/translator/)
+
+## See Also
+
+- [FREE_TIERS.md](./FREE_TIERS.md) — curated free-tier guide
+- [USER_GUIDE.md](../guides/USER_GUIDE.md) — provider setup walkthrough
+- [ARCHITECTURE.md](../architecture/ARCHITECTURE.md) — overall architecture

README.md

@@ -7,7 +7,7 @@
 
 # 🚀 OmniRoute — The Free AI Gateway
 
-<img src="./docs/diagrams/readme-hero.svg" width="100%" alt="OmniRoute — Never stop coding. Every AI tool → 342 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 342 AI providers · 90+ free tiers · ~1.51B free tokens/mo · 19 routing strategies · $0 to start."/>
+<img src="./docs/diagrams/readme-hero.svg" width="100%" alt="OmniRoute — Never stop coding. Every AI tool → 352 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 352 AI providers · 90+ free tiers · ~1.51B free tokens/mo · 19 routing strategies · $0 to start."/>
 
 </div>
 
@@ -17,9 +17,9 @@
 
 </div>
 
-> Stacking free tiers by hand is painful — dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute aggregates the **documented** free tiers of **42 provider pools / 495 models** into one honest number and shows it live on the dashboard (`/dashboard/free-tiers`).
+> Stacking free tiers by hand is painful — dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute catalogs **455 free-tier entries across 40 recurring pool keys** and computes the token headline from the **20 pools with a published positive monthly budget**, deduplicated by shared pool. The result stays visible on the dashboard (`/dashboard/free-tiers`).
 
-<img src="./docs/diagrams/free-tier-budget.svg" width="100%" alt="OmniRoute free-tier budget card: ~1.51B free tokens per month steady, up to ~2.13B in the first month with signup credits, from the documented free tiers of 42 provider pools / 495 models behind one endpoint. Honest pool-deduped math — each shared pool counted once (counting every rate limit 24/7 would read ~10B; not published), 15 providers ToS-flagged so you decide. Budget bar of the countable free pools with per-model grid (Mistral Large 3 1B, GPT-4o mini 150M, Gemini 2.5 Flash 60M … Claude Sonnet 4.5 25K), one-time first-month signup credits (vertex 300M, agentrouter 200M, predibase 25M, together 25M, glm-cn 20M, doubao 15M, ai21 10M, longcat 10M, deepseek 5M, hyperbolic 5M, nscale 5M), plus permanently-free no-token-cap providers (SiliconFlow, Z.AI GLM-Flash, Kilo, OpenCode Zen, baidu …) and a $10 OpenRouter top-up unlocking +24M/mo — surfaced separately so they never inflate the headline. Live used/remaining on /dashboard/free-tiers."/>
+<img src="./docs/diagrams/free-tier-budget.svg" width="100%" alt="OmniRoute free-tier budget card: ~1.51B free tokens per month steady, up to ~2.13B in the first month with signup credits, from 40 documented recurring pool keys covering 455 cataloged free-tier entries behind one endpoint. Honest pool-deduped math — each shared pool counted once, including 20 recurring pools with a published positive monthly token budget; 15 providers are marked avoid in the terms-risk catalog so you decide. Budget bar includes Mistral 1B, LLM7 150M, Nara 150M, Gemini 60M and smaller pools, plus first-month signup credits and permanently-free no-token-cap providers surfaced separately so they never inflate the headline. Live used/remaining on /dashboard/free-tiers."/>
 
 > Animated summary of the live `/dashboard/free-tiers` page. Full methodology (pool dedupe, credit tiers, provider terms): **[docs/reference/FREE_TIERS.md](docs/reference/FREE_TIERS.md)**.
 >
@@ -61,14 +61,14 @@
 
 <div align="center">
 
-|                           | v3.8.49 | **v3.8.50** | `v3.8.51+`  |
-| ------------------------- | :-----: | :---------: | :---------: |
-| 🌐 Providers              |   290   |   **342**   | more queued |
-| 🧠 Documented models      |  1185   |  **1202**   |      —      |
-| 🖼️ Modality Bridge        |    —    |  🆕 vision  |    video    |
-| 📡 Radar free catalog     |    —    |  🆕 opt-in  |      —      |
-| ⚖️ Quota-aware scheduling |    —    |      —      |   🔭 next   |
-| 📊 Quota telemetry        |    —    |      —      |   🔭 next   |
+|                           | v3.8.49 |        **v3.8.50**        | `v3.8.51+`  |
+| ------------------------- | :-----: | :-----------------------: | :---------: |
+| 🌐 Providers              |   290   |          **352**          | more queued |
+| 🧠 Unique chat model IDs  |  1185   |         **1312**          |      —      |
+| 🖼️ Modality Bridge        |    —    | 🆕 vision + audio + video |      —      |
+| 📡 Radar free catalog     |    —    |         🆕 opt-in         |      —      |
+| ⚖️ Quota-aware scheduling |    —    |      🆕 Quota-Share       |      —      |
+| 📊 Quota telemetry        |    —    |          🆕 live          |      —      |
 
 **→ [Roadmap](ROADMAP.md) — riding the rail to `v3.9.0 LTS`**
 
@@ -101,7 +101,7 @@
   <tr>
     <td align="right"><b>⚙️ Features</b></td>
     <td align="center"><a href="#-combos--the-flagship">🎯 Combos</a></td>
-    <td align="center"><a href="#-342-ai-providers--90-free">🌐 Providers</a></td>
+    <td align="center"><a href="#-352-ai-providers--154-catalog-marked-free">🌐 Providers</a></td>
     <td align="center"><a href="#-full-cli--a2a--mcp">🔌 CLI &amp; MCP</a></td>
   </tr>
   <tr>
@@ -126,7 +126,7 @@
     <td align="right"><b>📦 Project</b></td>
     <td align="center"><a href="#%EF%B8%8F-tech-stack">🛠️ Tech Stack</a></td>
     <td align="center"><a href="#-documentation">📖 Docs</a></td>
-    <td align="center"><a href="#-500-contributors">👥 Contributors</a></td>
+    <td align="center"><a href="#-600-contributors">👥 Contributors</a></td>
   </tr>
 </table>
 
@@ -210,7 +210,7 @@ curl http://localhost:20128/v1/chat/completions \
 
 </div>
 
-<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint. 342 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 342 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 56 free forever — no card needed) · Every tool works (33 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 109 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
+<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint and 352 providers. Automatic fallback keeps routing while another healthy target is available. Six pillars: resilient fallback across 352 providers · up to 95% token savings on eligible workloads · $0 to start with 90+ free tiers and 56 recurring/keyless free-forever providers · 35 CLI/agent integrations through one config · OpenAI, Claude, Gemini and Responses API compatibility at /v1 · production controls including circuit breakers, TLS stealth, MCP 110 tools, A2A, memory, guardrails, evals and 39,000+ static test declarations across 5,100+ tracked test files."/>
 
 <br/>
 <br/>
@@ -225,7 +225,7 @@ curl http://localhost:20128/v1/chat/completions \
 
 <div align="center">
 
-<img src="./docs/diagrams/tier-cascade.svg" width="100%" alt="OmniRoute request flow: your IDE or CLI (Claude Code, Cursor, Cline…) calls one local endpoint (http://localhost:20128/v1); the OmniRoute Smart Router (RTK + Caveman compression, 19 routing strategies, circuit breakers, TLS stealth, MCP, A2A, guardrails) auto-falls back across 4 provider tiers — Tier 1 Subscription (Claude Code, Codex, Copilot), quota out? Tier 2 API Key (DeepSeek, Groq, xAI), budget hit? Tier 3 Cheap (GLM $0.5, MiniMax $0.2), budget hit? Tier 4 Free (Kiro, Qoder, Pollinations) — always on."/>
+<img src="./docs/diagrams/tier-cascade.svg" width="100%" alt="OmniRoute request flow: your IDE or CLI (Claude Code, Cursor, Cline…) calls one local endpoint (http://localhost:20128/v1); the OmniRoute Smart Router (RTK + Caveman compression, 19 routing strategies, circuit breakers, TLS stealth, MCP, A2A, guardrails) can fall back across 4 provider tiers while an eligible healthy target remains — Tier 1 Subscription, Tier 2 API Key, Tier 3 Cheap and Tier 4 Free."/>
 
 </div>
 
@@ -318,7 +318,7 @@ curl http://localhost:20128/v1/chat/completions \
 
 <img src="./docs/diagrams/strategies-grid.svg" width="100%" alt="All 19 combo routing strategies animated — one tile per strategy: priority, fill-first, weighted, round-robin, p2c, least-used, random, strict-random, cost-optimized, headroom, reset-window, reset-aware, context-relay, context-optimized, cache-optimized, lkgp, auto, fusion, pipeline. See the table above for what each one does."/>
 
-> A **combo** is a chain of models OmniRoute routes across **automatically**. Quota runs out, a provider fails, or costs spike — the combo silently slides to the next model. **This is what makes OmniRoute unbreakable.** 🛡️
+> A **combo** is a chain of models OmniRoute routes across **automatically**. If quota runs out, a provider fails, or costs spike, the combo can move to the next eligible healthy model. 🛡️
 
 ### ⚡ Zero-config — just use `auto`
 
@@ -429,7 +429,7 @@ All **19** strategies — mix & match per combo step:
   <tr>
     <td align="center">17</td>
     <td nowrap><code>auto</code></td>
-    <td>14-factor live scoring across every connection 🤖</td>
+    <td>15-factor live scoring across every connection 🤖</td>
   </tr>
   <tr>
     <td align="center">18</td>
@@ -443,7 +443,7 @@ All **19** strategies — mix & match per combo step:
   </tr>
 </table>
 
-<sub>The Auto-Combo engine scores every candidate on **14 factors** (health, quota, cost, latency, success rate, freshness…) — see [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md).</sub>
+<sub>The Auto-Combo engine scores every candidate on **15 factors** (health, quota, cost, latency, task fit, quality, session availability…) — see [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md).</sub>
 
 ##
 
@@ -461,7 +461,7 @@ All **19** strategies — mix & match per combo step:
 
 </div>
 
-<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 342 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, built-in MCP server with 109 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project&apos;s docs."/>
+<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — a dated feature snapshot vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 352 providers, 90+ free tiers built in, 19 routing strategies, 12-engine token compression, built-in MCP server with 110 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA and 43 i18n UI locales. OmniRoute is MIT-licensed and self-hostable. Competitor capabilities and counts may change; see the linked methodology."/>
 
 <sub>📊 Full methodology &amp; per-feature detail vs 9router, OpenRouter, CLIProxyAPI &amp; LiteLLM → [`docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`](docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md)</sub>
 
@@ -517,9 +517,9 @@ Pix copia-e-cola:
 
 ## 📡 OmniRoute Radar
 
-The main free-tier headline remains **~1.53B tokens/month** from the documented,
+The main free-tier headline remains **~1.51B tokens/month** from the documented,
 pool-deduplicated catalog above. Temporary provider signup credits can separately lift the first
-month to **~2.15B**. Radar is an optional, signed catalog overlay for people who want fresher
+month to **~2.13B**. Radar is an optional, signed catalog overlay for people who want fresher
 free-model availability between OmniRoute releases; the community catalog and every existing free
 feature remain free.
 
@@ -548,7 +548,7 @@ the current catalog at **[radar.omniroute.online/planos](https://radar.omniroute
 - **🗜️ Compression hardening** — default-on inflation guard, Caveman packs for DE / FR / JA + Chinese (wényán), RTK filters for Gradle & .NET. → [Compression](docs/compression/COMPRESSION_ENGINES.md)
 - **💸 Honest flat-rate cost** — subscription / coding-plan providers read **$0** in cost analytics; budget, quota & routing keep estimating. → [API Reference](docs/reference/API_REFERENCE.md)
 - **⚖️ Quota-Share routing** — split a shared account's quota fairly across pooled keys, work-conserving so idle slices are lent out. → [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md)
-- **🤖 One-command CLI/agent setup** — `setup-*` configures 12+ coding tools; `omniroute run` launches 7 CLIs (Claude Code, Codex, Aider, Goose, OpenCode, Qwen Code, Gemini CLI) with zero config written; `omniroute configure` is an interactive provider+model picker with per-context favorites. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
+- **🤖 One-command CLI/agent setup** — 12 registered `setup-*` commands; `omniroute run` launches 7 CLIs (Claude Code, Codex, Aider, Goose, OpenCode, Qwen Code, Gemini CLI); `omniroute configure` supports 9 targets with an interactive provider+model picker and per-context favorites. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
 - **🛰️ Remote mode** — drive a remote OmniRoute with scoped tokens (`connect` / `contexts` / `tokens`) + an `antigravity` OAuth helper for VPS installs. → [Remote Mode](docs/guides/REMOTE-MODE.md)
 - **🧭 Smarter auto-routing** — `auto/<category>:<tier>` combos, **Fusion** (model panel + judge), task-aware routing, per-request model / mode / USD-budget overrides. → [Auto-Combo](docs/routing/AUTO-COMBO.md)
 - **🗜️ Pluggable compression** — 12 composable engines + Compression Studios: LLMLingua-2, two-tier Ultra, omniglyph, per-step fidelity gate, GCF v3.2, drag-reorder editor. → [Compression](docs/compression/COMPRESSION_ENGINES.md)
@@ -557,9 +557,9 @@ the current catalog at **[radar.omniroute.online/planos](https://radar.omniroute
 - **🧠 Memory you control** — off by default, opt-in int8 vector quantization + typed decay, per-request `x-omniroute-no-memory`. → [Memory](docs/frameworks/MEMORY.md)
 - **🛡️ Security** — prompt-injection guard on every LLM route (red-team suite), opt-in credential-masking guardrail (redacts leaked API keys/secrets in both directions), free DuckDuckGo last-resort web search, and an optional OIDC login gate for the dashboard (password login always stays available). → [Guardrails](docs/security/GUARDRAILS.md)
 - **🖼️ New endpoints** — `/v1/ocr` (Mistral OCR) and `/v1/audio/translations` (Whisper-style) round out the media surface. → [API Reference](docs/reference/API_REFERENCE.md)
-- **🎨 Image / video / audio generation** — one API for media: xAI Grok Imagine & Novita AI video, ComfyUI, Freepik, Adobe Firefly, Microsoft Designer, Segmind, EdgeTTS. → [API Reference](docs/reference/API_REFERENCE.md)
+- **🎨 Image / video / audio generation** — one API for media: xAI Grok Imagine & Novita AI video, ComfyUI, Freepik, Adobe Firefly, Microsoft Designer, Segmind, and speech providers such as ElevenLabs. → [API Reference](docs/reference/API_REFERENCE.md)
 - **🌍 Deployment & ops** — reverse-proxy `basePath`, browser-language auto-detect, per-key device tracking, root-less MITM trust, zh-TW localization. → [Environment](docs/reference/ENVIRONMENT.md)
-- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **342-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
+- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **352-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
 - **📡 Routing transparency** — every response carries an `X-OmniRoute-Decision` header naming the strategy/provider/latency that served it, a new `cache-optimized` combo strategy + Auto-Combo `cacheAffinity` factor route repeat requests back to the connection holding the cached prefix, and a read-only `/v1/auto-combo/{channel}/candidates` endpoint exposes an `auto/*` channel's live candidate pool. → [Auto-Combo](docs/routing/AUTO-COMBO.md)
 - **⚡ Local performance & infra** — one-click local Redis, Cloudflare Workers / Deno Deploy relay deployers, Bifrost & Mux as supervised embedded services. → [Embedded Services](docs/frameworks/EMBEDDED-SERVICES.md)
 
@@ -612,7 +612,7 @@ the current catalog at **[radar.omniroute.online/planos](https://radar.omniroute
 <b>＋ also works with</b> · Kiro · Command Code · Antigravity · Windsurf · AMP · <b>any OpenAI-compatible tool</b>
 </div>
 
-<sub>📖 Per-tool setup for all 34 tools (26 CLI Code's + 8 CLI Agents) → [`docs/reference/CLI-TOOLS.md`](docs/reference/CLI-TOOLS.md) · 🧩 OpenCode plugin → [`@omniroute/opencode-provider`](https://www.npmjs.com/package/@omniroute/opencode-provider)</sub>
+<sub>📖 Per-tool setup for all 35 tools (26 CLI Code's + 9 CLI Agents) → [`docs/reference/CLI-TOOLS.md`](docs/reference/CLI-TOOLS.md) · 🧩 OpenCode plugin → [`@omniroute/opencode-provider`](https://www.npmjs.com/package/@omniroute/opencode-provider)</sub>
 
 </div>
 
@@ -642,11 +642,11 @@ of your shell history. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
 
 <div align="center">
 
-## 🌐 342 AI Providers — 90+ Free
+## 🌐 352 AI Providers — 154 Catalog-Marked Free
 
 </div>
 
-> The most complete catalog of any open-source router: **342 providers**, **90+ with a free tier**, **56 free forever**.
+> **352 registered providers** across the canonical chat, media, search, local, cloud-agent and system collections, including **154 carrying `hasFree: true` discovery metadata**. The chat model registry covers **268 providers / 2,566 distinct provider-model pairs / 1,312 raw model IDs**; the separate free-budget catalog has **455 per-model rows**, **40 recurring pools** and **56 recurring/keyless free-forever providers**. These are different denominators by design; definitions and pool-deduped calculations live in the [Provider Reference](docs/reference/PROVIDER_REFERENCE.md) and [Free Tiers](docs/reference/FREE_TIERS.md).
 
 <div align="center">
 
@@ -679,7 +679,7 @@ of your shell history. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
   </tr>
 </table>
 
-<sub>…and 220+ more — every icon resolves live from the dashboard's provider catalog. 📖 [Provider Reference](docs/reference/PROVIDER_REFERENCE.md)</sub>
+<sub>…and 330+ more — every icon resolves live from the dashboard's provider catalog. 📖 [Provider Reference](docs/reference/PROVIDER_REFERENCE.md)</sub>
 
 <br/>
 
@@ -769,7 +769,7 @@ From inside the editor: open the **Extensions** view, search **"OmniRoute"**, cl
 
 </div>
 
-<img src="./docs/diagrams/privacy-local.svg" width="100%" alt="Private and local-first — your keys, your machine, your data; OmniRoute is a local proxy that never phones home. Eleven guarantees: runs 100% on your hardware (0 cloud hops), zero telemetry by default, credentials encrypted at rest (AES-256-GCM), no account or sign-up, hardened gateway (API-key scoping, IP filtering, rate limits, prompt-injection guard), loopback-only process routes, upstream header scrubbing, strictly opt-in PII redaction, sanitized errors that never leak internals, a local audit trail in your own SQLite, and MIT-licensed fully open-source code."/>
+<img src="./docs/diagrams/privacy-local.svg" width="100%" alt="Private and local-first — OmniRoute's gateway and control plane run on your machine. Prompts are sent to the upstream provider selected for each request; OmniRoute adds no hosted prompt-processing hop and telemetry is disabled by default. Credentials are encrypted at rest with AES-256-GCM; controls include API-key scoping, IP filtering, rate limits, prompt-injection guards, upstream-header scrubbing, opt-in PII redaction, sanitized errors and a local SQLite audit trail. OmniRoute is MIT-licensed and self-hostable."/>
 
 <sub>📖 [Authorization](docs/architecture/AUTHZ_GUIDE.md) · [Guardrails](docs/security/GUARDRAILS.md) · [Compliance](docs/security/COMPLIANCE.md)</sub>
 
@@ -810,7 +810,7 @@ Tokens are scoped `read` / `write` / `admin`; process-spawning routes stay loopb
 
 <div align="left">
 
-<img src="./docs/diagrams/cli-terminal.svg" width="50%" alt="Animated terminal demoing the OmniRoute CLI — omniroute providers list, omniroute combo list, omniroute health — cycling over the 80+ command surface: providers · oauth · keys · combo · nodes · models · cache · compression · cost · usage · quota · health · resilience · telemetry · logs · audit · mcp · a2a · cloud · memory · skills · eval · tunnel · backup · sync · webhooks · policy · pricing · translator · simulate …"/>
+<img src="./docs/diagrams/cli-terminal.svg" width="50%" alt="Animated terminal demoing the OmniRoute CLI — omniroute providers list, omniroute combo list and omniroute health — cycling over the 85-command top-level surface: providers · oauth · keys · combo · nodes · models · cache · compression · cost · usage · quota · health · resilience · telemetry · logs · audit · mcp · a2a · cloud · memory · skills · eval · tunnel · backup · sync · webhooks · policy · pricing · translator · simulate …"/>
 
 </div>
 
@@ -821,7 +821,7 @@ Expose OmniRoute over **MCP**, **A2A**, a **REST API**, **webhooks** or a **remo
 <table>
   <tr><th align="left">Interface</th><th align="left">Endpoint / command</th><th align="left">Use it for</th></tr>
   <tr><td align="left" nowrap>🧰 <b>MCP (stdio)</b></td><td align="left" nowrap><code>omniroute --mcp</code></td><td align="left">Plug into Claude Desktop, Cursor, any MCP client</td></tr>
-  <tr><td align="left" nowrap>🌊 <b>MCP (HTTP)</b></td><td align="left" nowrap><code>/api/mcp/stream</code></td><td align="left">Remote MCP — <b>109 tools</b>, 33 scopes, full audit trail</td></tr>
+  <tr><td align="left" nowrap>🌊 <b>MCP (HTTP)</b></td><td align="left" nowrap><code>/api/mcp/stream</code></td><td align="left">Remote MCP — <b>110 tools</b>, 33 scopes, full audit trail</td></tr>
   <tr><td align="left" nowrap>📡 <b>MCP (SSE)</b></td><td align="left" nowrap><code>/api/mcp/sse</code></td><td align="left">Streaming MCP transport</td></tr>
   <tr><td align="left" nowrap>🤝 <b>A2A</b></td><td align="left" nowrap><code>/.well-known/agent.json</code></td><td align="left">Agent-to-agent, <b>JSON-RPC 2.0</b> + SSE, 6 skills</td></tr>
   <tr><td align="left" nowrap>🌐 <b>REST API</b></td><td align="left" nowrap><code>/v1/*</code></td><td align="left">OpenAI-compatible — chat, embeddings, images, audio, OCR</td></tr>
@@ -846,7 +846,7 @@ claude mcp add-server omniroute --type http --url http://localhost:20128/api/mcp
 
 ### 📖 How it works — pipeline, architecture & savings math
 
-<img src="./docs/diagrams/compression-pipeline.svg" width="100%" alt="OmniRoute compression pipeline: a client request of 10,000 tokens passes through 12 stacked engines — Session-Dedup, CCR, Lite, RTK, Responses Tool Output, Headroom, Relevance, Caveman, Aggressive, LLMLingua-2, Ultra, OmniGlyph — and reaches the provider at about 1,080 tokens, up to 95% saved. Code, URLs and JSON are always preserved byte-perfect."/>
+<img src="./docs/diagrams/compression-pipeline.svg" width="100%" alt="OmniRoute compression pipeline: an illustrative 10,000-token client request passes through 12 composable engines — Session-Dedup, CCR, Lite, RTK, Responses Tool Output, Headroom, Relevance, Caveman, Aggressive, LLMLingua-2, Ultra and OmniGlyph — and can reach the provider at about 1,080 tokens in the documented stacked example. Structured content is protected by preservation guards and per-step fidelity gates; explicit lossy or experimental modes may transform eligible content."/>
 
 Default stacked combo runs `RTK → Caveman`. When both act on the same tool/context payload, savings compound:
 
@@ -988,12 +988,42 @@ docker run -d --name omniroute --restart unless-stopped --stop-timeout 40 \
   -p 127.0.0.1:20128:20128 -v omniroute-data:/app/data diegosouzapw/omniroute:latest
 ```
 
+`:latest` follows the highest **published** stable SemVer. It does not track git `main`. Pin `:X.Y.Z` for GitOps. See [Docker Release Channels](docs/guides/DOCKER_GUIDE.md#release-channels).The image pins **`OMNIROUTE_MEMORY_MB=1024`**. That is enough for the dashboard and a light chat. **Coding agents** (`POST /v1/responses` from Claude Code, Codex, Grok, …) need a much larger V8 heap or the process `FATAL ERROR`s at ~12 GiB under two overlapping long contexts. Size the container above the heap (native buffers sit outside V8):
+
+| Workload                            | Heap (`-e OMNIROUTE_MEMORY_MB`) | Container (`--memory`) |
+| ----------------------------------- | ------------------------------- | ---------------------- |
+| Dashboard / light chat              | `1024` (image default)          | ≥2 g                   |
+| One coding agent                    | `8192`                          | ≥10 g                  |
+| Two concurrent long `/v1/responses` | `10240`–`12288`                 | ≥12–16 g               |
+
+```bash
+docker run -d --name omniroute --restart unless-stopped --stop-timeout 40 \
+  -e OMNIROUTE_MEMORY_MB=8192 --memory=10g \
+  -p 127.0.0.1:20128:20128 -v omniroute-data:/app/data diegosouzapw/omniroute:latest
+```
+
+Full table: [Docker Guide — runtime RAM](docs/guides/DOCKER_GUIDE.md#runtime-ram-for-coding-agents).
+
 > **Pre-release Docker channel:** `diegosouzapw/omniroute:next` and
 > `diegosouzapw/omniroute:next-web` follow the current default `release/v*`
 > branch. These mutable tags are intended only for testing unreleased fixes and
 > are **not supported for production**. See
 > [Docker Release Channels](docs/guides/DOCKER_GUIDE.md#release-channels).
 
+**🥟 Bun**
+
+Standard `bun install` and global installation (`bun install -g omniroute`) are supported via Bun runtime detection:
+
+- **Built-in `bun:sqlite`**: OmniRoute uses Bun's built-in `bun:sqlite` driver when running under Bun, falling back to `better-sqlite3` on Node.js or `sql.js`.
+- **Automatic Webpack bundler selection**: Development (`bun run dev`) and production builds (`bun run build`) automatically detect Bun and disable Turbopack in favor of Webpack to prevent native V8 binding incompatibilities.
+- **Dedicated Bun Dockerfile**: Multi-stage `Dockerfile.bun` for native Bun production deployments (`docker build -f Dockerfile.bun -t omniroute:bun .`).
+
+```bash
+# Install and run with Bun
+bun install
+bun run dev
+```
+
 **🛠️ From source**
 
 ```bash
@@ -1076,7 +1106,7 @@ same process on one port, so there is no separate CLI-only package today.
 
 <div align="center">
 
-<sub>Dados de cobertura social em 2026-08-17 · YT: 741 | TT: 137 | IG: 124 · Frescor (dias): YT 0 · TT 14 · IG 15</sub>
+<sub>Snapshot do painel em 2026-08-24 · Catálogo bruto: YT 809 | TT 137 | IG 124 · Frescor (dias): YT 1 | TT 21 | IG 22</sub>
 
 <table>
   <tr>
@@ -1085,52 +1115,52 @@ same process on one port, so there is no separate CLI-only package today.
         <img src="https://placehold.co/320x180/111827/FFFFFF?text=Instagram+Reel+%7C+nick_saraev&font=montserrat&bold=true" alt="Instagram Reel" width="300"/>
       </a><br/>
       <b>🎬 #1 — Instagram</b><br/>
-      <sub>nick_saraev — 1,628,910 views</sub>
+      <sub>nick_saraev — 3,042,474 views</sub>
+    </td>
+    <td align="center" width="320">
+      <a href="https://www.instagram.com/reel/DaSs65mMrHk/">
+        <img src="https://placehold.co/320x180/111827/FFFFFF?text=Instagram+Reel+%7C+theopenstack&font=montserrat&bold=true" alt="Instagram Reel — theopenstack" width="300"/>
+      </a><br/>
+      <b>🎬 #2 — Instagram</b><br/>
+      <sub>theopenstack — 692,419 views</sub>
+    </td>
+    <td align="center" width="320">
+      <a href="https://www.tiktok.com/@milesreevesai/video/7667980059189366019">
+        <img src="https://placehold.co/320x180/111827/FFFFFF?text=TikTok+%7C+milesreevesai&font=montserrat&bold=true" alt="TikTok — milesreevesai" width="300"/>
+      </a><br/>
+      <b>🎬 #3 — TikTok</b><br/>
+      <sub>milesreevesai — 620,400 views</sub>
     </td>
     <td align="center" width="320">
       <a href="https://www.youtube.com/watch?v=QucgvbO5gsM">
         <img src="https://img.youtube.com/vi/QucgvbO5gsM/maxresdefault.jpg" alt="YouTube — Vaibhav Sisinty" width="300"/>
       </a><br/>
-      <b>🎬 #2 — YouTube</b><br/>
-      <sub>Vaibhav Sisinty — 373,084 views</sub>
+      <b>🎬 #4 — YouTube</b><br/>
+      <sub>Vaibhav Sisinty — 391,109 views</sub>
     </td>
     <td align="center" width="320">
-      <a href="https://www.youtube.com/shorts/fZIBK_4fKq8">
-        <img src="https://img.youtube.com/vi/fZIBK_4fKq8/maxresdefault.jpg" alt="YouTube Shorts" width="300"/>
+      <a href="https://www.instagram.com/reel/DbIt9AjK7-U/">
+        <img src="https://placehold.co/320x180/111827/FFFFFF?text=Instagram+Reel+%7C+buildwithai.club&font=montserrat&bold=true" alt="Instagram Reel — buildwithai.club" width="300"/>
       </a><br/>
-      <b>🎬 #3 — YouTube Shorts</b><br/>
-      <sub>Nick Automates — 207,714 views</sub>
-    </td>
-    <td align="center" width="320">
-      <a href="https://www.tiktok.com/@milesreevesai/video/7667980059189366019">
-        <img src="https://placehold.co/320x180/111827/FFFFFF?text=TikTok+Top+1&font=montserrat&bold=true" alt="TikTok Thumbnail" width="300"/>
-      </a><br/>
-      <b>🎬 #4 — TikTok</b><br/>
-      <sub>milesreevesai — 620,400 views</sub>
-    </td>
-    <td align="center" width="320">
-      <a href="https://www.youtube.com/watch?v=LkP6ocAoQkk">
-        <img src="https://img.youtube.com/vi/LkP6ocAoQkk/maxresdefault.jpg" alt="Valency Labs" width="300"/>
-      </a><br/>
-      <b>🎬 #5 — YouTube</b><br/>
-      <sub>Valency Labs — 135,974 views</sub>
+      <b>🎬 #5 — Instagram</b><br/>
+      <sub>buildwithai.club — 347,652 views</sub>
     </td>
   </tr>
 </table>
 
 </div>
 
-**Ranking completo (`v > 0`, maior alcance):**
+**Ranking completo (URLs canônicas deduplicadas, `v > 0`, maior alcance):**
 
-| #1                                                                                     | #2                                                                                                      | #3                                                                                     | #4                                                                                          | #5                                                                                          |
-| -------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- |
-| [nick_saraev — Instagram](https://www.instagram.com/reel/Da8ZthUPK98/) — **1,628,910** | [milesreevesai — TikTok](https://www.tiktok.com/@milesreevesai/video/7667980059189366019) — **620,400** | [Vaibhav Sisinty — YouTube](https://www.youtube.com/watch?v=QucgvbO5gsM) — **373,084** | [Nick Automates — YouTube Shorts](https://www.youtube.com/shorts/fZIBK_4fKq8) — **207,714** | [midudev — TikTok](https://www.tiktok.com/@midudev/video/7664636453544152342) — **177,800** |
+| #1                                                                                     | #2                                                                                    | #3                                                                                                      | #4                                                                                     | #5                                                                                        |
+| -------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
+| [nick_saraev — Instagram](https://www.instagram.com/reel/Da8ZthUPK98/) — **3,042,474** | [theopenstack — Instagram](https://www.instagram.com/reel/DaSs65mMrHk/) — **692,419** | [milesreevesai — TikTok](https://www.tiktok.com/@milesreevesai/video/7667980059189366019) — **620,400** | [Vaibhav Sisinty — YouTube](https://www.youtube.com/watch?v=QucgvbO5gsM) — **391,109** | [buildwithai.club — Instagram](https://www.instagram.com/reel/DbIt9AjK7-U/) — **347,652** |
 
-| #6                                                                                    | #7                                                                                                  | #8                                                                                  | #9                                                                           | #10                                                                                    |
-| ------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- |
-| [theopenstack — Instagram](https://www.instagram.com/reel/DaSs65mMrHk/) — **155,453** | [t.ghoush.ai — TikTok](https://www.tiktok.com/@t.ghoush.ai/video/7669497680527248656) — **152,800** | [Valency Labs — YouTube](https://www.youtube.com/watch?v=LkP6ocAoQkk) — **135,974** | [Asati — YouTube](https://www.youtube.com/watch?v=JjPtJcqwhqg) — **126,130** | [Vaibhav Sisinty — YouTube](https://www.youtube.com/watch?v=NuNDpeZYQ28) — **122,672** |
+| #6                                                                                  | #7                                                                                      | #8                                                                                          | #9                                                                                        | #10                                                                                         |
+| ----------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- |
+| [nivedan.ai — Instagram](https://www.instagram.com/reel/DbIrCksJiqq/) — **331,973** | [vaibhavsisinty — Instagram](https://www.instagram.com/reel/Dae05TSAK1l/) — **263,744** | [Nick Automates — YouTube Shorts](https://www.youtube.com/shorts/fZIBK_4fKq8) — **218,174** | [theroshankrishna — Instagram](https://www.instagram.com/reel/Dapjs58z0P0/) — **186,786** | [midudev — TikTok](https://www.tiktok.com/@midudev/video/7664636453544152342) — **177,800** |
 
-Métricas de validação: 1002 vídeos rastreados · 7,069,190 visualizações conhecidas · 595 perfis/canais · 13+ idiomas · 13+ criadores.
+Métricas canônicas em 2026-08-24: **1.029 vídeos únicos** · **11.132.922 visualizações conhecidas** (`v > 0`) · **639 canais/perfis por rede**. O painel bruto contém 1.070 linhas; 41 duplicatas do Instagram foram normalizadas pela URL canônica, mantendo a maior contagem por vídeo.
 
 > 🎬 **Made a video about OmniRoute?** Open an [issue](https://github.com/diegosouzapw/OmniRoute/issues/new) or [discussion](https://github.com/diegosouzapw/OmniRoute/discussions) with the link — we'll feature it here.
 
@@ -1172,7 +1202,7 @@ Métricas de validação: 1002 vídeos rastreados · 7,069,190 visualizações c
   <tr><td nowrap><b>Runtime</b></td><td>Node.js 22.x / 24.x LTS — <code>&gt;=22.22.2 &lt;23 || &gt;=24.0.0 &lt;27</code></td></tr>
   <tr><td nowrap><b>Language</b></td><td>TypeScript 6.0 — <b>100% TypeScript</b> across <code>src/</code> and <code>open-sse/</code> (zero <code>any</code> in core since v2.0)</td></tr>
   <tr><td nowrap><b>Framework</b></td><td>Next.js 16 + React 19 + Tailwind CSS 4</td></tr>
-  <tr><td nowrap><b>Database</b></td><td>better-sqlite3 (SQLite, WAL journaling) + LowDB (JSON legacy) — 120 domain modules, 154 migrations</td></tr>
+  <tr><td nowrap><b>Database</b></td><td>better-sqlite3 (SQLite, WAL journaling) + LowDB (JSON legacy) — 120 domain modules, 159 migrations</td></tr>
   <tr><td nowrap><b>Memory</b></td><td>SQLite FTS5 full-text + int8-quantized vector embeddings, typed decay</td></tr>
   <tr><td nowrap><b>Schemas</b></td><td>Zod 4 — MCP tool I/O validation + API contracts</td></tr>
   <tr><td nowrap><b>Protocols</b></td><td>MCP (stdio / HTTP / SSE) + A2A v0.3 (JSON-RPC 2.0 + SSE)</td></tr>
@@ -1182,7 +1212,7 @@ Métricas de validação: 1002 vídeos rastreados · 7,069,190 visualizações c
   <tr><td nowrap><b>Stealth</b></td><td>wreq-js — JA3 / JA4 TLS fingerprint impersonation, 3-level proxy</td></tr>
   <tr><td nowrap><b>Resilience</b></td><td>Circuit breaker, exponential backoff, anti-thundering-herd, auto-combo self-healing</td></tr>
   <tr><td nowrap><b>Logging</b></td><td>pino — structured JSON logs with request context</td></tr>
-  <tr><td nowrap><b>Testing</b></td><td>Node.js test runner + Vitest — <b>25,000+ test cases</b> across 3,300+ files (unit, integration, E2E, security, ecosystem)</td></tr>
+  <tr><td nowrap><b>Testing</b></td><td>Node.js test runner + Vitest — <b>39,000+ static test declarations</b> across 5,100+ tracked test files (unit, integration, E2E, security, ecosystem)</td></tr>
   <tr><td nowrap><b>Platforms</b></td><td>Desktop (Electron) · Android (Termux) · PWA (any browser)</td></tr>
   <tr><td nowrap><b>CI/CD</b></td><td>GitHub Actions — auto npm publish + Docker Hub on release</td></tr>
   <tr><td nowrap><b>Links</b></td><td><a href="https://omniroute.online">Website</a> · <a href="https://www.npmjs.com/package/omniroute">npm</a> · <a href="https://hub.docker.com/r/diegosouzapw/omniroute">Docker Hub</a></td></tr>
@@ -1233,9 +1263,9 @@ Métricas de validação: 1002 vídeos rastreados · 7,069,190 visualizações c
   <tr><td nowrap><b><a href="docs/compression/COMPRESSION_RULES_FORMAT.md">Compression Rules Format</a></b></td><td>JSON rule-pack schemas for Caveman and RTK filters</td></tr>
   <tr><td nowrap><b><a href="docs/compression/COMPRESSION_LANGUAGE_PACKS.md">Compression Language Packs</a></b></td><td>Language detection and Caveman rule-pack authoring</td></tr>
   <tr><td nowrap><b><a href="docs/architecture/RESILIENCE_GUIDE.md">Resilience Guide</a></b></td><td>Circuit breakers, cooldowns, queue, anti-thundering herd, TLS spoofing</td></tr>
-  <tr><td nowrap><b><a href="docs/routing/AUTO-COMBO.md">Auto-Combo Engine</a></b></td><td>14-factor scoring, mode packs, self-healing</td></tr>
+  <tr><td nowrap><b><a href="docs/routing/AUTO-COMBO.md">Auto-Combo Engine</a></b></td><td>15-factor scoring, mode packs, self-healing</td></tr>
   <tr><td nowrap><b><a href="docs/ops/PROXY_GUIDE.md">Proxy Guide</a></b></td><td>3-level proxy system, 1proxy marketplace, registry CRUD</td></tr>
-  <tr><td nowrap><b><a href="docs/reference/FREE_TIERS.md">Free Tiers</a></b></td><td>90+ free providers consolidated directory (42 documented token pools / 495 models)</td></tr>
+  <tr><td nowrap><b><a href="docs/reference/FREE_TIERS.md">Free Tiers</a></b></td><td>Consolidated directory: 40 documented recurring pools / 455 cataloged free-tier entries</td></tr>
   <tr><td nowrap><b><a href="docs/guides/FEATURES.md">Features Gallery</a></b></td><td>Visual dashboard tour with screenshots</td></tr>
   <tr><td nowrap><b><a href="docs/architecture/CODEBASE_DOCUMENTATION.md">Codebase Documentation</a></b></td><td>Beginner-friendly codebase walkthrough</td></tr>
 </table>
@@ -1246,7 +1276,7 @@ Métricas de validação: 1002 vídeos rastreados · 7,069,190 visualizações c
   <tr><th align="left">Document</th><th align="left">Description</th></tr>
   <tr><td nowrap><b><a href="docs/reference/API_REFERENCE.md">API Reference</a></b></td><td>All endpoints with examples</td></tr>
   <tr><td nowrap><b><a href="docs/openapi.yaml">OpenAPI Spec</a></b></td><td>OpenAPI 3.0 specification</td></tr>
-  <tr><td nowrap><b><a href="open-sse/mcp-server/README.md">MCP Server</a></b></td><td>109 MCP tools, IDE configs, Python/TS/Go clients</td></tr>
+  <tr><td nowrap><b><a href="open-sse/mcp-server/README.md">MCP Server</a></b></td><td>110 MCP tools, IDE configs, Python/TS/Go clients</td></tr>
   <tr><td nowrap><b><a href="docs/frameworks/MCP-SERVER.md">MCP Server Guide</a></b></td><td>MCP installation, transports, and tool reference</td></tr>
   <tr><td nowrap><b><a href="src/lib/a2a/README.md">A2A Server</a></b></td><td>JSON-RPC 2.0 protocol, skills, streaming, task mgmt</td></tr>
   <tr><td nowrap><b><a href="docs/frameworks/A2A-SERVER.md">A2A Server Guide</a></b></td><td>A2A agent card, tasks, skills, and streaming</td></tr>
@@ -1262,7 +1292,7 @@ Métricas de validação: 1002 vídeos rastreados · 7,069,190 visualizações c
   <tr><td nowrap><b><a href="SECURITY.md">Security Policy</a></b></td><td>Vulnerability reporting and security practices</td></tr>
   <tr><td nowrap><b><a href="docs/guides/I18N.md">i18n Guide</a></b></td><td>43-language support, translation workflow, RTL</td></tr>
   <tr><td nowrap><b><a href="docs/ops/RELEASE_CHECKLIST.md">Release Checklist</a></b></td><td>Pre-release validation steps</td></tr>
-  <tr><td nowrap><b><a href="docs/ops/COVERAGE_PLAN.md">Coverage Plan</a></b></td><td>Test coverage strategy and 25,000+ test suite</td></tr>
+  <tr><td nowrap><b><a href="docs/ops/COVERAGE_PLAN.md">Coverage Plan</a></b></td><td>Test coverage strategy for 39,000+ static test declarations across 5,100+ tracked test files</td></tr>
 </table>
 
 <br/>
@@ -1273,93 +1303,123 @@ Métricas de validação: 1002 vídeos rastreados · 7,069,190 visualizações c
 
 > OmniRoute is shaped by a passionate open-source community. These individuals have made exceptional contributions that directly impact the quality, stability, and reach of the project. **Thank you.**
 
+### External contributors by merged pull requests
+
+<table>
+  <tr><th align="center">Rank</th><th align="left">Contributor</th><th align="center">Merged PRs</th><th align="right">~Changed lines</th></tr>
+  <tr><td align="center">1</td><td align="left"><a href="https://github.com/backryun"><b>backryun</b></a></td><td align="center">190</td><td align="right">227,977</td></tr>
+  <tr><td align="center">2</td><td align="left"><a href="https://github.com/oyi77"><b>oyi77</b></a></td><td align="center">180</td><td align="right">407,678</td></tr>
+  <tr><td align="center">3</td><td align="left"><a href="https://github.com/rdself"><b>rdself</b></a></td><td align="center">145</td><td align="right">80,663</td></tr>
+  <tr><td align="center">4</td><td align="left"><a href="https://github.com/JxnLexn"><b>JxnLexn</b></a></td><td align="center">128</td><td align="right">387,049</td></tr>
+  <tr><td align="center">5</td><td align="left"><a href="https://github.com/KooshaPari"><b>KooshaPari</b></a></td><td align="center">101</td><td align="right">125,747</td></tr>
+  <tr><td align="center">6</td><td align="left"><a href="https://github.com/herjarsa"><b>herjarsa</b></a></td><td align="center">88</td><td align="right">230,872</td></tr>
+  <tr><td align="center">7</td><td align="left"><a href="https://github.com/RaviTharuma"><b>RaviTharuma</b></a></td><td align="center">79</td><td align="right">55,106</td></tr>
+  <tr><td align="center">8</td><td align="left"><a href="https://github.com/maxmad64bis"><b>maxmad64bis</b></a></td><td align="center">69</td><td align="right">394,715</td></tr>
+  <tr><td align="center">9</td><td align="left"><a href="https://github.com/artickc"><b>artickc</b></a></td><td align="center">59</td><td align="right">33,260</td></tr>
+  <tr><td align="center">10</td><td align="left"><a href="https://github.com/HouMinXi"><b>HouMinXi</b></a></td><td align="center">51</td><td align="right">47,334</td></tr>
+  <tr><td align="center">10</td><td align="left"><a href="https://github.com/chirag127"><b>chirag127</b></a></td><td align="center">51</td><td align="right">5,153</td></tr>
+  <tr><td align="center">12</td><td align="left"><a href="https://github.com/xz-dev"><b>xz-dev</b></a></td><td align="center">50</td><td align="right">245,976</td></tr>
+  <tr><td align="center">13</td><td align="left"><a href="https://github.com/hartmark"><b>hartmark</b></a></td><td align="center">47</td><td align="right">52,185</td></tr>
+  <tr><td align="center">14</td><td align="left"><a href="https://github.com/rqzbeh"><b>rqzbeh</b></a></td><td align="center">39</td><td align="right">143,181</td></tr>
+  <tr><td align="center">15</td><td align="left"><a href="https://github.com/dhaern"><b>dhaern</b></a></td><td align="center">34</td><td align="right">19,559</td></tr>
+  <tr><td align="center">16</td><td align="left"><a href="https://github.com/Dingding-leo"><b>Dingding-leo</b></a></td><td align="center">33</td><td align="right">1,986</td></tr>
+  <tr><td align="center">17</td><td align="left"><a href="https://github.com/NomenAK"><b>NomenAK</b></a></td><td align="center">32</td><td align="right">13,854</td></tr>
+  <tr><td align="center">18</td><td align="left"><a href="https://github.com/MumuTW"><b>MumuTW</b></a></td><td align="center">30</td><td align="right">16,953</td></tr>
+  <tr><td align="center">19</td><td align="left"><a href="https://github.com/benzntech"><b>benzntech</b></a></td><td align="center">29</td><td align="right">11,641</td></tr>
+  <tr><td align="center">20</td><td align="left"><a href="https://github.com/pacocartones"><b>pacocartones</b></a></td><td align="center">24</td><td align="right">9,331</td></tr>
+  <tr><td align="center">20</td><td align="left"><a href="https://github.com/Prudhvivuda"><b>Prudhvivuda</b></a></td><td align="center">24</td><td align="right">6,312</td></tr>
+</table>
+
+<sub>Frozen at live <code>release/v3.8.50</code> tip <code>dafb4ae808</code>, with merges through 2026-08-24 05:26:03 UTC. The paginated GitHub GraphQL census contains 5,911 merged PRs: 2,707 by the repository owner, 179 by Dependabot, and <b>3,025 external PRs from 535 distinct contributors</b>. “Changed lines” is GitHub additions + deletions and includes generated files, lockfiles, catalogs, translations and documentation; it is churn, not authored LOC. Ties at the cutoff are retained.</sub>
+
+### GitHub-attributed commits
+
 <table>
-  <tr>
-    <td align="center" width="160">
-      <a href="https://github.com/oyi77">
-        <img src="https://github.com/oyi77.png" width="40" style="border-radius:50%" alt="oyi77"/><br/>
-        <b>oyi77</b>
-      </a><br/>
-      <sub>🥇 213 commits • +114K lines</sub><br/>
-      <sub>Analytics engine, SQL aggregations,<br/>proxy marketplace, test coverage</sub>
-    </td>
-    <td align="center" width="160">
-      <a href="https://github.com/rdself">
-        <img src="https://github.com/rdself.png" width="40" style="border-radius:50%" alt="R.D. &amp; Randi"/><br/>
-        <b>R.D. &amp; Randi</b>
-      </a><br/>
-      <sub>🥈 108 commits • +38K lines</sub><br/>
-      <sub>Endpoints page, tunnel integrations,<br/>Docker workflows, A2A status, compression UI</sub>
-    </td>
-    <td align="center" width="160">
-      <a href="https://github.com/christopher-s">
-        <img src="https://github.com/christopher-s.png" width="40" style="border-radius:50%" alt="Chris Staley"/><br/>
-        <b>Chris Staley</b>
-      </a><br/>
-      <sub>🥉 70 commits • +1.8K lines</sub><br/>
-      <sub>SSE stream hardening, Responses API,<br/>Gemini pagination, test regression fixes</sub>
-    </td>
-    <td align="center" width="160">
-      <a href="https://github.com/zen0bit">
-        <img src="https://github.com/zen0bit.png" width="40" style="border-radius:50%" alt="zenobit"/><br/>
-        <b>zenobit</b>
-      </a><br/>
-      <sub>🏅 62 commits • +22K lines</sub><br/>
-      <sub>CI/CD pipeline, i18n for 33 languages,<br/>Void Linux package, platform fixes</sub>
-    </td>
-    <td align="center" width="160">
-      <a href="https://github.com/JxnLexn">
-        <img src="https://github.com/JxnLexn.png" width="40" style="border-radius:50%" alt="Jan Leon"/><br/>
-        <b>Jan Leon</b>
-      </a><br/>
-      <sub>🏅 58 commits • +22K lines</sub><br/>
-      <sub>Reasoning-effort routing, proxy controls,<br/>quota visibility, Live Zone compression</sub>
-    </td>
-  </tr>
   <tr>
     <td align="center" width="160">
       <a href="https://github.com/backryun">
         <img src="https://github.com/backryun.png" width="40" style="border-radius:50%" alt="backryun"/><br/>
         <b>backryun</b>
       </a><br/>
-      <sub>🏅 53 commits • +70K lines</sub><br/>
-      <sub>Provider catalog curation — Perplexity, Kimi,<br/>Cerebras, Copilot, LMArena refreshes</sub>
+      <sub>🥇 220 GitHub-attributed commits</sub>
     </td>
     <td align="center" width="160">
-      <a href="https://github.com/chirag127">
-        <img src="https://github.com/chirag127.png" width="40" style="border-radius:50%" alt="Chirag Singhal"/><br/>
-        <b>Chirag Singhal</b>
+      <a href="https://github.com/oyi77">
+        <img src="https://github.com/oyi77.png" width="40" style="border-radius:50%" alt="Paijo"/><br/>
+        <b>Paijo</b>
       </a><br/>
-      <sub>🏅 46 commits • +4.8K lines</sub><br/>
-      <sub>Error sanitization, MITM prefill fix,<br/>fusion judge, breaker/429 correctness</sub>
+      <sub>🥈 219 GitHub-attributed commits</sub>
     </td>
     <td align="center" width="160">
-      <a href="https://github.com/kfiramar">
-        <img src="https://github.com/kfiramar.png" width="40" style="border-radius:50%" alt="kfiramar"/><br/>
-        <b>kfiramar</b>
+      <a href="https://github.com/rdself">
+        <img src="https://github.com/rdself.png" width="40" style="border-radius:50%" alt="Randi"/><br/>
+        <b>Randi</b>
       </a><br/>
-      <sub>🏅 38 commits • +1.7K lines</sub><br/>
-      <sub>Codex websocket + passthrough, auth/onboarding,<br/>Electron hardening, DB migrations</sub>
+      <sub>🥉 108 GitHub-attributed commits</sub>
     </td>
     <td align="center" width="160">
-      <a href="https://github.com/benzntech">
-        <img src="https://github.com/benzntech.png" width="40" style="border-radius:50%" alt="Benson K B"/><br/>
-        <b>Benson K B</b>
+      <a href="https://github.com/RaviTharuma">
+        <img src="https://github.com/RaviTharuma.png" width="40" style="border-radius:50%" alt="Ravi Tharuma"/><br/>
+        <b>Ravi Tharuma</b>
       </a><br/>
-      <sub>🏅 28 commits • +9.2K lines</sub><br/>
-      <sub>Electron desktop app, auto-updater,<br/>release build workflows, cross-platform CI</sub>
+      <sub>🏅 81 GitHub-attributed commits</sub>
     </td>
     <td align="center" width="160">
-      <a href="https://github.com/herjarsa">
-        <img src="https://github.com/herjarsa.png" width="40" style="border-radius:50%" alt="Hernan J. Ardila"/><br/>
-        <b>Hernan J. Ardila</b>
+      <a href="https://github.com/christopher-s">
+        <img src="https://github.com/christopher-s.png" width="40" style="border-radius:50%" alt="Chris"/><br/>
+        <b>Chris</b>
       </a><br/>
-      <sub>🏅 25 commits • +174K lines</sub><br/>
-      <sub>Zero-latency combos, vision-bridge auto-routing,<br/>catalog context-length, resilience 429 hints</sub>
+      <sub>🏅 70 GitHub-attributed commits</sub>
+    </td>
+    <td align="center" width="160">
+      <a href="https://github.com/hartmark">
+        <img src="https://github.com/hartmark.png" width="40" style="border-radius:50%" alt="Markus Hartung"/><br/>
+        <b>Markus Hartung</b>
+      </a><br/>
+      <sub>🏅 69 GitHub-attributed commits · tied #6</sub>
+    </td>
+  </tr>
+  <tr>
+    <td align="center" width="160">
+      <a href="https://github.com/maxmad64bis">
+        <img src="https://github.com/maxmad64bis.png" width="40" style="border-radius:50%" alt="Dizzle"/><br/>
+        <b>Dizzle</b>
+      </a><br/>
+      <sub>🏅 69 GitHub-attributed commits · tied #6</sub>
+    </td>
+    <td align="center" width="160">
+      <a href="https://github.com/JxnLexn">
+        <img src="https://github.com/JxnLexn.png" width="40" style="border-radius:50%" alt="Jan Leon"/><br/>
+        <b>Jan Leon</b>
+      </a><br/>
+      <sub>🏅 64 GitHub-attributed commits</sub>
+    </td>
+    <td align="center" width="160">
+      <a href="https://github.com/zen0bit">
+        <img src="https://github.com/zen0bit.png" width="40" style="border-radius:50%" alt="zenobit"/><br/>
+        <b>zenobit</b>
+      </a><br/>
+      <sub>🏅 62 GitHub-attributed commits</sub>
+    </td>
+    <td align="center" width="160">
+      <a href="https://github.com/HouMinXi">
+        <img src="https://github.com/HouMinXi.png" width="40" style="border-radius:50%" alt="Bob.Hou"/><br/>
+        <b>Bob.Hou</b>
+      </a><br/>
+      <sub>🏅 51 GitHub-attributed commits · tied #10</sub>
+    </td>
+    <td align="center" width="160">
+      <a href="https://github.com/xz-dev">
+        <img src="https://github.com/xz-dev.png" width="40" style="border-radius:50%" alt="Xiangzhe"/><br/>
+        <b>Xiangzhe</b>
+      </a><br/>
+      <sub>🏅 51 GitHub-attributed commits · tied #10</sub>
     </td>
   </tr>
 </table>
 
+<sub>Rechecked at 2026-08-24 06:14:31 UTC: GitHub-attributed commits reported by the repository Contributors API for the <code>release/v3.8.50</code> default branch. The API returned 525 identities (415 users, 2 bots, 108 anonymous); this table excludes the maintainer, bots and anonymous identities and retains competition ties. It is distinct from both the merged-PR ranking above and the 639-person Git-metadata census below.</sub>
+
 > 🙏 These contributors' features, bug fixes, and infrastructure improvements are a **core part** of what makes OmniRoute reliable and feature-rich. Every pull request, every test case, and every i18n translation file matters. Open source is built by people like them.
 
 </div>
@@ -1376,25 +1436,48 @@ A heartfelt thank-you to the people who fund OmniRoute out of their own pocket
 
 <table>
   <tr>
+    <td align="center" width="180">
+      <a href="https://github.com/drewbitt">
+        <img src="https://github.com/drewbitt.png?size=140" width="72" style="border-radius:50%" alt="Andrew"/><br/>
+        <b>Andrew</b>
+      </a><br/>
+      <sub>💛 Active monthly sponsor</sub>
+    </td>
+    <td align="center" width="180">
+      <a href="https://github.com/psylligent">
+        <img src="https://github.com/psylligent.png?size=140" width="72" style="border-radius:50%" alt="Vlad I"/><br/>
+        <b>Vlad I</b>
+      </a><br/>
+      <sub>💛 Active monthly sponsor</sub>
+    </td>
+    <td align="center" width="180">
+      <a href="https://github.com/pacocartones">
+        <img src="https://github.com/pacocartones.png?size=140" width="72" style="border-radius:50%" alt="Paco Cartones"/><br/>
+        <b>Paco Cartones</b>
+      </a><br/>
+      <sub>💛 Active one-time sponsor</sub>
+    </td>
     <td align="center" width="180">
       <a href="https://github.com/igormorais123">
         <img src="https://github.com/igormorais123.png?size=140" width="72" style="border-radius:50%" alt="Professor Igor Morais Vasconcelos"/><br/>
         <b>Prof. Igor Morais</b>
       </a><br/>
-      <sub>💛 Sponsor</sub>
+      <sub>💛 Past one-time supporter</sub>
     </td>
     <td align="center" width="180">
       <a href="https://github.com/longtao77">
         <img src="https://github.com/longtao77.png?size=140" width="72" style="border-radius:50%" alt="longtao"/><br/>
         <b>longtao</b>
       </a><br/>
-      <sub>💛 Sponsor</sub>
+      <sub>💛 Past one-time supporter</sub>
     </td>
   </tr>
 </table>
 
 <sub>… and others who prefer to stay private 💛</sub>
 
+<sub>Public GitHub Sponsors revalidated on 2026-08-24. GitHub's <code>activeOnly</code> status determines the active labels above; previously disclosed public one-time supporters remain thanked, and private sponsors remain anonymous.</sub>
+
 <b><a href="https://github.com/sponsors/diegosouzapw">💖 Become a sponsor →</a></b> — every dollar keeps OmniRoute free and independent.
 
 </div>
@@ -1403,11 +1486,13 @@ A heartfelt thank-you to the people who fund OmniRoute out of their own pocket
 
 <div align="center">
 
-## 👥 320+ Contributors
+## 👥 600+ Contributors
 
 </div>
 
-[![Contributors](https://contrib.rocks/image?repo=diegosouzapw/OmniRoute&max=400&columns=20&anon=1)](https://github.com/diegosouzapw/OmniRoute/graphs/contributors)
+[![Contributors](https://contrib.rocks/image?repo=diegosouzapw/OmniRoute&max=639&columns=20&anon=1)](https://github.com/diegosouzapw/OmniRoute/graphs/contributors)
+
+<sub>Audited on 2026-08-24 at frozen base <code>ac02c5b42f</code> and rechecked at live <code>release/v3.8.50</code> tip <code>dafb4ae808</code>: <b>639 normalized human Git identities</b> — 407 appear as commit authors (including the maintainer) and 232 only in explicit <code>Co-authored-by</code> trailers. The census normalizes GitHub noreply handles, excludes 26 bot/agent/service/placeholder identities, and does not merge ordinary email addresses merely because their display names match.</sub>
 
 ### How to Contribute
 
@@ -1424,7 +1509,8 @@ See [CONTRIBUTING.md](CONTRIBUTING.md) for detailed guidelines.
 
 ```bash
 # Create a release — npm publish happens automatically
-gh release create v3.8.2 --title "v3.8.2" --generate-notes
+VERSION=x.y.z
+gh release create "v${VERSION}" --title "v${VERSION}" --generate-notes
 ```
 
 <br/>
@@ -1466,88 +1552,108 @@ gh release create v3.8.2 --title "v3.8.2" --generate-notes
 
 OmniRoute stands on the shoulders of giants. It started as a fork of **[9router](https://github.com/decolua/9router)** and a TypeScript port of the Go project **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** — and from there, every subsystem below was inspired by an open-source project that got there first. Each one shaped a concrete piece of OmniRoute. This is our thank-you to all of them. 🙏
 
-> ⭐ star counts as of July 2026 — go give these projects a star.
+> ⭐ star counts verified from GitHub's REST API on August 24, 2026 — go give these projects a star. Counts are an exact dated snapshot and will naturally change.
 
 ### 🧬 Lineage & gateway
 
 <table>
   <tr><th align="left">Project</th><th align="center">⭐</th><th align="left">How it inspired OmniRoute</th></tr>
-  <tr><td nowrap><b><a href="https://github.com/decolua/9router">9router</a></b></td><td align="center">22.7k</td><td>The original project this fork is built on — extended here with multi-modal APIs and a full TypeScript rewrite.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/router-for-me/CLIProxyAPI">CLIProxyAPI</a></b></td><td align="center">43.6k</td><td>The Go implementation that inspired this JavaScript / TypeScript port.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/BerriAI/litellm">LiteLLM</a></b></td><td align="center">54.0k</td><td>The AI gateway whose public pricing dataset feeds our cost-tracking sync and whose provider-normalization model informed our routing.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/decolua/9router">9router</a></b></td><td align="center">26,161</td><td>The original project this fork is built on — extended here with multi-modal APIs and a full TypeScript rewrite.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/router-for-me/CLIProxyAPI">CLIProxyAPI</a></b></td><td align="center">48,497</td><td>The Go implementation that inspired this JavaScript / TypeScript port.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/BerriAI/litellm">LiteLLM</a></b></td><td align="center">57,100</td><td>The AI gateway whose public pricing dataset feeds our cost-tracking sync and whose provider-normalization model informed our routing.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/miuuyy/codex-chatgpt-web">codex-chatgpt-web</a></b></td><td align="center">1,410</td><td>MIT source adapted into the vendored ChatGPT Web → Codex Responses bridge, including browser-session, response-framing, usage and web-search adapters.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/Alishahryar1/free-claude-code">free-claude-code</a></b></td><td align="center">48,112</td><td>Patterns ported into stream recovery, no-thinking aliases, fallback web search, sliding-window limits, log redaction and hardened launcher flows.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/standardagents/composer-api">composer-api</a></b></td><td align="center">322</td><td>Cursor Composer tool-choice, output-constraint and tool-commit patterns adapted into the native Cursor executor.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/ndycode/codex-multi-auth">codex-multi-auth</a></b></td><td align="center">457</td><td>Fresh-login and refresh-token rotation patterns ported into Codex OAuth reauthentication.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/ex-machina-co/opencode-anthropic-auth">opencode-anthropic-auth</a></b></td><td align="center">510</td><td>Claude Code-compatible transform defaults and billing-header behavior generalized into OmniRoute's config-driven bridge.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/520mmxx/grok2api-merged">grok2api-merged</a></b></td><td align="center">2</td><td>Its Grok model mappings, fake-TypeError Statsig generator, request and device defaults, and NDJSON response processor were materially adapted into OmniRoute's Grok Web executor.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/TQZHR/grok2api">TQZHR/grok2api</a></b></td><td align="center">705</td><td>The principal transitive code source behind grok2api-merged; its model, header, payload, Statsig and processor implementations are preserved in the Grok Web lineage.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/chenyme/grok2api">chenyme/grok2api</a></b></td><td align="center">7,520</td><td>The underlying MIT source for Grok payload and device defaults, the Statsig generator, and the <code>result.response</code> processor carried through TQZHR and grok2api-merged.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/miuzhaii/grok2api-pro">grok2api-pro</a></b></td><td align="center">27</td><td>A transitive source credited by grok2api-merged for its proxy-pool layer; OmniRoute preserves that lineage notice but does not claim a proxy-pool port in its bounded Grok Web executor.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/CNFlyCat/GrokProxy">GrokProxy</a></b></td><td align="center">50</td><td>Its cookie-authenticated Grok proxy and <code>result.response.token</code> streaming pattern informed OmniRoute's Grok Web transport.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/lianying1716/GrokBridge">GrokBridge</a></b></td><td align="center">5</td><td>The original Grok Web implementation consulted its HTTP/browser upstream design; its direct HTTP path derives from GrokProxy, so no independent code port is claimed.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/imjustprism/grok-web-api">grok-web-api</a></b></td><td align="center">14</td><td>Its Rust <code>ChatOptions</code> and response-envelope schemas informed OmniRoute's TypeScript Grok request and streaming-response types.</td></tr>
 </table>
 
 ### 🗜️ Context & token compression — engines
 
 <table>
   <tr><th align="left">Project</th><th align="center">⭐</th><th align="left">How it inspired OmniRoute</th></tr>
-  <tr><td nowrap><b><a href="https://github.com/JuliusBrussee/caveman">Caveman</a></b></td><td align="center">90.8k</td><td>The viral "why use many token when few token do trick" project — its caveman-speak philosophy powers our standard compression mode and 30+ filler/condensation rules.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/rtk-ai/rtk">RTK – Rust Token Killer</a></b></td><td align="center">71.8k</td><td>High-performance command-output compression — inspired our RTK engine, JSON filter DSL, raw-output recovery and the stacked RTK → Caveman pipeline.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/headroomlabs-ai/headroom">headroom</a></b></td><td align="center">60.1k</td><td>Reversible context-compression (SmartCrusher) — inspired our <code>headroom</code> engine and the <code>ccr</code> retrieve-marker pattern.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/microsoft/LLMLingua">LLMLingua</a></b></td><td align="center">6.5k</td><td>Prompt-compression research (LLMLingua / LLMLingua-2) — inspired our async, code-safe, fail-open <code>llmlingua</code> engine.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/atjsh/llmlingua-2-js">llmlingua-2-js</a></b></td><td align="center">30</td><td>The JS/ONNX port (MobileBERT / XLM-RoBERTa) used as the worker-thread backend for our LLMLingua engine.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/leninejunior/troglodita">Troglodita</a></b></td><td align="center">26</td><td>PT-BR token compression — powers our pt-BR language pack: pleonasm reduction and filler removal tuned for Brazilian-Portuguese grammar.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/DietrichGebert/ponytail">ponytail</a></b></td><td align="center">86.0k</td><td>The viral "lazy senior dev" YAGNI-coder skill — inspired our <b>less-code</b> Output Style: smallest-working-change steering that cuts _generated_ code (the output-axis sibling to Caveman's terse prose).</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/JuliusBrussee/caveman">Caveman</a></b></td><td align="center">100,538</td><td>The viral "why use many token when few token do trick" project — its caveman-speak philosophy powers our standard compression mode and 30+ filler/condensation rules.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/rtk-ai/rtk">RTK – Rust Token Killer</a></b></td><td align="center">77,185</td><td>High-performance command-output compression — inspired our RTK engine, JSON filter DSL, raw-output recovery and the stacked RTK → Caveman pipeline.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/headroomlabs-ai/headroom">headroom</a></b></td><td align="center">67,310</td><td>Reversible context-compression (SmartCrusher) — inspired our <code>headroom</code> engine and the <code>ccr</code> retrieve-marker pattern.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/microsoft/LLMLingua">LLMLingua</a></b></td><td align="center">6,598</td><td>Prompt-compression research (LLMLingua / LLMLingua-2) — inspired our async, code-safe, fail-open <code>llmlingua</code> engine.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/atjsh/llmlingua-2-js">llmlingua-2-js</a></b></td><td align="center">31</td><td>The JS/ONNX port (MobileBERT / XLM-RoBERTa) used as the worker-thread backend for our LLMLingua engine.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/leninejunior/troglodita">Troglodita</a></b></td><td align="center">40</td><td>PT-BR token compression — powers our pt-BR language pack: pleonasm reduction and filler removal tuned for Brazilian-Portuguese grammar.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/DietrichGebert/ponytail">ponytail</a></b></td><td align="center">108,957</td><td>The viral "lazy senior dev" YAGNI-coder skill — inspired our <b>less-code</b> Output Style: smallest-working-change steering that cuts _generated_ code (the output-axis sibling to Caveman's terse prose).</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/ayghri/i-have-adhd">i-have-adhd</a></b></td><td align="center">23,526</td><td>Its action-first, ADHD-friendly response style was adapted into OmniRoute's concise output style across five languages.</td></tr>
 </table>
 
 ### 🧩 Compact formats, token research & code-aware tooling
 
 <table>
   <tr><th align="left">Project</th><th align="center">⭐</th><th align="left">How it inspired OmniRoute</th></tr>
-  <tr><td nowrap><b><a href="https://github.com/toon-format/toon">TOON</a></b></td><td align="center">24.9k</td><td>Token-Oriented Object Notation — its columnar, header-plus-rows model shaped our tabular compaction stage.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/blackwell-systems/gcf">GCF – Graph Compact Format</a></b></td><td align="center">22</td><td>First inspired our tabular compaction stage; now its zero-dependency, lossless generic-profile encoder is <b>vendored directly</b> as the Headroom codec (MIT, SPDX-marked), current with GCF spec v3.2.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/ooples/token-optimizer-mcp">token-optimizer-mcp</a></b></td><td align="center">444</td><td>Brotli/SQLite cache + per-session context-delta — inspired our <code>session-dedup</code> engine.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/Mibayy/token-savior">token-savior</a></b></td><td align="center">1.1k</td><td>Bash-output compaction + MCP profiles — inspired our compression bail-out discipline and MCP tool-manifest reduction.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/ppgranger/token-saver">token-saver</a></b></td><td align="center">117</td><td>Content-aware, per-file-type output compression with failure-aware bail-out — validated our per-type dispatch and minimum-gain skip.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/alexgreensh/token-optimizer">token-optimizer</a></b></td><td align="center">1.7k</td><td>"Find the ghost tokens" — its offload + recoverable-handle pattern informed our CCR offload thinking.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/Shweta-Mishra-ai/tokenmizer">TokenMizer</a></b></td><td align="center">16</td><td>A session-graph + cross-turn line-dedup blueprint that informed our session-dedup design.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/toon-format/toon">TOON</a></b></td><td align="center">25,233</td><td>Token-Oriented Object Notation — its columnar, header-plus-rows model shaped our tabular compaction stage.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/blackwell-systems/gcf">GCF – Graph Compact Format</a></b></td><td align="center">41</td><td>Its compact graph format and generic-profile design informed OmniRoute's tabular compaction and Headroom codec format.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/blackwell-systems/gcf-typescript">gcf-typescript</a></b></td><td align="center">4</td><td>The MIT TypeScript implementation directly vendored and extended as the Headroom generic-profile codec.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/ooples/token-optimizer-mcp">token-optimizer-mcp</a></b></td><td align="center">494</td><td>Brotli/SQLite cache + per-session context-delta — inspired our <code>session-dedup</code> engine.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/Mibayy/token-savior">token-savior</a></b></td><td align="center">1,122</td><td>Bash-output compaction + MCP profiles — inspired our compression bail-out discipline and MCP tool-manifest reduction.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/ppgranger/token-saver">token-saver</a></b></td><td align="center">138</td><td>Content-aware, per-file-type output compression with failure-aware bail-out — validated our per-type dispatch and minimum-gain skip.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/alexgreensh/token-optimizer">token-optimizer</a></b></td><td align="center">1,951</td><td>"Find the ghost tokens" — its offload + recoverable-handle pattern informed our CCR offload thinking.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/Shweta-Mishra-ai/tokenmizer">TokenMizer</a></b></td><td align="center">28</td><td>A session-graph + cross-turn line-dedup blueprint that informed our session-dedup design.</td></tr>
   <tr><td nowrap><b><a href="https://github.com/jessefreitas/OmniCompress">OmniCompress</a></b></td><td align="center">3</td><td>Rust columnar-JSON + content-addressed retrieve + cross-message dedup — validated our <code>headroom</code>/<code>ccr</code>/<code>session-dedup</code> engine design and the cache-stable "compressed form is position-independent" invariant.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/atlassian-labs/mcp-compressor">mcp-compressor</a></b></td><td align="center">98</td><td>MCP tool-schema/description compression — informed our MCP tool-manifest cardinality reduction.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/pdavis68/RepoMapper">RepoMapper</a></b></td><td align="center">187</td><td>Aider-style repo-map ranking — informed our repo-map / retrieval-ranking exploration.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/atlassian-labs/mcp-compressor">mcp-compressor</a></b></td><td align="center">113</td><td>MCP tool-schema/description compression — informed our MCP tool-manifest cardinality reduction.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/pdavis68/RepoMapper">RepoMapper</a></b></td><td align="center">197</td><td>Aider-style repo-map ranking — informed our repo-map / retrieval-ranking exploration.</td></tr>
   <tr><td nowrap><b><a href="https://github.com/mrsimpson/quiet-shell-mcp">quiet-shell-mcp</a></b></td><td align="center">4</td><td>Declarative shell-output reduction over MCP — validated our declarative bash-output compaction.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/dsherret/ts-morph">ts-morph</a></b></td><td align="center">6.1k</td><td>TypeScript Compiler API toolkit — inspired our parser-based comment removal that preserves string, template and regex literals.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/dsherret/ts-morph">ts-morph</a></b></td><td align="center">6,162</td><td>TypeScript Compiler API toolkit — inspired our parser-based comment removal that preserves string, template and regex literals.</td></tr>
 </table>
 
 ### 🧠 Memory & RAG
 
 <table>
   <tr><th align="left">Project</th><th align="center">⭐</th><th align="left">How it inspired OmniRoute</th></tr>
-  <tr><td nowrap><b><a href="https://github.com/mem0ai/mem0">Mem0</a></b></td><td align="center">61.2k</td><td>Universal memory layer — its proxy-as-write/read-boundary model shaped our memory architecture.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/letta-ai/letta">Letta (MemGPT)</a></b></td><td align="center">23.9k</td><td>Stateful agents with tiered memory — inspired our Context Control & Recovery (CCR) tiered model.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/onestardao/WFGY">WFGY</a></b></td><td align="center">1.8k</td><td>The ProblemMap taxonomy of 16 recurring RAG/LLM failure modes — the shared vocabulary in our troubleshooting guide.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/mem0ai/mem0">Mem0</a></b></td><td align="center">63,902</td><td>Universal memory layer — its proxy-as-write/read-boundary model shaped our memory architecture.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/letta-ai/letta">Letta (MemGPT)</a></b></td><td align="center">24,382</td><td>Stateful agents with tiered memory — inspired our Context Control & Recovery (CCR) tiered model.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/onestardao/WFGY">WFGY</a></b></td><td align="center">1,781</td><td>The ProblemMap taxonomy of 16 recurring RAG/LLM failure modes — the shared vocabulary in our troubleshooting guide.</td></tr>
 </table>
 
 ### 🛰️ Traffic inspection, MITM & transparent proxy
 
 <table>
   <tr><th align="left">Project</th><th align="center">⭐</th><th align="left">How it inspired OmniRoute</th></tr>
-  <tr><td nowrap><b><a href="https://github.com/chouzz/llm-interceptor">llm-interceptor</a></b></td><td align="center">49</td><td>MITM interception/analysis of coding-assistant ↔ LLM traffic — our Traffic Inspector ports its SSE merge, conversation normalization, host passthrough and secret masking (MIT).</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/InterceptSuite/ProxyBridge">ProxyBridge</a></b></td><td align="center">5.5k</td><td>Transparent per-process proxy routing — inspired our crash-safe MITM teardown, socket idle-timeouts, <code>/proc</code> process attribution and TPROXY capture.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/chouzz/llm-interceptor">llm-interceptor</a></b></td><td align="center">66</td><td>MITM interception/analysis of coding-assistant ↔ LLM traffic — our Traffic Inspector ports its SSE merge, conversation normalization, host passthrough and secret masking. The upstream's complete license text is still under provenance review.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/InterceptSuite/ProxyBridge">ProxyBridge</a></b></td><td align="center">5,995</td><td>Transparent per-process proxy routing — inspired our crash-safe MITM teardown, socket idle-timeouts, <code>/proc</code> process attribution and TPROXY capture.</td></tr>
 </table>
 
 ### 📚 Model data, observability & UI
 
 <table>
   <tr><th align="left">Project</th><th align="center">⭐</th><th align="left">How it inspired OmniRoute</th></tr>
-  <tr><td nowrap><b><a href="https://github.com/anomalyco/models.dev">models.dev</a></b></td><td align="center">6.0k</td><td>Open database of AI model specs, pricing and capabilities — synced natively into our model catalog.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/xyflow/xyflow">React Flow / xyflow</a></b></td><td align="center">37.7k</td><td>The node-based graph library powering our real-time Compression Studio and Combo/Routing Studio.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/langchain-ai/langgraph">LangGraph</a></b></td><td align="center">37.6k</td><td>LangGraph Studio's live workflow-graph visualization inspired our Studios' real-time cascade view.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/langfuse/langfuse">Langfuse</a></b></td><td align="center">31.4k</td><td>Its trace → span → generation observability model shaped our Compression Studio waterfall.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/kiali/kiali">Kiali</a></b></td><td align="center">3.6k</td><td>Istio service-mesh observability — inspired our circuit-breaker badges and error-edge visuals in the Routing/Combo Studio.</td></tr>
-  <tr><td nowrap><b><a href="https://github.com/lobehub/lobe-icons">lobe-icons</a></b></td><td align="center">2.2k</td><td>AI/LLM brand logos that render the provider icons across our dashboard.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/anomalyco/models.dev">models.dev</a></b></td><td align="center">6,555</td><td>Open database of AI model specs, pricing and capabilities — synced natively into our model catalog.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/xyflow/xyflow">React Flow / xyflow</a></b></td><td align="center">38,108</td><td>The node-based graph library powering our real-time Compression Studio and Combo/Routing Studio.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/langchain-ai/langgraph">LangGraph</a></b></td><td align="center">40,314</td><td>LangGraph Studio's live workflow-graph visualization inspired our Studios' real-time cascade view.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/langfuse/langfuse">Langfuse</a></b></td><td align="center">33,592</td><td>Its trace → span → generation observability model shaped our Compression Studio waterfall.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/kiali/kiali">Kiali</a></b></td><td align="center">3,631</td><td>Istio service-mesh observability — inspired our circuit-breaker badges and error-edge visuals in the Routing/Combo Studio.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/lobehub/lobe-icons">lobe-icons</a></b></td><td align="center">2,428</td><td>AI/LLM brand logos that render the provider icons across our dashboard.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/lipis/flag-icons">flag-icons</a></b></td><td align="center">12,354</td><td>Provides the MIT-licensed SVG flags used by the README language selector.</td></tr>
 </table>
 
 ### 🛡️ Security
 
 <table>
   <tr><th align="left">Project</th><th align="center">⭐</th><th align="left">How it inspired OmniRoute</th></tr>
-  <tr><td nowrap><b><a href="https://github.com/tldrsec/awesome-secure-defaults">awesome-secure-defaults</a></b></td><td align="center">710</td><td>A curated list of secure-by-default libraries that guides our security choices (Helmet.js, DOMPurify, ssrf-req-filter, safe-regex, Google Tink).</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/tldrsec/awesome-secure-defaults">awesome-secure-defaults</a></b></td><td align="center">721</td><td>A curated list of secure-by-default libraries that guides our security choices (Helmet.js, DOMPurify, ssrf-req-filter, safe-regex, Google Tink).</td></tr>
 </table>
 
 ### 🧭 Complementary tools
 
 <table>
   <tr><th align="left">Project</th><th align="center">⭐</th><th align="left">How it inspired OmniRoute</th></tr>
+  <tr><td nowrap><b><a href="https://github.com/BlockRunAI/ClawRouter">ClawRouter</a></b></td><td align="center">6,564</td><td>Inspired request deduplication, emergency zero-cost fallback, pluggable Auto-Combo strategies and multilingual intent classification.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/lbjlaq/Antigravity-Manager">Antigravity-Manager</a></b></td><td align="center">30,652</td><td>Its account-aware model remapping, executable-path validation and plan-label behavior informed OmniRoute's Antigravity runtime.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/jlcodes99/vscode-antigravity-cockpit">vscode-antigravity-cockpit</a></b></td><td align="center">4,817</td><td>Its compact quota-reset countdown format inspired the corresponding provider-limit display in OmniRoute.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/iOfficeAI/AionUi">AionUi</a></b></td><td align="center">32,230</td><td>Its ACP integrations inspired OmniRoute's automatic detection of installed CLI agents.</td></tr>
+  <tr><td nowrap><b><a href="https://github.com/steipete/CodexBar">CodexBar</a></b></td><td align="center">20,507</td><td>Identified the Grok Build quota surface; OmniRoute then verified and corrected the live wire format independently.</td></tr>
 </table>
 
 ## 📄 License
@@ -1560,7 +1666,7 @@ MIT License - see [LICENSE](LICENSE) for details.
 
 **[⬆ Back to top](#-omniroute)** · Built with ❤️ for the open-source AI community.
 
-<sub>OmniRoute v3.8.49 · Node ≥22.22.2 · MIT License · <a href="https://omniroute.online">omniroute.online</a></sub>
+<sub>OmniRoute v3.8.50 · Node ≥22.22.2 · MIT License · <a href="https://omniroute.online">omniroute.online</a></sub>
 
 </div>
 <!-- GitHub Discussions enabled for community Q&A -->

bin/cli/api-commands/combos.mjs

@@ -30,20 +30,60 @@ export function register_combos(parent) {
       const data = res.ok ? await res.json() : await res.text();
       emit(data, gOpts);
     });
-  tag.command("patch-api-combos-id-")
-    .description("Update combo")
+  tag.command("get-api-combos-id-")
+    .description("Get combo by ID")
+    .requiredOption("--id <id>", "")
     .action(async (opts, cmd) => {
       const gOpts = cmd.optsWithGlobals();
       let url = "/api/combos/{id}";
-      const res = await apiFetch(url, { method: "PATCH", baseUrl: gOpts.baseUrl, apiKey: gOpts.apiKey });
+      url = url.replace("{id}", encodeURIComponent(opts.id ?? ""));
+      const res = await apiFetch(url, { method: "GET", baseUrl: gOpts.baseUrl, apiKey: gOpts.apiKey });
+      const data = res.ok ? await res.json() : await res.text();
+      emit(data, gOpts);
+    });
+  tag.command("put-api-combos-id-")
+    .description("Update combo")
+    .requiredOption("--id <id>", "")
+    .option("--body <jsonOrPath>", "JSON body or @path/to/file.json")
+    .action(async (opts, cmd) => {
+      const gOpts = cmd.optsWithGlobals();
+      let url = "/api/combos/{id}";
+      url = url.replace("{id}", encodeURIComponent(opts.id ?? ""));
+      let body;
+      if (opts.body) {
+        body = opts.body.startsWith("@")
+          ? JSON.parse(readFileSync(opts.body.slice(1), "utf8"))
+          : JSON.parse(opts.body);
+      }
+      const res = await apiFetch(url, { method: "PUT", body, baseUrl: gOpts.baseUrl, apiKey: gOpts.apiKey });
+      const data = res.ok ? await res.json() : await res.text();
+      emit(data, gOpts);
+    });
+  tag.command("patch-api-combos-id-")
+    .description("Update combo")
+    .requiredOption("--id <id>", "")
+    .option("--body <jsonOrPath>", "JSON body or @path/to/file.json")
+    .action(async (opts, cmd) => {
+      const gOpts = cmd.optsWithGlobals();
+      let url = "/api/combos/{id}";
+      url = url.replace("{id}", encodeURIComponent(opts.id ?? ""));
+      let body;
+      if (opts.body) {
+        body = opts.body.startsWith("@")
+          ? JSON.parse(readFileSync(opts.body.slice(1), "utf8"))
+          : JSON.parse(opts.body);
+      }
+      const res = await apiFetch(url, { method: "PATCH", body, baseUrl: gOpts.baseUrl, apiKey: gOpts.apiKey });
       const data = res.ok ? await res.json() : await res.text();
       emit(data, gOpts);
     });
   tag.command("delete-api-combos-id-")
     .description("Delete combo")
+    .requiredOption("--id <id>", "")
     .action(async (opts, cmd) => {
       const gOpts = cmd.optsWithGlobals();
       let url = "/api/combos/{id}";
+      url = url.replace("{id}", encodeURIComponent(opts.id ?? ""));
       const res = await apiFetch(url, { method: "DELETE", baseUrl: gOpts.baseUrl, apiKey: gOpts.apiKey });
       const data = res.ok ? await res.json() : await res.text();
       emit(data, gOpts);

bin/cli/api.mjs

@@ -52,6 +52,19 @@ function resolveUrl(path, opts) {
   return `${getBaseUrl(opts)}${path.startsWith("/") ? path : `/${path}`}`;
 }
 
+/** The machine-derived token is valid only for the local loopback server. */
+export function isLoopbackUrl(value) {
+  try {
+    const hostname = new URL(value).hostname.replace(/^\[|\]$/g, "").toLowerCase();
+    if (hostname === "localhost" || hostname === "::1") return true;
+    if (/^127(?:\.[0-9]{1,3}){3}$/.test(hostname)) return true;
+    if (/^::ffff:(?:127\.|7f[0-9a-f]{2}:)/i.test(hostname)) return true;
+    return false;
+  } catch {
+    return false;
+  }
+}
+
 export async function buildHeaders(opts) {
   const headers = new Headers(opts.headers || {});
   if (!headers.has("accept")) headers.set("accept", "application/json");
@@ -87,10 +100,17 @@ export async function buildHeaders(opts) {
   if (auth && !headers.has("authorization")) {
     headers.set("authorization", `Bearer ${auth}`);
   }
-  // Inject machine-id derived CLI token; env var override for testing.
-  const cliToken = opts.cliToken ?? process.env.OMNIROUTE_CLI_TOKEN ?? (await getCliToken());
-  if (cliToken && !headers.has(CLI_TOKEN_HEADER)) {
-    headers.set(CLI_TOKEN_HEADER, cliToken);
+  // Inject the machine-derived credential only for an explicit local loopback
+  // destination. Remote contexts and absolute remote URLs use scoped access
+  // tokens and must never receive this machine-bound local credential.
+  const destinationUrl = opts.destinationUrl ?? getBaseUrl(opts);
+  if (!isLoopbackUrl(destinationUrl)) {
+    headers.delete(CLI_TOKEN_HEADER);
+  } else {
+    const cliToken = opts.cliToken ?? process.env.OMNIROUTE_CLI_TOKEN ?? (await getCliToken());
+    if (cliToken && !headers.has(CLI_TOKEN_HEADER)) {
+      headers.set(CLI_TOKEN_HEADER, cliToken);
+    }
   }
   if (opts.idempotencyKey && !headers.has("idempotency-key")) {
     headers.set("idempotency-key", opts.idempotencyKey);
@@ -195,8 +215,12 @@ function fetchOnce(url, init, timeoutMs) {
 export async function apiFetch(path, opts = {}) {
   const method = String(opts.method || "GET").toUpperCase();
   const url = resolveUrl(path, opts);
-  const headers = await buildHeaders(opts);
+  const headers = await buildHeaders({ ...opts, destinationUrl: url });
   const body = serializeBody(opts.body, headers);
+  // Undici preserves custom headers across cross-origin redirects. A local server
+  // redirect must never turn the loopback machine credential into an outbound
+  // secret, so fail redirects whenever this header is present.
+  const redirect = headers.has(CLI_TOKEN_HEADER) ? "error" : opts.redirect;
   const timeout =
     opts.timeout ?? (Number.parseInt(process.env.OMNIROUTE_HTTP_TIMEOUT_MS || "", 10) || 30000);
   const maxAttempts = opts.retry === false ? 1 : (opts.retryMax ?? RETRY_DEFAULTS.maxAttempts);
@@ -205,7 +229,7 @@ export async function apiFetch(path, opts = {}) {
   let lastErr;
   for (let attempt = 1; attempt <= maxAttempts; attempt++) {
     try {
-      const res = await fetchOnce(url, { method, headers, body }, timeout);
+      const res = await fetchOnce(url, { method, headers, body, redirect }, timeout);
       if (res.ok) return enrichResponse(res, opts);
       if (attempt < maxAttempts && shouldRetryStatus(res.status, method, opts)) {
         const delay = computeBackoff(attempt, res.headers.get("retry-after"));

bin/cli/commands/auth-export.mjs

@@ -22,8 +22,15 @@ const VALID_FORMATS = new Set(["json", "env"]);
 const SECURE_FILE_MODE = 0o600;
 
 export function registerAuthExport(program) {
+  // #11226: `.command("auth export")` does NOT register a two-word command — commander
+  // parses the bare word `export` as a required positional argument of `auth`, so the
+  // action received (exportArgValue, options, command) while expecting (options, command)
+  // and crashed with "cmd.optsWithGlobals is not a function". Register `export` as a
+  // proper nested subcommand instead; the CLI surface stays `omniroute auth export`.
   program
-    .command("auth export")
+    .command("auth")
+    .description(t("authExport.description"))
+    .command("export")
     .description(t("authExport.description"))
     .option("--id <id>", t("authExport.idOpt"))
     .option("--format <format>", t("authExport.formatOpt"), "json")

bin/cli/commands/combo.mjs

@@ -3,7 +3,9 @@ import { printHeading } from "../io.mjs";
 import { withRuntime } from "../runtime.mjs";
 import { t } from "../i18n.mjs";
 import { apiFetch } from "../api.mjs";
+import { mcpCallTool } from "../mcpClient.mjs";
 import { emit } from "../output.mjs";
+import { resolveComboModels, collectModel } from "./comboModels.mjs";
 
 const VALID_STRATEGIES = [
   "priority",
@@ -62,15 +64,7 @@ export function extendComboSuggest(combo) {
         weights: opts.weights ? JSON.parse(opts.weights) : undefined,
         top: opts.top,
       };
-      const res = await apiFetch("/api/mcp/tools/call", {
-        method: "POST",
-        body: { name: "omniroute_best_combo_for_task", arguments: body },
-      });
-      if (!res.ok) {
-        process.stderr.write(`Error: ${res.status}\n`);
-        process.exit(1);
-      }
-      const data = await res.json();
+      const data = await mcpCallTool("omniroute_best_combo_for_task", body);
       const candidates = data.candidates ?? data;
       const rows = (Array.isArray(candidates) ? candidates : []).map((c, i) => ({
         rank: i + 1,
@@ -125,10 +119,31 @@ export function registerCombo(program) {
         .choices(VALID_STRATEGIES)
         .default("priority")
     )
+    .option(
+      "--models <spec>",
+      "Models for the combo: comma-separated provider/model entries, or a JSON array " +
+        '(e.g. --models "openai/gpt-4o,anthropic/claude-3-opus" or ' +
+        '--models \'[{"model":"gpt-4o","providerId":"openai"}]\')'
+    )
+    .option(
+      "--model <spec>",
+      "Add one model to the combo (provider/model or bare model id) — repeatable",
+      collectModel,
+      []
+    )
     .action(async (name, opts, cmd) => {
       const globalOpts = cmd.parent.optsWithGlobals();
+      let models;
+      try {
+        models = resolveComboModels(opts);
+      } catch (err) {
+        console.error(`Error: ${err instanceof Error ? err.message : String(err)}`);
+        process.exit(1);
+        return;
+      }
       const exitCode = await runComboCreateCommand(name, opts.strategy, {
         ...opts,
+        models,
         output: globalOpts.output,
       });
       if (exitCode !== 0) process.exit(exitCode);
@@ -284,12 +299,20 @@ export async function runComboCreateCommand(name, strategy = "priority", opts =
     return 1;
   }
 
+  const models = Array.isArray(opts.models) ? opts.models : [];
+  if (!models.length) {
+    console.error(
+      "combo create requires at least one target. Pass --models <provider/model,...> and/or repeat --model <provider/model>."
+    );
+    return 1;
+  }
+
   try {
     return await withRuntime(async ({ kind, api, db }) => {
       if (kind === "http") {
         const res = await api("/api/combos", {
           method: "POST",
-          body: { name, strategy, enabled: true, models: [], config: {} },
+          body: { name, strategy, enabled: true, models, config: {} },
           retry: false,
           acceptNotOk: true,
         });
@@ -305,7 +328,7 @@ export async function runComboCreateCommand(name, strategy = "priority", opts =
           console.error(`Combo '${name}' already exists. Delete it first.`);
           return 1;
         }
-        await db.combos.createCombo({ name, strategy, enabled: true, models: [], config: {} });
+        await db.combos.createCombo({ name, strategy, enabled: true, models, config: {} });
       }
 
       console.log(t("combo.created", { name }));

bin/cli/commands/comboModels.mjs

@@ -0,0 +1,142 @@
+// Parses the `--models` / `--model` options for `omniroute combo create` (#10954).
+//
+// Root cause of #10954: `combo create` only ever registered `--strategy`; the
+// HTTP body (POST /api/combos) and the local-db fallback (db.combos.createCombo)
+// both hardcoded `models: []`, so every combo created via the CLI came out
+// empty regardless of what the operator intended to route to.
+//
+// Accepted shapes mirror the server-side Zod union in
+// `src/shared/validation/schemas/combo.ts` (`comboModelEntry` /
+// `createComboSchema.models`) so a CLI-built payload never gets rejected by
+// the API that ultimately validates it:
+//   - a plain string ("provider/model" or a bare model id) — the server's
+//     `normalizeComboModels` (src/lib/combos/steps.ts) already splits the
+//     leading "provider/" segment off a plain string, so passing the raw
+//     token through is sufficient for the common case;
+//   - a structured `{ kind?: "model", model, providerId?, provider?, ... }`
+//     object;
+//   - a structured `{ kind: "combo-ref", comboName, ... }` object (nested
+//     combo reference).
+//
+// The CLI (bin/cli/**) ships as plain `.mjs` with relative-only imports — no
+// `@/` path aliases and no TS transpilation at runtime — so importing the
+// real Zod schema from `src/shared/validation/schemas/combo.ts` is not
+// viable here. This module instead validates the same minimal shape by hand
+// and stays a thin, independently testable unit.
+
+/**
+ * Validates one already-parsed combo model entry against the shape accepted
+ * by `comboModelEntry` (string | model-step | combo-ref). Throws with a
+ * 1-based, human-readable position when the entry does not match.
+ *
+ * @param {unknown} entry
+ * @param {number} index
+ * @returns {string | Record<string, unknown>}
+ */
+export function validateComboModelEntryShape(entry, index) {
+  const position = index + 1;
+
+  if (typeof entry === "string") {
+    const trimmed = entry.trim();
+    if (trimmed.length === 0) {
+      throw new Error(`--models entry #${position}: empty model string`);
+    }
+    if (trimmed.length > 300) {
+      throw new Error(`--models entry #${position}: model string exceeds 300 characters`);
+    }
+    return trimmed;
+  }
+
+  if (entry === null || typeof entry !== "object" || Array.isArray(entry)) {
+    throw new Error(`--models entry #${position}: must be a string or a JSON object`);
+  }
+
+  const kind = entry.kind;
+
+  if (kind === "combo-ref") {
+    if (typeof entry.comboName !== "string" || entry.comboName.trim().length === 0) {
+      throw new Error(
+        `--models entry #${position}: kind "combo-ref" requires a non-empty "comboName"`
+      );
+    }
+    return entry;
+  }
+
+  if (kind !== undefined && kind !== "model") {
+    throw new Error(`--models entry #${position}: unknown "kind" value ${JSON.stringify(kind)}`);
+  }
+
+  if (typeof entry.model !== "string" || entry.model.trim().length === 0) {
+    throw new Error(`--models entry #${position}: requires a non-empty "model"`);
+  }
+  if (entry.providerId !== undefined && typeof entry.providerId !== "string") {
+    throw new Error(`--models entry #${position}: "providerId" must be a string`);
+  }
+  if (entry.provider !== undefined && typeof entry.provider !== "string") {
+    throw new Error(`--models entry #${position}: "provider" must be a string`);
+  }
+
+  return entry;
+}
+
+/**
+ * Parses one `--models` spec — either a JSON array (`--models '[{"model":"gpt-4o"}]'`)
+ * or a comma-separated list of provider/model tokens
+ * (`--models 'openai/gpt-4o,anthropic/claude-3-opus'`) — into an array of
+ * combo model entries.
+ *
+ * @param {string} spec
+ * @returns {Array<string | Record<string, unknown>>}
+ */
+export function parseModelsSpec(spec) {
+  const trimmed = String(spec ?? "").trim();
+  if (trimmed.length === 0) return [];
+
+  if (trimmed.startsWith("[")) {
+    let parsed;
+    try {
+      parsed = JSON.parse(trimmed);
+    } catch (err) {
+      throw new Error(`--models: invalid JSON array (${err.message})`);
+    }
+    if (!Array.isArray(parsed)) {
+      throw new Error("--models: JSON value must be an array");
+    }
+    return parsed.map((entry, i) => validateComboModelEntryShape(entry, i));
+  }
+
+  return trimmed
+    .split(",")
+    .map((token) => token.trim())
+    .filter((token) => token.length > 0)
+    .map((token, i) => validateComboModelEntryShape(token, i));
+}
+
+/**
+ * Resolves the final `models` array for `combo create` from Commander opts:
+ * `--models <csv-or-json>` and/or repeatable `--model <spec>`.
+ *
+ * @param {{ models?: string, model?: string[] }} opts
+ * @returns {Array<string | Record<string, unknown>>}
+ */
+export function resolveComboModels(opts = {}) {
+  const result = [];
+
+  if (typeof opts.models === "string" && opts.models.trim().length > 0) {
+    result.push(...parseModelsSpec(opts.models));
+  }
+
+  if (Array.isArray(opts.model)) {
+    opts.model.forEach((token, i) => {
+      result.push(validateComboModelEntryShape(String(token).trim(), i));
+    });
+  }
+
+  return result;
+}
+
+/** Commander `collect`-style reducer for the repeatable `--model` option. */
+export function collectModel(value, previous) {
+  previous.push(value);
+  return previous;
+}

bin/cli/commands/compression.mjs

@@ -1,5 +1,6 @@
 import { readFileSync } from "node:fs";
 import { apiFetch } from "../api.mjs";
+import { mcpCallTool } from "../mcpClient.mjs";
 import { emit } from "../output.mjs";
 import { t } from "../i18n.mjs";
 
@@ -78,18 +79,17 @@ async function restComboStats(period) {
 }
 
 async function mcpCall(name, args, restFallback) {
-  const res = await apiFetch("/api/mcp/tools/call", {
-    method: "POST",
-    body: { name, arguments: args },
-  });
-  if (res.ok) return res.json();
-  // 404 = MCP tool surface not mounted on this build; 501 = not implemented.
-  // Anything else is a genuine error and we surface it.
-  if ((res.status === 404 || res.status === 501) && typeof restFallback === "function") {
-    return restFallback();
+  try {
+    return await mcpCallTool(name, args);
+  } catch (err) {
+    // Keep the REST fallback behavior for builds where the MCP surface
+    // is unreachable / not mounted. Anything else rethrows as an error.
+    const status = err?.status || err?.cause?.status;
+    if ((status === 404 || status === 501) && typeof restFallback === "function") {
+      return restFallback();
+    }
+    throw err;
   }
-  process.stderr.write(`Error: ${res.status}\n`);
-  process.exit(1);
 }
 
 async function confirm(q) {

bin/cli/commands/doctor.mjs

@@ -4,7 +4,9 @@ import os from "node:os";
 import path from "node:path";
 import { createDecipheriv, scryptSync } from "node:crypto";
 import { fileURLToPath, pathToFileURL } from "node:url";
+import { isLoopbackUrl } from "../api.mjs";
 import { resolveDataDir, resolveStoragePath } from "../data-dir.mjs";
+import { getCliToken, CLI_TOKEN_HEADER } from "../utils/cliToken.mjs";
 import { printHeading } from "../io.mjs";
 import { t } from "../i18n.mjs";
 import { readDatabaseHealth, readEncryptedCredentialSamples } from "../sqlite.mjs";
@@ -378,11 +380,11 @@ function checkMemory() {
   });
 }
 
-async function fetchWithTimeout(url) {
+async function fetchWithTimeout(url, options = {}) {
   const controller = new AbortController();
   const timeout = setTimeout(() => controller.abort(), CHECK_TIMEOUT_MS);
   try {
-    return await fetch(url, { signal: controller.signal });
+    return await fetch(url, { ...options, signal: controller.signal });
   } finally {
     clearTimeout(timeout);
   }
@@ -471,6 +473,98 @@ async function checkServerLiveness(options = {}) {
   );
 }
 
+export async function checkMachineTokenAuth(options = {}) {
+  if (process.env.OMNIROUTE_DISABLE_CLI_TOKEN === "true") {
+    return warn("CLI machine token", "CLI machine-token authentication is disabled", {
+      derived: false,
+      accepted: false,
+      disabled: true,
+      tokenExposed: false,
+    });
+  }
+
+  let url;
+  try {
+    const parsed = new URL(resolveLivenessUrl(options));
+    if (
+      !["http:", "https:"].includes(parsed.protocol) ||
+      parsed.username ||
+      parsed.password ||
+      !isLoopbackUrl(parsed.toString())
+    ) {
+      return warn(
+        "CLI machine token",
+        "Machine-token probes are limited to HTTP(S) loopback endpoints",
+        { derived: false, accepted: false, tokenExposed: false }
+      );
+    }
+    parsed.pathname = "/api/cli/whoami";
+    parsed.search = "";
+    parsed.hash = "";
+    url = parsed.toString();
+  } catch {
+    return warn("CLI machine token", "Could not resolve the management endpoint", {
+      derived: false,
+      accepted: false,
+      tokenExposed: false,
+    });
+  }
+
+  const token = await getCliToken();
+  if (!token) {
+    return fail(
+      "CLI machine token",
+      "Could not derive a machine token; verify the node-machine-id runtime is installed",
+      { derived: false, accepted: false, tokenExposed: false }
+    );
+  }
+
+  try {
+    const response = await fetchWithTimeout(url, {
+      headers: { [CLI_TOKEN_HEADER]: token },
+      redirect: "error",
+    });
+    if (response.ok) {
+      return ok("CLI machine token", "Server accepted the local machine token", {
+        url,
+        status: response.status,
+        derived: true,
+        accepted: true,
+        tokenExposed: false,
+      });
+    }
+    if (response.status === 401 || response.status === 403) {
+      return warn(
+        "CLI machine token",
+        "Server rejected the local machine token; if the CLI and server are on different hosts or container boundaries, run `omniroute connect <host> --key <oma_live_...>`",
+        {
+          url,
+          status: response.status,
+          derived: true,
+          accepted: false,
+          containerBoundaryLikely: true,
+          tokenExposed: false,
+        }
+      );
+    }
+    return warn("CLI machine token", `Machine-token probe returned HTTP ${response.status}`, {
+      url,
+      status: response.status,
+      derived: true,
+      accepted: false,
+      tokenExposed: false,
+    });
+  } catch {
+    return warn("CLI machine token", "Machine-token endpoint could not be reached", {
+      url,
+      status: 0,
+      derived: true,
+      accepted: false,
+      tokenExposed: false,
+    });
+  }
+}
+
 export async function collectDoctorChecks(context = {}, options = {}) {
   const rootDir =
     context.rootDir || path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..", "..", "..");
@@ -488,6 +582,7 @@ export async function collectDoctorChecks(context = {}, options = {}) {
 
   if (!options.skipLiveness) {
     checks.push(await checkServerLiveness(options));
+    checks.push(await checkMachineTokenAuth(options));
   }
 
   // CLI tool health checks

bin/cli/commands/mcp.mjs

@@ -61,27 +61,12 @@ export function registerMcp(program) {
             ? JSON.parse(argsPositional)
             : {};
 
-      if (opts.stream) {
-        await runMcpStream(tool, args, globalOpts);
-        return;
-      }
+      const exitCode = await runMcpCallCommand(tool, args, {
+        ...opts,
+        stream: opts.stream,
+      }, globalOpts);
 
-      const extraHeaders = opts.scope?.length ? { "X-MCP-Scopes": opts.scope.join(",") } : {};
-      const res = await apiFetch("/api/mcp/tools/call", {
-        method: "POST",
-        body: { name: tool, arguments: args },
-        headers: extraHeaders,
-      });
-      if (res.status === 403) {
-        process.stderr.write("Scope denied\n");
-        process.exit(4);
-      }
-      if (!res.ok) {
-        process.stderr.write(`Error: ${res.status}\n`);
-        process.exit(1);
-      }
-      const data = await res.json();
-      emit(data, globalOpts);
+      if (exitCode !== 0) process.exit(exitCode);
     });
 
   mcp
@@ -99,112 +84,132 @@ export function registerMcp(program) {
       const data = await res.json();
       emit(data.scopes ?? data, cmd.optsWithGlobals());
     });
-
-  // 5.2 — mcp tools + mcp audit
-  const tools = mcp.command("tools").description(t("mcp.tools.description"));
-
-  tools
-    .command("list")
-    .description(t("mcp.tools.list.description"))
-    .option("--scope <s>", t("mcp.tools.list.scope"))
-    .action(async (opts, cmd) => {
-      const params = new URLSearchParams();
-      if (opts.scope) params.set("scope", opts.scope);
-      const res = await apiFetch(`/api/mcp/tools?${params}`);
-      if (!res.ok) {
-        process.stderr.write(`Error: ${res.status}\n`);
-        process.exit(1);
-      }
-      const data = await res.json();
-      emit(data.tools ?? data, cmd.optsWithGlobals(), mcpToolSchema);
-    });
-
-  tools
-    .command("info <name>")
-    .description(t("mcp.tools.info.description"))
-    .action(async (name, opts, cmd) => {
-      const res = await apiFetch(`/api/mcp/tools?name=${encodeURIComponent(name)}`);
-      if (!res.ok) {
-        process.stderr.write(`Not found: ${name}\n`);
-        process.exit(1);
-      }
-      emit(await res.json(), cmd.optsWithGlobals());
-    });
-
-  tools
-    .command("schema <name>")
-    .description(t("mcp.tools.schema.description"))
-    .option("--io <kind>", t("mcp.tools.schema.io"), "input")
-    .action(async (name, opts, cmd) => {
-      const res = await apiFetch(`/api/mcp/tools?name=${encodeURIComponent(name)}&io=${opts.io}`);
-      if (!res.ok) {
-        process.stderr.write(`Not found: ${name}\n`);
-        process.exit(1);
-      }
-      const data = await res.json();
-      const globalOpts = cmd.optsWithGlobals();
-      if (globalOpts.output === "json") {
-        process.stdout.write(JSON.stringify(data.schema ?? data, null, 2) + "\n");
-      } else {
-        emit(data.schema ?? data, globalOpts);
-      }
-    });
-
-  const audit = mcp.command("audit").description(t("mcp.audit.description"));
-
-  audit
-    .command("tail")
-    .option("--follow", t("audit.tail.follow"))
-    .option("--limit <n>", t("audit.tail.limit"), parseInt, 100)
-    .action(async (opts, cmd) => {
-      const { runAuditTail } = await import("./audit.mjs");
-      await runAuditTail({ ...opts, source: "mcp" }, cmd);
-    });
-
-  audit
-    .command("stats")
-    .option("--period <p>", t("audit.stats.period"), "7d")
-    .action(async (opts, cmd) => {
-      const res = await apiFetch(`/api/mcp/audit/stats?period=${opts.period}`);
-      if (!res.ok) {
-        process.stderr.write(`Error: ${res.status}\n`);
-        process.exit(1);
-      }
-      emit(await res.json(), cmd.optsWithGlobals());
-    });
 }
 
-async function runMcpStream(tool, args, globalOpts) {
+/**
+ * Shared JSON-RPC 2.0 MCP client used by both stream and non-stream `mcp call`.
+ *
+ * Protocol:
+ *   1. POST /api/mcp/stream with initialize → get Mcp-Session-Id header
+ *   2. POST /api/mcp/stream with tools/call + Mcp-Session-Id header
+ *
+ * When `stream` is true, writes SSE data chunks to stdout as they arrive.
+ * When `stream` is false, returns the parsed JSON-RPC result.
+ *
+ * Returns the exit code (0 = success, non-zero = failure).
+ */
+async function mcpJsonRpcCall(tool, args, { stream = false, globalOpts = {} } = {}) {
   const baseUrl = globalOpts.baseUrl ?? "http://localhost:20128";
   const apiKey = globalOpts.apiKey ?? "";
-  const res = await fetch(`${baseUrl}/api/mcp/stream`, {
+  const streamUrl = `${baseUrl}/api/mcp/stream`;
+
+  const hdrs = {
+    "Content-Type": "application/json",
+    Accept: stream ? "text/event-stream" : "application/json",
+    ...(apiKey ? { Authorization: `Bearer ${apiKey}` } : {}),
+  };
+
+  // Step 1 — initialize
+  const initRes = await fetch(streamUrl, {
     method: "POST",
-    headers: {
-      "Content-Type": "application/json",
-      ...(apiKey ? { Authorization: `Bearer ${apiKey}` } : {}),
-    },
-    body: JSON.stringify({ name: tool, arguments: args }),
+    headers: hdrs,
+    body: JSON.stringify({
+      jsonrpc: "2.0",
+      id: 1,
+      method: "initialize",
+      params: {
+        protocolVersion: "2024-11-05",
+        capabilities: {},
+        clientInfo: { name: "omniroute-cli", version: "1.0" },
+      },
+    }),
   });
-  if (!res.ok) {
-    process.stderr.write(`HTTP ${res.status}\n`);
-    process.exit(1);
+
+  if (!initRes.ok) {
+    const text = await initRes.text().catch(() => "");
+    process.stderr.write(`MCP initialize failed: HTTP ${initRes.status}${text ? ` — ${text}` : ""}\n`);
+    return 1;
   }
-  const reader = res.body.getReader();
+
+  const sessionId = initRes.headers.get("mcp-session-id");
+  if (!sessionId) {
+    process.stderr.write("MCP initialize failed: no Mcp-Session-Id in response\n");
+    return 1;
+  }
+
+  // Step 2 — tools/call
+  const callHeaders = {
+    ...hdrs,
+    "mcp-session-id": sessionId,
+  };
+
+  const callRes = await fetch(streamUrl, {
+    method: "POST",
+    headers: callHeaders,
+    body: JSON.stringify({
+      jsonrpc: "2.0",
+      id: 2,
+      method: "tools/call",
+      params: { name: tool, arguments: args },
+    }),
+  });
+
+  if (!callRes.ok) {
+    const text = await callRes.text().catch(() => "");
+    process.stderr.write(`MCP call failed: HTTP ${callRes.status}${text ? ` — ${text}` : ""}\n`);
+    return 1;
+  }
+
+  if (stream) {
+    return readMcpSseStream(callRes.body);
+  }
+
+  // Non-stream: parse JSON-RPC response
+  const data = await callRes.json();
+  if (data.error) {
+    process.stderr.write(`MCP error: ${data.error.message || JSON.stringify(data.error)}\n`);
+    return 1;
+  }
+  // Print the result content
+  const content = data.result?.content;
+  if (content) {
+    for (const item of content) {
+      if (item.type === "text") {
+        process.stdout.write(item.text + "\n");
+      } else if (item.type === "resource") {
+        process.stdout.write(JSON.stringify(item.resource) + "\n");
+      } else {
+        process.stdout.write(JSON.stringify(item) + "\n");
+      }
+    }
+  } else {
+    process.stdout.write(JSON.stringify(data.result, null, 2) + "\n");
+  }
+  return 0;
+}
+
+async function readMcpSseStream(body) {
+  if (!body) return 1;
+  const reader = body.getReader();
   const dec = new TextDecoder();
   let buf = "";
   while (true) {
     const { done, value } = await reader.read();
     if (done) break;
     buf += dec.decode(value, { stream: true });
-    const lines = buf.split("\n");
-    buf = lines.pop() ?? "";
-    for (const line of lines) {
-      if (line.startsWith("data: ")) {
-        const raw = line.slice(6).trim();
-        if (raw && raw !== "[DONE]") process.stdout.write(raw + "\n");
-      }
+  }
+  const lines = buf.split("\n");
+  for (const line of lines) {
+    if (line.startsWith("data: ")) {
+      const raw = line.slice(6).trim();
+      if (raw && raw !== "[DONE]") process.stdout.write(raw + "\n");
     }
   }
+  return 0;
+}
+
+export async function runMcpCallCommand(tool, args, opts = {}, globalOpts = {}) {
+  return mcpJsonRpcCall(tool, args, { stream: opts.stream, globalOpts });
 }
 
 export async function runMcpStatusCommand(opts = {}) {
@@ -233,7 +238,8 @@ export async function runMcpStatusCommand(opts = {}) {
     }
 
     const transport = status.transport || "stdio";
-    console.log(status.running ? t("mcp.running", { transport }) : t("mcp.stopped"));
+    const online = status.online ?? status.running;
+    console.log(online ? t("mcp.running", { transport }) : t("mcp.stopped"));
     if (status.toolsCount !== undefined) console.log(`  Tools: ${status.toolsCount}`);
     if (status.scopes?.length) {
       console.log("  Scopes:");

bin/cli/commands/oauth.mjs

@@ -228,20 +228,37 @@ async function runSocialFlow(def, opts) {
 
 async function runDeviceFlow(def, opts) {
   const providerKey = resolveBackendKey(def.id);
-  const startRes = await apiFetch(`/api/providers/${providerKey}/auth/start`, {
-    ...targetApiOptions(opts),
-    method: "POST",
-  });
+  let startRes = await apiFetch(`/api/oauth/${providerKey}/device-code`, targetApiOptions(opts));
+  if (!startRes.ok) {
+    startRes = await apiFetch(`/api/providers/${providerKey}/auth/start`, {
+      ...targetApiOptions(opts),
+      method: "POST",
+    });
+  }
   if (!startRes.ok) {
     process.stderr.write(`Failed to start device flow: ${startRes.status}\n`);
     process.exit(1);
   }
   const start = await startRes.json();
-  process.stdout.write(
-    `\nDevice code: ${start.userCode ?? start.user_code ?? ""}\nVisit: ${start.verificationUri ?? start.verification_uri}\n\n`
-  );
-  if (opts.browser !== false)
-    await openBrowser(start.verificationUri ?? start.verification_uri ?? "");
+  const userCode = start.userCode ?? start.user_code ?? "";
+  const verificationUri =
+    start.verificationUriComplete ??
+    start.verification_uri_complete ??
+    start.verificationUri ??
+    start.verification_uri ??
+    start.authUrl ??
+    start.url ??
+    "";
+
+  if (userCode) {
+    process.stdout.write(`\nDevice code: ${userCode}\nVisit: ${verificationUri}\n\n`);
+  } else if (verificationUri) {
+    process.stdout.write(`\nVisit: ${verificationUri}\n\n`);
+  } else {
+    process.stdout.write(`\nAuthorization URL not available\n\n`);
+  }
+
+  if (opts.browser !== false && verificationUri) await openBrowser(verificationUri);
   process.stderr.write("Waiting for device authorization...\n");
   const deadline = Date.now() + (opts.timeout ?? 300000);
   const intervalMs = (start.intervalMs ?? start.interval ?? 5) * 1000;
@@ -302,7 +319,18 @@ export async function runOAuthStatus(opts, cmd) {
     process.exit(1);
   }
   const data = await res.json();
-  const connections = (data.connections ?? data.providers ?? data.items ?? data).filter(
+  const payload = data?.connections ?? data?.providers ?? data?.items ?? data;
+  // #11236 (bug 5 residual): a 200 whose body is out of contract (no
+  // connections/providers/items array — e.g. `{"status":"ok"}`) used to fall
+  // through to `.filter` on a non-array and crash with a bare TypeError plus a
+  // libuv teardown assertion on Windows. Coerce to an empty list with a
+  // sanitized one-line warning instead of dumping a stack trace.
+  if (!Array.isArray(payload)) {
+    process.stderr.write(
+      "Warning: unexpected response shape from /api/providers; showing no connections.\n"
+    );
+  }
+  const connections = (Array.isArray(payload) ? payload : []).filter(
     (c) => c.authType === "oauth" || c.authType === "oauth2"
   );
   emit(connections, globalOpts, connectionSchema);

bin/cli/commands/oneproxy.mjs

@@ -1,4 +1,5 @@
 import { apiFetch } from "../api.mjs";
+import { mcpCallTool } from "../mcpClient.mjs";
 import { emit } from "../output.mjs";
 import { t } from "../i18n.mjs";
 
@@ -8,15 +9,7 @@ function fmtTs(v) {
 }
 
 async function mcpCall(name, args) {
-  const res = await apiFetch("/api/mcp/tools/call", {
-    method: "POST",
-    body: { name, arguments: args },
-  });
-  if (!res.ok) {
-    process.stderr.write(`MCP error: ${res.status}\n`);
-    process.exit(1);
-  }
-  return res.json();
+  return mcpCallTool(name, args);
 }
 
 const proxySchema = [

bin/cli/commands/plugin.mjs

@@ -9,10 +9,13 @@ import { discoverPlugins } from "../plugins.mjs";
 // (instead of string-interpolating into `execSync`) prevents a malicious plugin
 // name like `foo; rm -rf ~` or `` foo`id` `` from being interpreted by the shell.
 function runNpm(args) {
-  const res = spawnSync("npm", args, { stdio: "inherit", shell: false });
+  const isBun = Boolean(process.versions.bun);
+  const pm = isBun ? "bun" : "npm";
+  const cmdArgs = isBun && args[0] === "install" ? ["add", ...args.slice(1)] : args;
+  const res = spawnSync(pm, cmdArgs, { stdio: "inherit", shell: false });
   if (res.error) throw res.error;
   if (typeof res.status === "number" && res.status !== 0) {
-    throw new Error(`npm exited with code ${res.status}`);
+    throw new Error(`${pm} exited with code ${res.status}`);
   }
 }
 

bin/cli/commands/providers.mjs

@@ -129,7 +129,34 @@ function buildTestInput(connection, apiKey) {
   };
 }
 
-async function runProviderTest(db, connection) {
+async function testProviderConnectionThroughServer(connection) {
+  try {
+    const res = await apiFetch(`/api/providers/${encodeURIComponent(connection.id)}/test`, {
+      method: "POST",
+      body: {},
+      retry: false,
+      timeout: 30000,
+      acceptNotOk: true,
+    });
+    const data = res.ok ? await res.json() : { valid: false, error: `HTTP ${res.status}` };
+    return {
+      connection: publicConnection(connection),
+      ...data,
+      valid: data.valid === true,
+      skipped: false,
+    };
+  } catch (error) {
+    return {
+      connection: publicConnection(connection),
+      valid: false,
+      skipped: false,
+      error: error instanceof Error ? error.message : String(error),
+      statusCode: null,
+    };
+  }
+}
+
+async function runProviderTest(db, connection, { serverUp = false } = {}) {
   // Only API-key connections can be probed with a stored credential. OAuth /
   // no-auth connections have nothing for testProviderApiKey() to send, and
   // getProviderApiKey() throws for them by design — reporting that as a FAILED
@@ -151,6 +178,9 @@ async function runProviderTest(db, connection) {
     // means the CLI has no probe recipe, not that the provider is unhealthy.
     // Persisting it would overwrite a good test_status with a failure.
     if (result.unsupported) {
+      if (serverUp) {
+        return testProviderConnectionThroughServer(connection);
+      }
       return {
         connection: publicConnection(connection),
         ...result,
@@ -266,6 +296,7 @@ export async function runTestCommand(selector, opts = {}) {
 }
 
 export async function runTestAllCommand(opts = {}) {
+  const serverUp = await isServerUp();
   const { db } = await openOmniRouteDb();
   try {
     const connections = listProviderConnections(db);
@@ -280,7 +311,7 @@ export async function runTestAllCommand(opts = {}) {
         });
         continue;
       }
-      results.push(await runProviderTest(db, connection));
+      results.push(await runProviderTest(db, connection, { serverUp }));
     }
 
     if (opts.json) {

bin/cli/commands/resilience.mjs

@@ -1,6 +1,7 @@
 import { createInterface } from "node:readline";
 import { Argument } from "commander";
 import { apiFetch } from "../api.mjs";
+import { mcpCallTool } from "../mcpClient.mjs";
 import { emit } from "../output.mjs";
 import { t } from "../i18n.mjs";
 
@@ -166,14 +167,7 @@ export function registerResilience(program) {
       ])
     )
     .action(async (name, opts, cmd) => {
-      const res = await apiFetch("/api/mcp/tools/call", {
-        method: "POST",
-        body: { name: "omniroute_set_resilience_profile", arguments: { profile: name } },
-      });
-      if (!res.ok) {
-        process.stderr.write(`Error: ${res.status}\n`);
-        process.exit(1);
-      }
+      await mcpCallTool("omniroute_set_resilience_profile", { profile: name });
       process.stdout.write(`Profile: ${name}\n`);
     });
 

bin/cli/commands/serve.mjs

@@ -1,7 +1,7 @@
 import { spawn } from "node:child_process";
 import { existsSync, readFileSync } from "node:fs";
 import { join, dirname } from "node:path";
-import { fileURLToPath } from "node:url";
+import { fileURLToPath, pathToFileURL } from "node:url";
 import { platform, totalmem } from "node:os";
 import { t } from "../i18n.mjs";
 import { writePidFile, cleanupPidFile, waitForServer } from "../utils/pid.mjs";
@@ -12,7 +12,7 @@ import {
   isFatalInstrumentationHookFailure,
   formatAndroidInstrumentationFailureHint,
 } from "../utils/ensureAndroidCacheDir.mjs";
-import { resolveServerHost } from "../utils/serverHost.mjs";
+import { resolveServerHost, resolveExposureWarning } from "../utils/serverHost.mjs";
 import {
   resolveMaxOldSpaceMb,
   calibrateHeapFallbackMb,
@@ -20,6 +20,7 @@ import {
   buildNodeHeapArgs,
 } from "../../../scripts/build/runtime-env.mjs";
 import { resolveTlsOptions } from "../../../scripts/dev/tls-options.mjs";
+import { startDetachedTray, validateTrayOptions } from "../tray/detachedTray.mjs";
 
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const _pkg = JSON.parse(readFileSync(join(__dirname, "..", "..", "..", "package.json"), "utf8"));
@@ -42,7 +43,7 @@ function parsePort(value, fallback) {
 }
 
 export function registerServe(program) {
-  program
+  const command = program
     .command("serve", { isDefault: true })
     .description(t("serve.description"))
     .option("--port <port>", t("serve.port"))
@@ -51,7 +52,7 @@ export function registerServe(program) {
     .option("--log", t("serve.log"))
     .option("--no-recovery", t("serve.no_recovery"))
     .option("--max-restarts <n>", t("serve.max_restarts"), parseInt, 2)
-    .option("--tray", t("serve.tray") || "Show system tray icon (desktop only)")
+    .option("--tray", t("serve.tray") || "Start in the system tray (desktop only)")
     .option("--no-tray", t("serve.no_tray") || "Disable system tray icon")
     .option(
       "--tls-cert <path>",
@@ -66,6 +67,9 @@ export function registerServe(program) {
     .action(async (opts) => {
       await runServe(opts);
     });
+  command.addOption(command.createOption("--tray-worker").hideHelp());
+  command.addOption(command.createOption("--tray-ready-port <port>").hideHelp());
+  command.addOption(command.createOption("--tray-ready-token <token>").hideHelp());
 }
 
 /** Once-per-process guard so the Android/Termux cache hint is not spammed. */
@@ -95,6 +99,32 @@ export function resetInstrumentationFailureHintForTests() {
 export async function runServe(opts = {}) {
   const startedAt = performance.now();
 
+  const trayOptionError = validateTrayOptions(opts);
+  if (trayOptionError) throw new Error(trayOptionError);
+
+  if (opts.tray === true && opts.trayWorker !== true) {
+    const port = parsePort(opts.port ?? process.env.PORT ?? "20128", 20128);
+    const tlsCert = opts.tlsCert ?? process.env.OMNIROUTE_TLS_CERT;
+    const tlsKey = opts.tlsKey ?? process.env.OMNIROUTE_TLS_KEY;
+    urlScheme = resolveTlsOptions({
+      ...process.env,
+      ...(tlsCert ? { OMNIROUTE_TLS_CERT: tlsCert } : {}),
+      ...(tlsKey ? { OMNIROUTE_TLS_KEY: tlsKey } : {}),
+    })
+      ? "https"
+      : "http";
+    const result = await startDetachedTray({
+      cliPath: join(ROOT, "bin", "omniroute.mjs"),
+      port,
+      maxRestarts: opts.maxRestarts ?? 2,
+      tlsCert,
+      tlsKey,
+    });
+    console.log(`\x1b[32m✔ OmniRoute tray started in background\x1b[0m`);
+    console.log(`  \x1b[1mDashboard:\x1b[0m  ${urlScheme}://localhost:${port}`);
+    return result;
+  }
+
   // Same prep as bin/omniroute.mjs — keep it here so a direct `runServe()` call
   // (tests / programmatic) still gets a writable Next.js cache dir before spawn.
   ensureAndroidCacheDir({ env: process.env });
@@ -132,6 +162,15 @@ export async function runServe(opts = {}) {
 `);
   }
 
+  // GHSA-wmgv-ph3p-rv57: the default posture (all interfaces + no API key) is a
+  // deliberate local-first choice, but it must be loud at startup — an operator
+  // on an untrusted network learns the two escape hatches here, not after a
+  // surprise quota bill.
+  const exposureWarning = resolveExposureWarning();
+  if (exposureWarning) {
+    console.warn(`\x1b[33m  ⚠  ${exposureWarning}\x1b[0m\n`);
+  }
+
   const serverWsJs = join(APP_DIR, "server-ws.mjs");
   const serverJs = existsSync(serverWsJs) ? serverWsJs : join(APP_DIR, "server.js");
 
@@ -255,7 +294,8 @@ export async function runServe(opts = {}) {
     opts.log === true,
     opts.maxRestarts ?? 2,
     startedAt,
-    useTray
+    useTray,
+    { trayReadyPort: opts.trayReadyPort, trayReadyToken: opts.trayReadyToken }
   );
 }
 
@@ -368,9 +408,11 @@ async function runWithSupervisor(
   showLog,
   maxRestarts,
   startedAt,
-  useTray = false
+  useTray = false,
+  { trayReadyPort, trayReadyToken } = {}
 ) {
   if (showLog) process.env.OMNIROUTE_SHOW_LOG = "1";
+  writePidFile("supervisor", process.pid);
 
   const supervisor = new ServerSupervisor({
     serverPath: serverJs,
@@ -381,7 +423,7 @@ async function runWithSupervisor(
       if (detectMitmCrash(crashLog)) {
         try {
           const PROJECT_ROOT = join(dirname(fileURLToPath(import.meta.url)), "..", "..", "..");
-          const { updateSettings } = await import(`${PROJECT_ROOT}/src/lib/db/settings.ts`);
+          const { updateSettings } = await import(pathToFileURL(join(PROJECT_ROOT, "src/lib/db/settings.ts")).href);
           updateSettings({ mitmEnabled: false });
         } catch {}
         return "disable-mitm-and-retry";
@@ -394,17 +436,38 @@ async function runWithSupervisor(
 
   process.on("SIGINT", () => {
     killTrayIfActive();
+    cleanupPidFile("supervisor");
     supervisor.stop();
   });
   process.on("SIGTERM", () => {
     killTrayIfActive();
+    cleanupPidFile("supervisor");
     supervisor.stop();
   });
 
   if (!showLog) {
     waitForServer(dashboardPort, 60000).then(async (up) => {
       if (up) {
-        if (useTray) await maybeStartTray(dashboardPort, apiPort, supervisor);
+        if (useTray) {
+          const trayReady = await maybeStartTray(dashboardPort, apiPort, supervisor);
+          if (!trayReady) {
+            cleanupPidFile("supervisor");
+            supervisor.stop();
+            process.exitCode = 1;
+            return;
+          }
+          if (trayReadyPort && trayReadyToken) {
+            const { notifyTrayReady } = await import("../tray/detachedTray.mjs");
+            try {
+              await notifyTrayReady(parsePort(trayReadyPort, 0), trayReadyToken);
+            } catch {
+              cleanupPidFile("supervisor");
+              supervisor.stop();
+              process.exitCode = 1;
+              return;
+            }
+          }
+        }
         onReady(dashboardPort, apiPort, noOpen, startedAt);
       } else {
         reportReadinessTimeout(dashboardPort, supervisor);
@@ -451,29 +514,30 @@ function killTrayIfActive() {
 async function maybeStartTray(port, apiPort, supervisor) {
   try {
     const { initTray, isTraySupported } = await import("../tray/index.mjs");
-    if (!isTraySupported()) return;
+    if (!isTraySupported()) return false;
     const { default: open } = await import("open").catch(() => ({ default: null }));
     const dashboardUrl = `${urlScheme}://localhost:${port}`;
     const tray = await initTray({
       port,
       onQuit: () => {
         killTrayIfActive();
+        cleanupPidFile("supervisor");
         supervisor.stop();
       },
       onOpenDashboard: () => open?.(dashboardUrl),
-      onShowLogs: () => {
-        // In-place: open logs stream (best-effort)
-        process.stdout.write(`[omniroute][tray] Logs at: ${dashboardUrl}/logs\n`);
-      },
+      onShowLogs: () => open?.(`${dashboardUrl}/dashboard/logs`),
     });
     if (tray) {
       const { killTray } = await import("../tray/index.mjs");
       _killTray = killTray;
+      return true;
     }
+    return false;
   } catch (err) {
     // tray is optional — do not fail the server, but surface why it failed so
     // "--tray shows nothing" is diagnosable instead of silent (#4605).
     process.stderr.write(`[omniroute][tray] failed to start: ${err?.message ?? String(err)}\n`);
+    return false;
   }
 }
 

bin/cli/commands/setup-claude.mjs

@@ -169,7 +169,8 @@ export async function runSetupClaudeCommand(opts = {}) {
       let detail = `HTTP ${res.status}`;
       try {
         const errorBody = await res.json();
-        const serverMsg = errorBody?.error?.message || errorBody?.error || errorBody?.message || "";
+        const serverMsg =
+          errorBody?.error?.message || errorBody?.error || errorBody?.message || "";
         if (serverMsg) detail += ` — ${serverMsg}`;
       } catch {}
       throw new Error(detail);

bin/cli/commands/setup.mjs

@@ -1,4 +1,4 @@
-import { fileURLToPath } from "node:url";
+import { fileURLToPath, pathToFileURL } from "node:url";
 import { dirname, resolve } from "node:path";
 import { createPrompt, printHeading, printInfo, printSuccess } from "../io.mjs";
 import { openOmniRouteDb } from "../sqlite.mjs";
@@ -16,7 +16,7 @@ import { t } from "../i18n.mjs";
 const PROJECT_ROOT = resolve(dirname(fileURLToPath(import.meta.url)), "../../..");
 
 async function getListCliTools() {
-  const { listCliTools } = await import(`${PROJECT_ROOT}/src/shared/constants/cliTools.ts`);
+  const { listCliTools } = await import(pathToFileURL(resolve(PROJECT_ROOT, "src/shared/constants/cliTools.ts")).href);
   return listCliTools;
 }
 

bin/cli/commands/skills.mjs

@@ -1,5 +1,6 @@
 import { readFileSync } from "node:fs";
 import { apiFetch } from "../api.mjs";
+import { mcpCallTool } from "../mcpClient.mjs";
 import { emit } from "../output.mjs";
 import { t } from "../i18n.mjs";
 
@@ -106,14 +107,7 @@ export async function runSkillsInstall(opts, cmd) {
 }
 
 export async function runSkillsEnable(id, opts, cmd) {
-  const res = await apiFetch("/api/mcp/tools/call", {
-    method: "POST",
-    body: { name: "omniroute_skills_enable", arguments: { skillId: id, enabled: true } },
-  });
-  if (!res.ok) {
-    process.stderr.write(`Error: ${res.status}\n`);
-    process.exit(1);
-  }
+  await mcpCallTool("omniroute_skills_enable", { skillId: id, enabled: true });
   process.stdout.write(`Enabled: ${id}\n`);
 }
 
@@ -122,14 +116,7 @@ export async function runSkillsDisable(id, opts, cmd) {
     const ok = await confirm(`Disable ${id}?`);
     if (!ok) return;
   }
-  const res = await apiFetch("/api/mcp/tools/call", {
-    method: "POST",
-    body: { name: "omniroute_skills_enable", arguments: { skillId: id, enabled: false } },
-  });
-  if (!res.ok) {
-    process.stderr.write(`Error: ${res.status}\n`);
-    process.exit(1);
-  }
+  await mcpCallTool("omniroute_skills_enable", { skillId: id, enabled: false });
   process.stdout.write(`Disabled: ${id}\n`);
 }
 
@@ -153,16 +140,11 @@ export async function runSkillsExecute(id, opts, cmd) {
     : opts.inputFile
       ? JSON.parse(readFileSync(opts.inputFile, "utf8"))
       : {};
-  const res = await apiFetch("/api/mcp/tools/call", {
-    method: "POST",
-    body: { name: "omniroute_skills_execute", arguments: { skillId: id, input } },
-    timeout: opts.timeout ?? 30000,
-  });
-  if (!res.ok) {
-    process.stderr.write(`Error: ${res.status}\n`);
-    process.exit(1);
-  }
-  const data = await res.json();
+  const data = await mcpCallTool(
+    "omniroute_skills_execute",
+    { skillId: id, input },
+    { timeout: opts.timeout ?? 30000 },
+  );
   emit(data, globalOpts);
 }
 

bin/cli/commands/test-provider.mjs

@@ -38,12 +38,19 @@ export async function runTestProviderCommand(provider, model, opts = {}) {
   }
 
   const targetProvider = provider || "anthropic";
-  const targetModel = model || "claude-haiku-4-5-20251001";
+  const connections = await _loadConnections();
+  if (!connections) return 1;
+  const connection = _resolveConnection(connections, targetProvider, model);
+  if (!connection) {
+    console.error(`Provider connection not found: ${targetProvider}`);
+    return 1;
+  }
+  const targetModel = model || connection.defaultModel;
   const repeat = opts.repeat && opts.repeat > 0 ? opts.repeat : 1;
 
   const results = [];
   for (let i = 0; i < repeat; i++) {
-    const result = await _runSingleTest(targetProvider, targetModel);
+    const result = await _runSingleTest(connection, targetModel);
     results.push(result);
   }
 
@@ -70,18 +77,10 @@ export async function runTestProviderCommand(provider, model, opts = {}) {
 }
 
 async function _runAllProviders(opts) {
-  const res = await apiFetch("/api/providers?limit=200", {
-    retry: false,
-    timeout: 5000,
-    acceptNotOk: true,
-  });
-  if (!res.ok) {
-    console.error(t("test.noServer"));
-    return 1;
-  }
-  const data = await res.json();
-  const connections = (data.connections ?? data.providers ?? data.items ?? data).filter(
-    (c) => c.authType === "apikey" || c.testStatus !== "unavailable"
+  const loaded = await _loadConnections();
+  if (!loaded) return 1;
+  const connections = loaded.filter(
+    (c) => c.isActive !== false && (c.authType === "apikey" || c.testStatus !== "unavailable")
   );
   if (connections.length === 0) {
     console.log(t("test.noProviders"));
@@ -89,6 +88,7 @@ async function _runAllProviders(opts) {
   }
 
   const providers = connections.map((c) => ({
+    connectionId: c.id,
     provider: c.provider ?? c.id,
     model: c.defaultModel ?? c.model,
   }));
@@ -102,8 +102,8 @@ async function _runAllProviders(opts) {
   }
 
   const results = await Promise.all(
-    providers.map(async ({ provider, model }) => {
-      const r = await _runSingleTest(provider, model);
+    providers.map(async ({ connectionId, provider, model }) => {
+      const r = await _runSingleTest({ id: connectionId }, model);
       return { provider, model, ...r };
     })
   );
@@ -123,6 +123,13 @@ async function _runAllProviders(opts) {
 
 async function _runCompare(provider, opts) {
   const targetProvider = provider || "anthropic";
+  const connections = await _loadConnections();
+  if (!connections) return 1;
+  const connection = _resolveConnection(connections, targetProvider);
+  if (!connection) {
+    console.error(`Provider connection not found: ${targetProvider}`);
+    return 1;
+  }
   const models = opts.compare
     .split(",")
     .map((m) => m.trim())
@@ -138,7 +145,7 @@ async function _runCompare(provider, opts) {
   for (const model of models) {
     const results = [];
     for (let i = 0; i < repeat; i++) {
-      const result = await _runSingleTest(targetProvider, model);
+      const result = await _runSingleTest(connection, model);
       results.push(result);
     }
     rows.push({ model, ..._aggregate(results, true) });
@@ -180,19 +187,55 @@ async function _runCompare(provider, opts) {
   return rows.every((r) => r.success) ? 0 : 1;
 }
 
-async function _runSingleTest(provider, model) {
+async function _loadConnections() {
+  const res = await apiFetch("/api/providers?limit=200", {
+    retry: false,
+    timeout: 5000,
+    acceptNotOk: true,
+  });
+  if (!res.ok) {
+    console.error(t("test.noServer"));
+    return null;
+  }
+  const data = await res.json();
+  const connections = data.connections ?? data.providers ?? data.items ?? data;
+  if (!Array.isArray(connections)) {
+    console.error(t("test.noServer"));
+    return null;
+  }
+  return connections;
+}
+
+function _resolveConnection(connections, selector, model) {
+  const normalized = String(selector || "")
+    .trim()
+    .toLowerCase();
+  const active = connections.filter((connection) => connection.isActive !== false);
+  return (
+    active.find((connection) => String(connection.id || "").toLowerCase() === normalized) ??
+    active.find((connection) => String(connection.name || "").toLowerCase() === normalized) ??
+    active.find(
+      (connection) =>
+        String(connection.provider || "").toLowerCase() === normalized &&
+        (!model || connection.defaultModel === model || connection.model === model)
+    ) ??
+    active.find((connection) => String(connection.provider || "").toLowerCase() === normalized)
+  );
+}
+
+async function _runSingleTest(connection, model) {
   const startMs = Date.now();
   try {
-    const res = await apiFetch("/api/v1/providers/test", {
+    const res = await apiFetch(`/api/providers/${encodeURIComponent(connection.id)}/test`, {
       method: "POST",
-      body: { provider, model },
+      body: model ? { validationModelId: model } : {},
       retry: false,
       timeout: 30000,
       acceptNotOk: true,
     });
     const durationMs = Date.now() - startMs;
-    const data = res.ok ? await res.json() : { success: false, error: `HTTP ${res.status}` };
-    return { ...data, durationMs };
+    const data = res.ok ? await res.json() : { valid: false, error: `HTTP ${res.status}` };
+    return { ...data, success: data.valid === true, durationMs };
   } catch (err) {
     const msg = err instanceof Error ? err.message : String(err);
     return {

bin/cli/commands/update.mjs

@@ -5,6 +5,7 @@ import { fileURLToPath } from "node:url";
 import { execFile } from "node:child_process";
 import { promisify } from "node:util";
 import { t } from "../i18n.mjs";
+import { npmBin, npmExecOptions } from "../npm-exec.mjs";
 
 const execFileAsync = promisify(execFile);
 
@@ -31,9 +32,13 @@ export async function getCurrentVersion() {
 // they were already on the latest version (#4376). `execFn` is injectable for tests.
 export async function getLatestVersion(execFn = execFileAsync) {
   try {
-    const { stdout } = await execFn("npm", ["view", "omniroute", "version", "--prefer-online"], {
-      timeout: 15000,
-    });
+    // argv is all literals, so enabling the shell on win32 cannot splice a
+    // runtime value into the command line (Hard Rule #13).
+    const { stdout } = await execFn(
+      npmBin(),
+      ["view", "omniroute", "version", "--prefer-online"],
+      npmExecOptions(process.platform, { timeoutMs: 15000 })
+    );
     return stdout.trim();
   } catch {
     return null;
@@ -114,9 +119,11 @@ export async function runUpdateCommand(opts = {}) {
 
   if (showChangelog) {
     try {
-      const { stdout } = await execFileAsync("npm", ["view", "omniroute", "changelog"], {
-        timeout: 10000,
-      });
+      const { stdout } = await execFileAsync(
+        npmBin(),
+        ["view", "omniroute", "changelog"],
+        npmExecOptions(process.platform, { timeoutMs: 15000 })
+      );
       if (stdout.trim()) {
         console.log(stdout.trim());
       } else {

bin/cli/locales/en.json

@@ -254,7 +254,7 @@
     "log": "Show server logs inline",
     "no_recovery": "Disable auto-restart on crash (debugging mode)",
     "max_restarts": "Max crash restarts within 30s before giving up (default: 2)",
-    "tray": "Show system tray icon (desktop only, opt-in)",
+    "tray": "Start in the system tray (desktop only, opt-in)",
     "no_tray": "Disable system tray icon",
     "tls_cert": "Path to a TLS certificate (PEM) to serve HTTPS (also OMNIROUTE_TLS_CERT)",
     "tls_key": "Path to the TLS private key (PEM) to serve HTTPS (also OMNIROUTE_TLS_KEY)"

bin/cli/locales/pt-BR.json

@@ -26,7 +26,8 @@
     "testFailed": "Teste do provedor falhou: {error}",
     "loginEnabled": "Login: habilitado (senha atualizada)",
     "loginDisabled": "Login: desabilitado",
-    "providerInfo": "Provedor: {info}"
+    "providerInfo": "Provedor: {info}",
+    "opencode": "Instala e configura o plugin @omniroute/opencode-plugin incluído para o OpenCode"
   },
   "doctor": {
     "title": "OmniRoute Doctor",
@@ -254,7 +255,9 @@
     "no_recovery": "Desabilitar reinício automático em crash (modo debug)",
     "max_restarts": "Máximo de reinícios em 30s antes de desistir (padrão: 2)",
     "tray": "Mostrar ícone na bandeja do sistema (apenas desktop, opt-in)",
-    "no_tray": "Desabilitar ícone na bandeja do sistema"
+    "no_tray": "Desabilitar ícone na bandeja do sistema",
+    "tls_cert": "Caminho para um certificado TLS (PEM) para servir HTTPS (também OMNIROUTE_TLS_CERT)",
+    "tls_key": "Caminho para a chave privada TLS (PEM) para servir HTTPS (também OMNIROUTE_TLS_KEY)"
   },
   "backup": {
     "title": "Backup",

bin/cli/locales/zh-CN.json

@@ -38,7 +38,8 @@
     "testFailed": "提供者测试失败：{error}",
     "loginEnabled": "登录：已启用（密码已更新）",
     "loginDisabled": "登录：已禁用",
-    "providerInfo": "提供者：{info}"
+    "providerInfo": "提供者：{info}",
+    "opencode": "安装并配置随附的 @omniroute/opencode-plugin 以用于 OpenCode"
   },
   "doctor": {
     "title": "OmniRoute 诊断",
@@ -252,7 +253,9 @@
     "no_recovery": "禁用崩溃自动重启（调试模式）",
     "max_restarts": "30 秒内的最大崩溃重启次数（默认：2）",
     "tray": "显示系统托盘图标（仅桌面，选择加入）",
-    "no_tray": "禁用系统托盘图标"
+    "no_tray": "禁用系统托盘图标",
+    "tls_cert": "用于提供 HTTPS 服务的 TLS 证书（PEM）路径（也可用 OMNIROUTE_TLS_CERT）",
+    "tls_key": "用于提供 HTTPS 服务的 TLS 私钥（PEM）路径（也可用 OMNIROUTE_TLS_KEY）"
   },
   "backup": {
     "title": "备份",
@@ -1258,5 +1261,69 @@
     "search": "搜索 npm 注册表中的可用插件",
     "update": "更新已安装的插件",
     "scaffold": "搭建新的插件模板"
+  },
+  "authExport": {
+    "description": "导出已解密的提供者凭据（仅限本地，明文输出）",
+    "idOpt": "仅导出与此 id/名称/提供者匹配的连接",
+    "formatOpt": "输出格式：json 或 env",
+    "outOpt": "将输出写入文件而非标准输出（以 0600 权限写入）",
+    "forceOpt": "确认你了解此操作会打印/写入明文密钥",
+    "warning": "⚠ 此操作会打印/写入已解密的明文 API 密钥和 OAuth 令牌。请确保你的屏幕、shell 历史记录以及任何输出文件保持私密。",
+    "confirmHeading": "⚠ 警告：此操作会以明文导出已解密的提供者凭据",
+    "confirmBody": "此命令会为所选连接解密并打印/写入 apiKey、accessToken、refreshToken 和\nidToken。请将输出视为机密。",
+    "confirmFooter": "如需确认，请运行：\n  omniroute auth export --force",
+    "missingKey": "导出凭据需要 STORAGE_ENCRYPTION_KEY。",
+    "notFound": "未找到连接：{id}",
+    "invalidFormat": "无效格式：{format}。请使用 json 或 env。"
+  },
+  "radar": {
+    "description": "检查并同步本地 Radar 目录订阅源",
+    "status": "显示本地 Radar 设置和订阅源缓存状态",
+    "sync": "通过本地服务器同步目录、推荐、优惠和 Intel"
+  },
+  "launch": {
+    "description": "启动指向 OmniRoute 的 Claude Code（本地或远程，使用 --profile）",
+    "token": "Claude 客户端应发送的令牌（ANTHROPIC_AUTH_TOKEN）",
+    "notRunning": "无法在 {port} 访问 OmniRoute。请使用 “omniroute serve” 启动它。",
+    "notFound": "在 PATH 中未找到 “claude” CLI。"
+  },
+  "run": {
+    "description": "通过 OmniRoute 启动受支持的 CLI 目标"
+  },
+  "setupClaude": {
+    "description": "从 OmniRoute 模型目录生成 ~/.claude/profiles 的 Claude Code 配置文件"
+  },
+  "connect": {
+    "description": "连接到远程 OmniRoute 服务器并进入远程模式"
+  },
+  "tokens": {
+    "description": "管理限定范围的 CLI 访问令牌（远程模式）"
+  },
+  "configure": {
+    "description": "从活动服务器选择提供者+模型并配置受支持的本地 CLI"
+  },
+  "launchCodex": {
+    "description": "启动指向 OmniRoute 的 Codex CLI（本地或远程 VPS）"
+  },
+  "setupCodex": {
+    "description": "从 OmniRoute 实时模型目录生成 ~/.codex 配置文件"
+  },
+  "packs": {
+    "description": "管理可选的运行时包（ML / 浏览器自动化）",
+    "listDescription": "列出可选包及其安装状态",
+    "installDescription": "将可选包安装到 DATA_DIR",
+    "verifyDescription": "根据随附的校验和索引验证已安装的包",
+    "removeDescription": "移除已安装的可选包",
+    "sourceOpt": "存放包负载和包索引的目录",
+    "warnNoIndex": "未找到 optional-packs.index.json —— 此检出无法进行安装/验证（桌面捆绑包会附带它）",
+    "errUnknown": "未知的包：{name}",
+    "errNoIndex": "未找到包索引；请通过 --source <dir> 传入存放包负载的目录（桌面捆绑包会将其附带在应用旁）",
+    "installed": "包 “{name}” 已安装并在 {dir} 验证通过",
+    "restartHint": "请重启 OmniRoute 服务器（或桌面应用），以便运行时加载该包",
+    "removed": "包 “{name}” 已移除",
+    "notInstalled": "包 “{name}” 未安装",
+    "verifyOk": "所有已安装的包均已验证通过",
+    "verifyFailed": "{count} 个包验证失败",
+    "noneInstalled": "未安装可选包"
   }
 }

bin/cli/locales/zh-TW.json

@@ -38,7 +38,8 @@
     "testFailed": "提供者測試失敗：{error}",
     "loginEnabled": "登入：已啟用（密碼已更新）",
     "loginDisabled": "登入：已停用",
-    "providerInfo": "提供者：{info}"
+    "providerInfo": "提供者：{info}",
+    "opencode": "安裝並配置隨附的 @omniroute/opencode-plugin 以用於 OpenCode"
   },
   "doctor": {
     "title": "OmniRoute 診斷",
@@ -252,7 +253,9 @@
     "no_recovery": "停用崩潰自動重啟（除錯模式）",
     "max_restarts": "30 秒內的最大崩潰重啟次數（預設：2）",
     "tray": "顯示系統托盤圖示（僅桌面，選擇加入）",
-    "no_tray": "停用系統托盤圖示"
+    "no_tray": "停用系統托盤圖示",
+    "tls_cert": "用於提供 HTTPS 服務的 TLS 憑證（PEM）路徑（也可用 OMNIROUTE_TLS_CERT）",
+    "tls_key": "用於提供 HTTPS 服務的 TLS 私鑰（PEM）路徑（也可用 OMNIROUTE_TLS_KEY）"
   },
   "backup": {
     "title": "備份",
@@ -1258,5 +1261,69 @@
     "search": "搜尋 npm 登錄檔中的可用外掛",
     "update": "更新已安裝的外掛",
     "scaffold": "搭建新的外掛模板"
+  },
+  "authExport": {
+    "description": "匯出已解密的提供者憑據（僅限本機，明文輸出）",
+    "idOpt": "僅匯出與此 id/名稱/提供者相符的連線",
+    "formatOpt": "輸出格式：json 或 env",
+    "outOpt": "將輸出寫入檔案而非標準輸出（以 0600 權限寫入）",
+    "forceOpt": "確認你了解此操作會列印/寫入明文密鑰",
+    "warning": "⚠ 此操作會列印/寫入已解密的明文 API 金鑰和 OAuth 令牌。請確保你的螢幕、shell 歷史記錄以及任何輸出檔案保持私密。",
+    "confirmHeading": "⚠ 警告：此操作會以明文匯出已解密的提供者憑據",
+    "confirmBody": "此命令會為所選連線解密並列印/寫入 apiKey、accessToken、refreshToken 和\nidToken。請將輸出視為機密。",
+    "confirmFooter": "如需確認，請執行：\n  omniroute auth export --force",
+    "missingKey": "匯出憑據需要 STORAGE_ENCRYPTION_KEY。",
+    "notFound": "找不到連線：{id}",
+    "invalidFormat": "無效格式：{format}。請使用 json 或 env。"
+  },
+  "radar": {
+    "description": "檢查並同步本機 Radar 目錄訂閱來源",
+    "status": "顯示本機 Radar 設定和訂閱來源快取狀態",
+    "sync": "透過本機伺服器同步目錄、推薦、優惠和 Intel"
+  },
+  "launch": {
+    "description": "啟動指向 OmniRoute 的 Claude Code（本機或遠端，使用 --profile）",
+    "token": "Claude 用戶端應傳送的令牌（ANTHROPIC_AUTH_TOKEN）",
+    "notRunning": "無法在 {port} 存取 OmniRoute。請使用「omniroute serve」啟動它。",
+    "notFound": "在 PATH 中找不到「claude」CLI。"
+  },
+  "run": {
+    "description": "透過 OmniRoute 啟動受支援的 CLI 目標"
+  },
+  "setupClaude": {
+    "description": "從 OmniRoute 模型目錄產生 ~/.claude/profiles 的 Claude Code 配置檔"
+  },
+  "connect": {
+    "description": "連線到遠端 OmniRoute 伺服器並進入遠端模式"
+  },
+  "tokens": {
+    "description": "管理限定範圍的 CLI 存取令牌（遠端模式）"
+  },
+  "configure": {
+    "description": "從使用中的伺服器選擇提供者+模型並配置受支援的本機 CLI"
+  },
+  "launchCodex": {
+    "description": "啟動指向 OmniRoute 的 Codex CLI（本機或遠端 VPS）"
+  },
+  "setupCodex": {
+    "description": "從 OmniRoute 即時模型目錄產生 ~/.codex 配置檔"
+  },
+  "packs": {
+    "description": "管理可選的執行階段套件（ML / 瀏覽器自動化）",
+    "listDescription": "列出可選套件及其安裝狀態",
+    "installDescription": "將可選套件安裝到 DATA_DIR",
+    "verifyDescription": "根據隨附的總和檢查碼索引驗證已安裝的套件",
+    "removeDescription": "移除已安裝的可選套件",
+    "sourceOpt": "存放套件負載和套件索引的目錄",
+    "warnNoIndex": "找不到 optional-packs.index.json —— 此檢出無法進行安裝/驗證（桌面套件會隨附它）",
+    "errUnknown": "未知的套件：{name}",
+    "errNoIndex": "找不到套件索引；請透過 --source <dir> 傳入存放套件負載的目錄（桌面套件會將其隨附在應用程式旁）",
+    "installed": "套件「{name}」已安裝並在 {dir} 驗證通過",
+    "restartHint": "請重新啟動 OmniRoute 伺服器（或桌面應用程式），以便執行階段載入該套件",
+    "removed": "套件「{name}」已移除",
+    "notInstalled": "套件「{name}」未安裝",
+    "verifyOk": "所有已安裝的套件均已驗證通過",
+    "verifyFailed": "{count} 個套件驗證失敗",
+    "noneInstalled": "未安裝可選套件"
   }
 }

bin/cli/mcpClient.mjs

@@ -0,0 +1,127 @@
+/**
+ * Shared MCP JSON-RPC client for CLI commands.
+ *
+ * The server exposes MCP through /api/mcp/stream (Streamable HTTP transport).
+ * Calling a tool requires:
+ *   1. POST initialize → get Mcp-Session-Id response header
+ *   2. POST tools/call with that session header
+ *
+ * Older CLI paths POSTed { name, arguments } to /api/mcp/tools/call, which is
+ * not a registered route, so every MCP-backed command was broken.
+ *
+ * These functions route through apiFetch so CLI auth, remote contexts and
+ * timeouts are handled the same way as every other management API call.
+ */
+import { apiFetch } from "./api.mjs";
+
+function mcpError(message, status) {
+  const err = new Error(message);
+  if (status) err.status = status;
+  return err;
+}
+
+async function callMcpEndpoint(payload, { timeout, stream }) {
+  const res = await apiFetch("/api/mcp/stream", {
+    method: "POST",
+    body: payload,
+    timeout,
+    acceptNotOk: true,
+    headers: stream ? { Accept: "text/event-stream" } : {},
+  });
+
+  if (!res.ok) {
+    const text = await res.text().catch(() => "");
+    throw mcpError(
+      `${payload.method} ${payload.id}: HTTP ${res.status}${text ? ` — ${text}` : ""}`,
+      res.status,
+    );
+  }
+  return res;
+}
+
+/**
+ * Call an MCP tool over /api/mcp/stream.
+ *
+ * Non-stream: returns the JSON-RPC result payload.
+ * Stream: writes SSE `data:` chunks to stdout and returns null on success.
+ */
+export async function mcpCallTool(name, args = {}, options = {}) {
+  const { timeout, scope } = options;
+  const scopeHeader = scope?.length ? { "X-MCP-Scopes": scope.join(",") } : {};
+
+  const initRes = await callMcpEndpoint(
+    {
+      jsonrpc: "2.0",
+      id: 1,
+      method: "initialize",
+      params: {
+        protocolVersion: "2024-11-05",
+        capabilities: {},
+        clientInfo: { name: "omniroute-cli", version: "1.0" },
+      },
+    },
+    { timeout, stream: options.stream },
+  );
+
+  const sessionId = initRes.headers.get("mcp-session-id");
+  if (!sessionId) {
+    throw mcpError("MCP initialize failed: no Mcp-Session-Id in response", 500);
+  }
+
+  const callRes = await callMcpEndpoint(
+    {
+      jsonrpc: "2.0",
+      id: 2,
+      method: "tools/call",
+      params: { name, arguments: args },
+    },
+    { timeout, stream: options.stream },
+  );
+
+  if (options.stream) {
+    return consumeSse(callRes.body, options.onChunk);
+  }
+
+  const data = await callRes.json();
+  if (data.error) {
+    const err = mcpError(`MCP error: ${data.error.message || JSON.stringify(data.error)}`);
+    err.code = data.error.code;
+    throw err;
+  }
+  if (data.result?.isError) {
+    const msg = data.result?.content?.[0]?.text || "unknown tool error";
+    throw mcpError(`MCP error: ${msg}`, 500);
+  }
+  return data.result;
+}
+
+async function consumeSse(body, onChunk) {
+  if (!body) throw mcpError("MCP stream returned no body", 500);
+  const reader = body.getReader();
+  const decoder = new TextDecoder();
+  let buf = "";
+  const flushLines = () => {
+    let idx;
+    while ((idx = buf.indexOf("\n")) >= 0) {
+      const line = buf.slice(0, idx);
+      buf = buf.slice(idx + 1);
+      if (line.startsWith("data: ")) {
+        const raw = line.slice(6).trim();
+        if (raw && raw !== "[DONE]") (onChunk ?? writeStdout)(raw);
+      }
+    }
+  };
+  while (true) {
+    const { done, value } = await reader.read();
+    if (done) break;
+    buf += decoder.decode(value, { stream: true });
+    flushLines();
+  }
+  buf += decoder.decode();
+  flushLines();
+  return null;
+}
+
+function writeStdout(raw) {
+  process.stdout.write(raw + "\n");
+}

bin/cli/npm-exec.mjs

@@ -0,0 +1,34 @@
+// Spawning npm from the CLI, on every platform.
+//
+// On Windows npm is `npm.cmd`, a batch wrapper. Node ≥ 24 refuses to spawn a
+// `.cmd` without a shell (nodejs/node#52554), and a bare `npm` can additionally
+// resolve to an extensionless shim that `CreateProcess` cannot execute — so the
+// call fails with `EINVAL` or `ENOENT` while npm works fine in the same terminal.
+// `src/lib/services/installers/utils.ts` already solves this for the server; this
+// is the same rule for the `bin/cli` entry points, which cannot import TypeScript.
+//
+// SECURITY (Hard Rule #13): enabling the shell means the SHELL splits the command
+// line, not `execFile`. Every argv element passed alongside these options must be
+// a literal — never a runtime value — or it must be validated first. Callers that
+// need to pass a user-supplied name have to guard it themselves.
+
+/** The npm binary to spawn on this platform. */
+export function npmBin(platform = process.platform) {
+  const isBun = Boolean(process.versions.bun);
+  if (platform === "win32") return isBun ? "bun.exe" : "npm.cmd";
+  return isBun ? "bun" : "npm";
+}
+
+/**
+ * `execFile` / `spawnSync` options for an npm call.
+ *
+ * @param {NodeJS.Platform} platform
+ * @param {{ timeoutMs?: number, stdio?: string }} [options]
+ */
+export function npmExecOptions(platform = process.platform, options = {}) {
+  const base = {};
+  if (options.timeoutMs !== undefined) base.timeout = options.timeoutMs;
+  if (options.stdio !== undefined) base.stdio = options.stdio;
+  if (platform !== "win32") return { ...base, shell: false };
+  return { ...base, shell: true, windowsHide: true };
+}

bin/cli/provider-test.mjs

@@ -10,6 +10,10 @@ const PROVIDER_TEST_CONFIGS = {
     format: "openai",
     baseUrl: "https://openrouter.ai/api/v1",
     model: "openai/gpt-4o-mini",
+    // #11226: /models is public on OpenRouter (200 with any or no key) — probe the
+    // authenticated key-info endpoint instead so a bad key fails the test here
+    // instead of on the first real chat request.
+    keyCheckPath: "/auth/key",
   },
   groq: {
     format: "openai",
@@ -101,13 +105,19 @@ async function testOpenAILikeProvider(input, config) {
     "Content-Type": "application/json",
   };
 
-  const modelsRes = await fetchWithTimeout(joinUrl(config.baseUrl, "/models"), {
-    method: "GET",
-    headers,
-  });
+  // Providers whose /models endpoint is public (e.g. OpenRouter) declare a
+  // keyCheckPath pointing at an authenticated endpoint so the probe actually
+  // exercises the key instead of the public catalog.
+  const probeRes = await fetchWithTimeout(
+    joinUrl(config.baseUrl, config.keyCheckPath || "/models"),
+    {
+      method: "GET",
+      headers,
+    }
+  );
 
-  if (modelsRes.ok || modelsRes.status === 401 || modelsRes.status === 403) {
-    return classifyResponse(modelsRes);
+  if (probeRes.ok || probeRes.status === 401 || probeRes.status === 403) {
+    return classifyResponse(probeRes);
   }
 
   const chatRes = await fetchWithTimeout(joinUrl(config.baseUrl, "/chat/completions"), {

bin/cli/runtime.mjs

@@ -1,9 +1,14 @@
-import { fileURLToPath } from "node:url";
+import { fileURLToPath, pathToFileURL } from "node:url";
 import { dirname, resolve } from "node:path";
 import { apiFetch, isServerUp } from "./api.mjs";
 
 const PROJECT_ROOT = resolve(dirname(fileURLToPath(import.meta.url)), "../..");
 
+// Dynamic `import()` resolves its specifier as a URL, not as a filesystem path.
+// On Windows an absolute path starts with a drive letter, which the ESM loader
+// reads as the unsupported URL scheme `e:` and rejects. Pass a file:// URL.
+const projectFileUrl = (relPath) => pathToFileURL(resolve(PROJECT_ROOT, relPath)).href;
+
 export class ServerOfflineError extends Error {
   constructor(message = "Server is offline and operation requires HTTP runtime") {
     super(message);
@@ -22,8 +27,8 @@ function makeHttpContext(opts) {
 
 async function importDbModules() {
   const [combos, recovery] = await Promise.all([
-    import(`${PROJECT_ROOT}/src/lib/db/combos.ts`),
-    import(`${PROJECT_ROOT}/src/lib/db/recovery.ts`),
+    import(projectFileUrl("src/lib/db/combos.ts")),
+    import(projectFileUrl("src/lib/db/recovery.ts")),
   ]);
   return { combos, recovery };
 }

bin/cli/runtime/nativeDeps.mjs

@@ -114,30 +114,30 @@ export function isBetterSqliteBinaryValid() {
 
 export function npmInstallRuntime(pkgs, opts = {}) {
   const cwd = ensureRuntimeDir();
-  // Persist to the runtime package.json (exact version) instead of --no-save so a later
-  // install of a sibling runtime dep (e.g. systray2 from trayRuntime.ts, which writes to the
-  // same runtime dir) does not prune this package as "extraneous" — that pruning otherwise
-  // reproduces "No SQLite driver available" after a tray install removes better-sqlite3.
-  // npm 12+ defaults `allowScripts` to off, silently skipping lifecycle/install
-  // scripts (e.g. better-sqlite3's node-gyp/prebuild-install rebuild) unless the
-  // package has a matching `allowScripts` entry — and still exits 0, masking the
-  // failure (#10713). The runtime dir is a CLI-owned, non-user package.json, so
-  // explicitly allowing scripts for the packages we are installing here is safe.
-  const npmArgs = [
-    "install",
-    ...pkgs,
-    "--no-audit",
-    "--no-fund",
-    "--prefer-online",
-    "--save-exact",
-    ...pkgs.map((pkg) => `--allow-scripts=${pkg}`),
-  ];
-  // On Windows .cmd files cannot be executed without a shell; use cmd.exe /c explicitly
-  // so we never set shell:true (which would propagate env and enable injection).
   const isWin = platform() === "win32";
-  const [exe, args] = isWin ? ["cmd.exe", ["/c", "npm", ...npmArgs]] : ["npm", npmArgs];
+  const isBun = Boolean(process.versions.bun);
+
+  let exe, args, displayCmd;
+  if (isBun) {
+    const bunArgs = ["add", ...pkgs, "--trust"];
+    [exe, args] = isWin ? ["cmd.exe", ["/c", "bun", ...bunArgs]] : ["bun", bunArgs];
+    displayCmd = `bun ${bunArgs.join(" ")}`;
+  } else {
+    const npmArgs = [
+      "install",
+      ...pkgs,
+      "--no-audit",
+      "--no-fund",
+      "--prefer-online",
+      "--save-exact",
+      ...pkgs.map((pkg) => `--allow-scripts=${pkg}`),
+    ];
+    [exe, args] = isWin ? ["cmd.exe", ["/c", "npm", ...npmArgs]] : ["npm", npmArgs];
+    displayCmd = `npm ${npmArgs.join(" ")}`;
+  }
+
   if (!opts.silent) {
-    process.stdout.write(`[omniroute][runtime] npm ${npmArgs.join(" ")}\n`);
+    process.stdout.write(`[omniroute][runtime] ${displayCmd}\n`);
   }
   const res = spawnSync(exe, args, {
     cwd,

bin/cli/runtime/sqliteRuntime.mjs

@@ -6,7 +6,9 @@ import { pathToFileURL } from "node:url";
 import { validateBinaryMagic, platformBinaryLabel } from "./magicBytes.mjs";
 
 const RUNTIME_DIR = join(homedir(), ".omniroute", "runtime");
-const BETTER_SQLITE3_VERSION = "better-sqlite3@^12.10.1";
+// Exported so the packaging coherence guard (tests/unit/pack-boot-runtime-paths.test.ts)
+// can assert this stays on the same major as optionalDependencies.better-sqlite3 (#11242).
+export const BETTER_SQLITE3_VERSION = "better-sqlite3@^13.0.2";
 
 let resolvedCached = null;
 

bin/cli/runtime/trayRuntime.ts

@@ -2,6 +2,7 @@ import { existsSync, mkdirSync, writeFileSync, chmodSync } from "node:fs";
 import { join } from "node:path";
 import { homedir } from "node:os";
 import { execSync } from "node:child_process";
+import { pathToFileURL } from "node:url";
 
 const RUNTIME_DIR = join(homedir(), ".omniroute", "runtime");
 // systray2 is a maintained fork with prebuilt binaries — installed lazily at runtime,
@@ -16,6 +17,16 @@ export const SYSTRAY_PACKAGE = "systray2";
 export const SYSTRAY_VERSION = "2.1.4";
 const SYSTRAY_SPEC = `${SYSTRAY_PACKAGE}@${SYSTRAY_VERSION}`;
 
+// Dynamic `import()` resolves its specifier as a URL, not a filesystem path.
+// On Windows the lazily-installed systray2 lives at an absolute path whose
+// leading drive letter the ESM loader parses as an unsupported URL scheme
+// (e.g. `c:`) and rejects. Build a file:// URL so the tray import works on
+// Windows too. Same defect fixed for the CLI db-fallback imports in #11238,
+// missed at this call site.
+export function systrayModuleSpecifier(runtimeDir: string): string {
+  return pathToFileURL(join(runtimeDir, "node_modules", SYSTRAY_PACKAGE)).href;
+}
+
 export function resolveSystrayBinName(platform: NodeJS.Platform): string | null {
   if (platform === "win32") return "tray_windows_release.exe";
   if (platform === "darwin") return "tray_darwin_release";
@@ -60,8 +71,7 @@ export async function loadSystray(): Promise<(new (...args: unknown[]) => unknow
   // drop the +x bit on extraction (observed on macOS).
   chmodSystrayBinAt(RUNTIME_DIR, process.platform);
   try {
-    const modPath = join(RUNTIME_DIR, "node_modules", SYSTRAY_PACKAGE);
-    const mod = await import(modPath);
+    const mod = await import(systrayModuleSpecifier(RUNTIME_DIR));
     return (mod.default ?? mod.SysTray ?? mod) as (new (...args: unknown[]) => unknown) | null;
   } catch (err) {
     console.warn(`[omniroute] tray runtime import failed: ${(err as Error).message}`);

bin/cli/sqlite.mjs

@@ -5,10 +5,14 @@ import { ensureSettingsSchema, hashManagementPassword, updateSettings } from "./
 
 async function loadSqlite() {
   if (process.versions.bun) {
-    return { Database: (await import("bun:sqlite")).Database };
+    try {
+      return { Database: (await import("bun:sqlite")).Database, driver: "bun:sqlite" };
+    } catch (bunError) {
+      // fall through to better-sqlite3 if bun:sqlite fails
+    }
   }
   try {
-    return { Database: (await import("better-sqlite3")).default };
+    return { Database: (await import("better-sqlite3")).default, driver: "better-sqlite3" };
   } catch (error) {
     return { error };
   }
@@ -86,12 +90,14 @@ export function normalizeBunSqliteParams(params) {
 
 export function createSqliteNativeError(error) {
   const message = error instanceof Error ? error.message : String(error);
+  const isBun = Boolean(process.versions.bun);
+  const rebuildCmd = isBun ? "bun add better-sqlite3 --trust" : "npm rebuild better-sqlite3";
   if (message.includes("NODE_MODULE_VERSION") || message.includes("ERR_DLOPEN_FAILED")) {
     return new Error(
-      "better-sqlite3 native binding is incompatible with this Node.js runtime. " +
-        "Run `npm rebuild better-sqlite3` in the OmniRoute project and try again. " +
-        "Or run: omniroute runtime repair  " +
-        "(rebuilds into a user-writable runtime; works without a C++ toolchain)."
+      `better-sqlite3 native binding is incompatible with this runtime. ` +
+        `Run \`${rebuildCmd}\` in the OmniRoute project and try again. ` +
+        `Or run: omniroute runtime repair  ` +
+        `(rebuilds into a user-writable runtime; works without a C++ toolchain).`
     );
   }
   if (
@@ -100,10 +106,9 @@ export function createSqliteNativeError(error) {
     message.includes("Cannot find module 'better-sqlite3'")
   ) {
     return new Error(
-      "better-sqlite3 native binding could not be found (no prebuilt addon for this platform). " +
-        "This is common under `npx`, which runs a fresh, ephemeral install that never built the addon. " +
-        "Run: omniroute runtime repair  " +
-        "(rebuilds into a user-writable runtime; works without a C++ toolchain)."
+      `better-sqlite3 native binding could not be found (no prebuilt addon for this platform). ` +
+        `Run: omniroute runtime repair  ` +
+        `(rebuilds into a user-writable runtime; works without a C++ toolchain).`
     );
   }
   return error;
@@ -111,7 +116,7 @@ export function createSqliteNativeError(error) {
 
 async function openSqliteDatabase(dbPath, options = {}) {
   const loaded = await loadSqlite();
-  if (process.versions.bun) {
+  if (loaded.driver === "bun:sqlite" || (process.versions.bun && !loaded.Database)) {
     if (options.fileMustExist && !fs.existsSync(dbPath)) {
       throw new Error(`SQLite file does not exist: ${dbPath}`);
     }

bin/cli/tray/autostart.mjs

@@ -114,17 +114,30 @@ function writeLinuxSystemdUnit(cliPath) {
   const unitDir = dirname(linuxSystemdUnitPath());
   mkdirSync(unitDir, { recursive: true });
   const envFile = join(userHomeDir(), ".omniroute", ".env");
+  const nodeBinDir = dirname(process.execPath);
+  const userLocalBin = join(userHomeDir(), ".local", "bin");
+  const pathEnv = `${nodeBinDir}:${userLocalBin}:/usr/local/sbin:/usr/local/bin:/usr/bin:/bin`;
   const lines = [
     "[Unit]",
     "Description=OmniRoute AI proxy router",
-    "After=network-online.target",
+    "After=network-online.target graphical-session.target",
     "Wants=network-online.target",
     "",
     "[Service]",
-    "Type=simple",
+    // Type=notify + WatchdogSec: the server sends READY=1 once listening and
+    // WATCHDOG=1 every 60s; if its event loop ever blocks (frozen process),
+    // the pings stop and systemd kills+restarts the service. NotifyAccess=all
+    // because the pings come from the server child, not the serve supervisor.
+    // Foreground serve only: `--daemon` escapes the cgroup and would break
+    // the notify handshake.
+    "Type=notify",
+    "NotifyAccess=all",
+    "WatchdogSec=180",
+    "TimeoutStartSec=300",
     `ExecStart=${buildServeExecLine(cliPath, { tray: false })}`,
     "Restart=on-failure",
     "RestartSec=5",
+    `Environment="PATH=${pathEnv}"`,
   ];
   if (existsSync(envFile)) lines.push(`EnvironmentFile=-${envFile}`);
   lines.push("", "[Install]", "WantedBy=default.target", "");
@@ -267,6 +280,10 @@ function isAgentSelfMac() {
   }
 }
 
+function isDetachedTrayWorker() {
+  return process.argv.includes("--tray-worker");
+}
+
 function enableMac() {
   const plistDir = join(homedir(), "Library", "LaunchAgents");
   mkdirSync(plistDir, { recursive: true });
@@ -291,7 +308,7 @@ function enableMac() {
   // If we're already the running agent, launchctl load/unload would SIGTERM us.
   // The plist is updated on disk and launchd already has us loaded under our own
   // PID — nothing more to do for the current session.
-  if (isAgentSelfMac()) return existsSync(plistPath);
+  if (isAgentSelfMac() || isDetachedTrayWorker()) return existsSync(plistPath);
   try {
     execSync("launchctl load -w " + JSON.stringify(plistPath), { stdio: "ignore" });
   } catch {}
@@ -304,7 +321,7 @@ function disableMac() {
   // `launchctl unload` sends SIGTERM and a user clicking "Disable Autostart"
   // from the tray would lose the tray icon instead of just flipping the label.
   // Removing the plist file is enough to stop the agent at the next login.
-  if (!isAgentSelfMac()) {
+  if (!isAgentSelfMac() && !isDetachedTrayWorker()) {
     try {
       execSync("launchctl unload -w " + JSON.stringify(plistPath), { stdio: "ignore" });
     } catch {}

bin/cli/tray/detachedTray.mjs

@@ -0,0 +1,176 @@
+import { execFileSync, spawn } from "node:child_process";
+import { randomBytes, timingSafeEqual } from "node:crypto";
+import { createServer, connect } from "node:net";
+
+/** Builds arguments for the hidden process that owns the server and tray. */
+export function buildTrayWorkerArgs({ port, maxRestarts, readyPort, readyToken, tlsCert, tlsKey }) {
+  const args = [
+    "serve",
+    "--tray",
+    "--tray-worker",
+    "--no-open",
+    "--port",
+    String(port),
+    "--max-restarts",
+    String(maxRestarts),
+    "--tray-ready-port",
+    String(readyPort),
+    "--tray-ready-token",
+    readyToken,
+  ];
+  if (tlsCert) args.push("--tls-cert", tlsCert);
+  if (tlsKey) args.push("--tls-key", tlsKey);
+  return args;
+}
+
+/** Builds the platform command that starts the hidden tray worker. */
+export function buildTrayLaunch({ platform, execPath, cliPath, workerArgs, label }) {
+  if (platform === "darwin") {
+    return {
+      command: "launchctl",
+      args: ["submit", "-l", label, "--", execPath, cliPath, ...workerArgs],
+      options: { stdio: "ignore" },
+    };
+  }
+  return {
+    command: execPath,
+    args: [cliPath, ...workerArgs],
+    options: { detached: true, stdio: "ignore", windowsHide: true },
+  };
+}
+
+/** Returns an error for command modes that conflict with detached tray mode. */
+export function validateTrayOptions(opts) {
+  if (opts.trayWorker && (!opts.trayReadyPort || !opts.trayReadyToken)) {
+    return "tray worker requires readiness credentials";
+  }
+  if (!opts.tray || opts.trayWorker) return null;
+  if (opts.daemon) return "--tray cannot use --daemon";
+  if (opts.log) return "--tray cannot use --log";
+  if (opts.noRecovery || opts.recovery === false) return "--tray cannot use --no-recovery";
+  return null;
+}
+
+/** Creates a token-protected loopback server for tray worker readiness. */
+export async function createTrayReadinessServer(token) {
+  let markReady;
+  const ready = new Promise((resolve) => {
+    markReady = resolve;
+  });
+  const expected = Buffer.from(token);
+  const server = createServer((socket) => {
+    let data = "";
+    socket.setEncoding("utf8");
+    socket.on("data", (chunk) => {
+      data += chunk;
+      if (data.length > 256) socket.destroy();
+    });
+    socket.on("end", () => {
+      const received = Buffer.from(data);
+      if (received.length !== expected.length || !timingSafeEqual(received, expected)) {
+        socket.end("ERROR");
+        return;
+      }
+      socket.end("READY");
+      markReady();
+    });
+  });
+  await new Promise((resolve, reject) => {
+    server.once("error", reject);
+    server.listen(0, "127.0.0.1", resolve);
+  });
+  const address = server.address();
+  return {
+    port: address.port,
+    wait(timeoutMs) {
+      return new Promise((resolve, reject) => {
+        const timer = setTimeout(
+          () => reject(new Error("Tray worker did not become ready")),
+          timeoutMs
+        );
+        ready.then(() => {
+          clearTimeout(timer);
+          resolve();
+        });
+      });
+    },
+    close() {
+      server.close();
+    },
+  };
+}
+
+/** Notifies the parent process that the server and tray are ready. */
+export async function notifyTrayReady(port, token) {
+  await new Promise((resolve, reject) => {
+    const socket = connect({ host: "127.0.0.1", port }, () => socket.end(token));
+    let reply = "";
+    socket.setEncoding("utf8");
+    socket.on("data", (chunk) => {
+      reply += chunk;
+    });
+    socket.on("end", () => {
+      if (reply === "READY") resolve();
+      else reject(new Error("Tray readiness token was rejected"));
+    });
+    socket.on("error", reject);
+  });
+}
+
+/** Starts a detached tray worker and waits until its server and tray are ready. */
+export async function startDetachedTray(
+  { cliPath, port, maxRestarts, tlsCert, tlsKey, timeoutMs = 60000 },
+  { platform = process.platform, spawnProcess = spawn } = {}
+) {
+  const token = randomBytes(32).toString("hex");
+  const readiness = await createTrayReadinessServer(token);
+  const label = `com.omniroute.tray.${process.pid}.${Date.now()}`;
+  const workerArgs = buildTrayWorkerArgs({
+    port,
+    maxRestarts,
+    readyPort: readiness.port,
+    readyToken: token,
+    tlsCert,
+    tlsKey,
+  });
+  const launch = buildTrayLaunch({
+    platform,
+    execPath: process.execPath,
+    cliPath,
+    workerArgs,
+    label,
+  });
+  const child = spawnProcess(launch.command, launch.args, launch.options);
+  const spawnFailure = new Promise((_, reject) => {
+    child.once("error", reject);
+    child.once("exit", (code) => {
+      if (platform !== "darwin" || code !== 0) {
+        reject(new Error(`Tray worker exited before readiness with code ${code ?? "unknown"}`));
+      }
+    });
+  });
+  if (platform !== "darwin") child.unref?.();
+  try {
+    await Promise.race([readiness.wait(timeoutMs), spawnFailure]);
+    return { platform, pid: child.pid, label: platform === "darwin" ? label : null };
+  } catch (err) {
+    if (platform === "darwin") {
+      try {
+        execFileSync("launchctl", ["bootout", `gui/${process.getuid()}/${label}`], {
+          stdio: "ignore",
+        });
+      } catch {}
+    } else if (platform === "win32" && child.pid) {
+      try {
+        execFileSync("taskkill", ["/PID", String(child.pid), "/T", "/F"], { stdio: "ignore" });
+      } catch {}
+    } else if (child.pid) {
+      try {
+        process.kill(child.pid, "SIGTERM");
+      } catch {}
+    }
+    throw err;
+  } finally {
+    readiness.close();
+  }
+}

bin/cli/tray/traySystray.mjs

@@ -97,9 +97,7 @@ export async function initSystrayUnix(
     }
   });
 
-  tray.ready().catch((err) => {
-    process.stderr.write(`[omniroute][tray] systray2 failed: ${err?.message ?? String(err)}\n`);
-  });
+  await tray.ready();
 
   return tray;
 }

bin/cli/tui/ProvidersTestAll.jsx

@@ -1,6 +1,7 @@
 import React, { useState, useEffect, useCallback } from "react";
 import { render, Box, Text, useInput } from "ink";
 import Spinner from "ink-spinner";
+import { apiFetch } from "../api.mjs";
 import { DataTable } from "../tui-components/DataTable.jsx";
 import { ProgressBar } from "../tui-components/ProgressBar.jsx";
 
@@ -31,22 +32,20 @@ const TABLE_SCHEMA = [
   { key: "error", header: "Error", width: 28, formatter: (v) => (v ? v.slice(0, 26) : "") },
 ];
 
-async function testOne(provider, model, baseUrl, apiKey) {
-  const headers = {
-    "Content-Type": "application/json",
-    ...(apiKey ? { Authorization: `Bearer ${apiKey}` } : {}),
-  };
+async function testOne(connectionId, model, baseUrl, apiKey) {
   const start = Date.now();
   try {
-    const res = await fetch(`${baseUrl}/api/v1/providers/test`, {
+    const res = await apiFetch(`/api/providers/${encodeURIComponent(connectionId)}/test`, {
       method: "POST",
-      headers,
-      body: JSON.stringify({ provider, model }),
-      signal: AbortSignal.timeout(30000),
+      body: model ? { validationModelId: model } : {},
+      baseUrl,
+      token: apiKey,
+      timeout: 30000,
+      acceptNotOk: true,
     });
     const latencyMs = Date.now() - start;
-    const data = res.ok ? await res.json() : { success: false, error: `HTTP ${res.status}` };
-    return { status: data.success ? STATUS.PASS : STATUS.FAIL, latencyMs, error: data.error };
+    const data = res.ok ? await res.json() : { valid: false, error: `HTTP ${res.status}` };
+    return { status: data.valid ? STATUS.PASS : STATUS.FAIL, latencyMs, error: data.error };
   } catch (err) {
     const msg = err instanceof Error ? err.message : String(err);
     return {
@@ -63,6 +62,7 @@ function ProvidersTestAllApp({ providers, baseUrl, apiKey, concurrency = 4, onEx
   const [rows, setRows] = useState(() =>
     providers.map((p, i) => ({
       id: i,
+      connectionId: p.connectionId ?? p.id,
       provider: p.provider ?? p.id ?? String(p),
       model: p.model ?? p.defaultModel ?? "",
       status: STATUS.PENDING,
@@ -91,7 +91,7 @@ function ProvidersTestAllApp({ providers, baseUrl, apiKey, concurrency = 4, onEx
           const row = queue[cursor++];
           running++;
           update(row.id, { status: STATUS.RUNNING });
-          testOne(row.provider, row.model, resolved, apiKey).then((result) => {
+          testOne(row.connectionId, row.model, resolved, apiKey).then((result) => {
             update(row.id, result);
             running--;
             nextSlot();

bin/cli/utils/cliToken.mjs

@@ -12,25 +12,39 @@ function getActiveSalt() {
   return process.env.OMNIROUTE_CLI_SALT || BUILTIN_DEFAULT_SALT;
 }
 
-export async function getCliToken() {
-  const salt = getActiveSalt();
-  if (_cached !== null && _cachedSalt === salt) return _cached;
+export function deriveCliToken(machineIdModule, salt) {
   try {
     // node-machine-id is CommonJS: under `await import()` its exports land on
     // `.default`, so destructuring `machineIdSync` off the namespace yields
     // undefined and calling it throws — which the catch below turned into an
     // empty token, silently disabling CLI auth for every management request.
     // Same resolution order as src/lib/machineToken.ts.
-    const mod = await import("node-machine-id");
-    const machineIdSync = mod.machineIdSync ?? mod.default?.machineIdSync;
-    if (typeof machineIdSync !== "function") throw new Error("machine-id API unavailable");
+    const machineIdSync =
+      machineIdModule?.machineIdSync || machineIdModule?.default?.machineIdSync;
+    if (typeof machineIdSync !== "function") return "";
     // machineIdSync(true) returns the original unhashed hardware ID — mirrors
     // getMachineTokenSync() in src/lib/machineToken.ts (#10148 cliToken hardening).
-    const mid = machineIdSync(true);
-    _cached = crypto.createHmac("sha256", mid).update(salt).digest("hex");
+    const rawId = machineIdSync(true);
+    if (!rawId) return "";
+    return crypto.createHmac("sha256", rawId).update(salt).digest("hex");
+  } catch {
+    return "";
+  }
+}
+
+export async function getCliToken() {
+  const salt = getActiveSalt();
+  if (_cached !== null && _cachedSalt === salt) return _cached;
+  try {
+    const imported = await import("node-machine-id");
+    const token = deriveCliToken(imported, salt);
+    if (!token) {
+      // Swallowing here changes control flow (every management call goes out
+      // unauthenticated and 401s), so leave a breadcrumb rather than failing mute.
+      console.debug("[CLI_TOKEN] machine-id resolution failed, CLI auth disabled");
+    }
+    _cached = token;
   } catch (e) {
-    // Swallowing here changes control flow (every management call goes out
-    // unauthenticated and 401s), so leave a breadcrumb rather than failing mute.
     console.debug("[CLI_TOKEN] machine-id resolution failed, CLI auth disabled:", e);
     _cached = "";
   }

bin/cli/utils/ensureAndroidCacheDir.mjs

@@ -94,10 +94,15 @@ export function ensureAndroidCacheDir(options = {}) {
  */
 export function isFatalInstrumentationHookFailure(text) {
   if (!text) return false;
-  return (
-    /Unsupported platform:\s*android/i.test(text) ||
-    /error occurred while loading instrumentation hook/i.test(text)
-  );
+  // Next.js wraps ANY throw inside instrumentation.register() with the generic
+  // "An error occurred while loading instrumentation hook:" prefix, on every
+  // platform (node_modules/next/dist/server/web/globals.js). That prefix alone
+  // therefore cannot identify the Android/Termux cache-probe failure — a bare
+  // generic instrumentation error on win32/desktop would be misreported as the
+  // Android bug and hide the real cause. Only match when the text actually
+  // carries the Android platform marker that Next's getCacheDirectory() emits.
+  // #10028
+  return /Unsupported platform:\s*android/i.test(text);
 }
 
 /**

bin/cli/utils/serverHost.mjs

@@ -24,3 +24,34 @@ export function resolveServerHost(
   }
   return "0.0.0.0";
 }
+
+const LOOPBACK_HOSTS = new Set(["127.0.0.1", "localhost", "::1", "[::1]"]);
+
+/**
+ * Boot-time exposure warning (GHSA-wmgv-ph3p-rv57): the shipped default binds
+ * all interfaces while the inference plane requires no credentials, so any
+ * LAN peer can spend the operator's quota. That local-first posture is a
+ * deliberate, documented default — but it must be LOUD at startup so an
+ * operator who never read the docs still learns the two escape hatches.
+ *
+ * Returns the warning text when the server will listen on a non-loopback
+ * interface with no API-key requirement, or null when the exposure is closed.
+ *
+ * @param {NodeJS.ProcessEnv} [env]
+ * @param {string} [host]
+ * @returns {string | null}
+ */
+export function resolveExposureWarning(env = process.env, host = resolveServerHost(env)) {
+  if (LOOPBACK_HOSTS.has(host)) return null;
+  const requireKey = String(env.REQUIRE_API_KEY || "")
+    .trim()
+    .toLowerCase();
+  if (requireKey === "true" || requireKey === "1" || requireKey === "yes") return null;
+  return (
+    `SECURITY: listening on ${host} with NO API-key requirement — the inference ` +
+    `plane (/v1/*) is reachable by ANY device that can route to this host, and ` +
+    `requests are billed to your configured providers. This local-first default ` +
+    `is intentional, but on an untrusted network either set REQUIRE_API_KEY=true ` +
+    `or bind loopback with OMNIROUTE_SERVER_HOST=127.0.0.1.`
+  );
+}

bin/nodeRuntimeSupport.mjs

@@ -44,6 +44,18 @@ export function getSecureFloorForMajor(major) {
 }
 
 export function getNodeRuntimeSupport(version = process.versions.node) {
+  if (process.versions.bun) {
+    return {
+      nodeVersion: `bun-${process.versions.bun} (Node.js API ${version})`,
+      nodeCompatible: true,
+      reason: "supported-bun",
+      supportedRange: SUPPORTED_NODE_RANGE + " || Bun >=1.1.0",
+      supportedDisplay: SUPPORTED_NODE_DISPLAY + ", or Bun 1.1+",
+      recommendedVersion: `v${RECOMMENDED_NODE_VERSION}`,
+      minimumSecureVersion: null,
+    };
+  }
+
   const parsed = parseNodeVersion(version);
   const secureFloor = getSecureFloorForMajor(parsed.major);
   const nodeCompatible = secureFloor ? compareNodeVersions(parsed, secureFloor) >= 0 : false;

bin/omniroute.mjs

@@ -17,7 +17,12 @@
 import { existsSync, readFileSync, writeFileSync } from "node:fs";
 import { join, dirname } from "node:path";
 import { fileURLToPath, pathToFileURL } from "node:url";
-import updateNotifier from "update-notifier";
+let updateNotifier = null;
+try {
+  updateNotifier = (await import("update-notifier")).default;
+} catch {
+  // update-notifier is optional in pruned standalone environments
+}
 import { isNativeBinaryCompatible } from "../scripts/build/native-binary-compat.mjs";
 import { getNodeRuntimeSupport, getNodeRuntimeWarning } from "./nodeRuntimeSupport.mjs";
 import { getDefaultDataDir } from "./cli/data-dir.mjs";
@@ -119,6 +124,9 @@ function loadEnvFile() {
     addEnvPath(join(ROOT, ".env"));
   }
 
+  const keyOrigin = new Map();
+  const shadowed = new Map();
+
   for (const envPath of envPaths) {
     try {
       if (existsSync(envPath)) {
@@ -131,19 +139,31 @@ function loadEnvFile() {
             const key = trimmed.slice(0, eqIdx).trim();
             if (process.env[key] === undefined) {
               process.env[key] = parseEnvValue(trimmed.slice(eqIdx + 1));
+              keyOrigin.set(key, envPath);
+            } else if (!shadowed.has(key)) {
+              // The line is inert: something set this key first. Report it once
+              // per key, whether the winner was an earlier file or the process
+              // environment (#6194: a shell's own HOSTNAME beat the .env and the
+              // server bound to the wrong address in silence).
+              shadowed.set(key, { winner: keyOrigin.get(key) ?? null, loser: envPath });
             }
           }
         }
         loadedEnvPaths.push(envPath);
       }
-    } catch {
-      // Ignore errors reading env files.
+    } catch (err) {
+      console.warn(`  \x1b[33m⚠ Could not read ${envPath}: ${err?.message ?? err}\x1b[0m`);
     }
   }
 
   for (const envPath of loadedEnvPaths) {
     console.log(`  \x1b[2m📋 Loaded env from ${envPath}\x1b[0m`);
   }
+
+  for (const [key, { winner, loser }] of shadowed) {
+    const setter = winner ? winner : "the environment";
+    console.warn(`  \x1b[33m⚠ ${key} in ${loser} is ignored, ${setter} set it first\x1b[0m`);
+  }
 }
 
 loadEnvFile();
@@ -236,8 +256,9 @@ if (shouldProvisionStorageKey(process.argv)) {
 
 // Register update notifier — checks npm once per 24h, notifies on exit via stderr.
 const _pkg = JSON.parse(readFileSync(join(ROOT, "package.json"), "utf8"));
-const _notifier = updateNotifier({ pkg: _pkg, updateCheckInterval: 1000 * 60 * 60 * 24 });
+const _notifier = updateNotifier ? updateNotifier({ pkg: _pkg, updateCheckInterval: 1000 * 60 * 60 * 24 }) : null;
 process.on("exit", () => {
+  if (!_notifier || !_notifier.update) return;
   if (process.env.OMNIROUTE_NO_UPDATE_NOTIFIER) return;
   if (process.env.CI) return;
   if (process.argv.includes("--quiet") || process.argv.includes("-q")) return;

changelog.d/features/10039-combo-lane-awareness-wave-2.md

@@ -1,2 +0,0 @@
-- **feat(admission):** add lane-aware admission probes for combo/fusion/chaos fan-out (fail-open, queueing disabled), an env-wins `OMNIROUTE_CHAT_VIRTUAL_LANES` activation flag applied at boot, and adaptive-lane visibility in the `omniroute_get_health` MCP tool (related to #9654)
-- **docs(mcp):** complete the MCP server README tool reference so the `schemas/` catalog is fully covered (agent-skills, oneproxy, web, tool-search, combo/routing, pricing and DB-health tools were previously only discoverable via `omniroute_tool_search`)

changelog.d/features/10057-docker-aware-auto-config.md

@@ -1 +0,0 @@
-- **feat(cli):** container-aware auto-config — `setup-*`, `omniroute configure`, `omniroute config set` and the CLI-tool config APIs now refuse to write into a containerised OmniRoute's ephemeral home (CLI exits `2`, API returns `422` with `containerEphemeralTarget`) and point at the host-CLI or bind-mount setup instead; `--allow-container-write` / `OMNIROUTE_ALLOW_CONTAINER_CONFIG_WRITE=true` opt back in. Also fixes `CLI_CONFIG_HOME` so the Compose `host` profile's `/host-home` bind mounts are honoured instead of silently falling back to the container home. (#10057)

changelog.d/features/10273-dashboard-embed-csp.md

@@ -1 +0,0 @@
-- feat(dashboard): opt-in `DASHBOARD_ALLOW_EMBED=vscode` relaxes CSP `frame-ancestors` to `'self' vscode-webview:` and drops `X-Frame-Options` for HTML pages only, so the dashboard renders inside the VS Code Simple Browser (OmniCopilot). Default posture unchanged — API routes stay unframable (#10273)

changelog.d/features/10389-cloudflare-playground.md

@@ -1 +0,0 @@
-- feat(providers): add **Cloudflare AI Playground** as a No Auth provider (`cloudflare-playground`, alias `cfp`) — free anonymous chat over the reverse-engineered `cf_agent` WebSocket protocol (PartySocket transport, no account/API key/cookies) with GLM 5.2, Kimi K2.7 Code, DeepSeek V4 Pro, gpt-oss-120B, Llama 3.3 70B, Qwen2.5 Coder 32B and 14 more curated models. The executor drives a headless Chromium via Playwright (the WS upgrade is TLS-fingerprint-gated), translates the `cf_agent` frame stream into OpenAI SSE, and surfaces upstream rate limits (3021) as HTTP 429. Fixes #10389

changelog.d/features/10542-aihorde-optional-key-image-catalog.md

@@ -1,2 +0,0 @@
-- **feat(providers):** AI Horde accepts an optional registered API key and advertises only live image models that currently have workers ([#10542](https://github.com/diegosouzapw/OmniRoute/pull/10542))
-- **fix(providers):** AI Horde Check validates keys via `/v2/find_user` instead of the unauthenticated OpenAI models list ([#10542](https://github.com/diegosouzapw/OmniRoute/pull/10542))

changelog.d/features/10581-jina-complete-provider.md

@@ -1 +0,0 @@
-- **feat(providers):** complete Jina AI as one credential pool — dashboard `jina-ai` / `jina-reader` share a token, `JINA_AI_API_KEY` is a real fallback, Test probes `GET https://api.jina.ai/v1/models` (embeddings fallback hits `jina-embeddings-v5-omni-small`), embed/rerank logs keep `connection_id`, catalog adds `jina-reranker-v3.5`, Omni v5 multimodal `{text}`/`{image}`/`{content}` docs pass through intact, and OmniRoute proxies classify / segment / `jina-search` (`s.jina.ai`). Reader stays a separate `r.jina.ai` card with an explicit label. Gemini Embedding 2 (`gemini/gemini-embedding-2`, alias `google/gemini-embedding-2`) uses dashboard `gemini` keys (or `GEMINI_API_KEY` / `GOOGLE_API_KEY` only when none exist), forwards native multimodal parts, and maps N OpenAI `input` items to N `:batchEmbedContents` vectors instead of one aggregated `:embedContent`. ([#10581](https://github.com/diegosouzapw/OmniRoute/pull/10581))

changelog.d/features/10617-auto-disable-banned-scope.md

@@ -1 +0,0 @@
-- **feat(settings):** add `autoDisableBannedScope` so permanent-ban auto-disable can target subscription/OAuth accounts only, leaving prepaid API keys in the routing pool ([#10617](https://github.com/diegosouzapw/OmniRoute/pull/10617))

changelog.d/features/10697-vscode-copilot-guide.md

@@ -1 +0,0 @@
-- **docs(guides):** OmniRoute now serves VS Code's **native Copilot Chat model picker** through the [OmniCopilot](https://github.com/diegosouzapw/OmniCopilot) extension ([Marketplace](https://marketplace.visualstudio.com/items?itemName=diegosouzapw.omnicopilot) · [Open VSX](https://open-vsx.org/extension/diegosouzapw/omnicopilot) — Cursor, Windsurf, VSCodium, Theia…) — no Copilot subscription needed since VS Code 1.122. New [`docs/guides/VSCODE-COPILOT.md`](docs/guides/VSCODE-COPILOT.md) covers setup, how the picker collapses the `dual`-prefix catalog via `GET /v1/models?prefix=alias`, and the **build-time** `DASHBOARD_ALLOW_EMBED=vscode` flag that renders the dashboard in an editor tab ([#10697](https://github.com/diegosouzapw/OmniRoute/pull/10697))

changelog.d/features/10701-dockerfile-dashboard-embed-arg.md

@@ -1 +0,0 @@
-- **feat(docker):** `DASHBOARD_ALLOW_EMBED` is now a Docker build argument — `docker build --build-arg DASHBOARD_ALLOW_EMBED=vscode` produces an image whose dashboard renders inside the VS Code Simple Browser (OmniCopilot's `dashboardOpen: "editor"`). Previously the flag was only reachable from a source build: Docker silently drops a `--build-arg` with no matching `ARG`, so the operator got the default image and no error. Builder-stage only and empty by default — the runtime stages deliberately do not carry it, and the unframable default posture is unchanged ([#10701](https://github.com/diegosouzapw/OmniRoute/pull/10701))

changelog.d/features/10729-cursor-api-key-and-cli-passthrough.md

@@ -1 +0,0 @@
-- **feat(providers):** new `cursor-api` provider (card "Cursor API", alias `cua`): connect a Cursor user API key (`crsr_…`) and route `cursor-api/<model>` through the existing Cursor agent executor (the key is exchanged for a 1h session token and cached), plus a `/api/cursor-cli/*` passthrough so the Cursor CLI itself runs through OmniRoute (`CURSOR_API_ENDPOINT=http://<omniroute>/api/cursor-cli`, `CURSOR_API_KEY=<OmniRoute key>`) with every RPC attributed and logged. The IDE `cursor` provider is unchanged. (#10729)

changelog.d/features/10771-health-root-endpoint.md

@@ -1 +0,0 @@
-- **feat(api):** `GET /api/health` now answers `{ status, timestamp }` without a key. Until now the path had no route, so the management-auth boundary answered first with a 401 — indistinguishable from a wrong key or an unknown route, which left Docker HEALTHCHECKs and Kubernetes probes unable to tell "down" from "misconfigured". Kept deliberately minimal: version, uptime and memory stay behind the authenticated `/api/monitoring/health` ([#PRNUM](https://github.com/diegosouzapw/OmniRoute/pull/10771)).

changelog.d/features/10783-task-routing-configurable-patterns.md

@@ -1 +0,0 @@
-- feat(routing): make Task-Aware Smart Routing's detection patterns operator-configurable via `settings.taskRouting.patternOverrides` (`PUT /api/settings/task-routing`) — the built-in patterns are English-only, so a non-English dashboard had no recourse short of turning detection off entirely; an override now replaces the pattern list for one task type without touching the rest (#10783)

changelog.d/features/9085-poolside-laguna-model-ids.md

@@ -1 +0,0 @@
-- **feat(providers):** publish Poolside's Laguna Preview catalog statically — `poolside/laguna-xs-2.1` and `poolside/laguna-s-2.1` (262144 context, 32768 max completion, tools + reasoning, text-only), so the models are routable and visible before a key is configured instead of only after live discovery. Pins the catalog form of the XS id against the `laguna-xs.2` variant carried by third-party listings. ([#9085](https://github.com/diegosouzapw/OmniRoute/issues/9085))

changelog.d/features/9760-video-bridge.md

@@ -1 +0,0 @@
-- feat(modality-bridge): bridge Chat and Responses video parts through a strict trusted-loopback, quota-bounded FFmpeg broker; enforce HTTPS redirects/SSRF plus format, protocol, stream, pixel, frame, 50 MiB broker/remote, 36 MiB inline, and 120-second limits; propagate caller aborts; preserve the actual successful fallback model through cache/meta/headers; expose sampled latency and honest success telemetry; and ship the localized Video settings UI (#9760)

changelog.d/features/9830-radar-local-model-state.md

@@ -1 +0,0 @@
-- **feat(radar):** Persist local model display-name/enabled overrides and hide/restore tombstones, with authenticated catalog controls and feed safety precedence ([#9830](https://github.com/diegosouzapw/OmniRoute/pull/9830))

changelog.d/features/9836-radar-guided-combos.md

@@ -1 +0,0 @@
-- **feat(radar):** add curated-family combo suggestions, a guided combo page, and the read-only Radar MCP catalog tool ([#9836](https://github.com/diegosouzapw/OmniRoute/pull/9836))

changelog.d/features/9912-radar-supporter-offers.md

@@ -1 +0,0 @@
-- **feat(radar):** add a signed live offers feed and supporter offers dashboard ([#9912](https://github.com/diegosouzapw/OmniRoute/pull/9912))

changelog.d/features/9923-radar-intel.md

@@ -1 +0,0 @@
-- **feat(radar):** add signed Intel insights, supporter recognition, and local Radar CLI commands ([#9923](https://github.com/diegosouzapw/OmniRoute/pull/9923))

changelog.d/features/9926-radar-launch-news.md

@@ -1 +0,0 @@
-- **feat(radar):** add a localized public news feed and dismissible dashboard launch banner, with the Radar announcement staged inactive for a separately authorized launch ([#9926](https://github.com/diegosouzapw/OmniRoute/pull/9926))

changelog.d/features/crofai-reasoning-efforts.md

@@ -1 +0,0 @@
-- feat(crof): advertise reasoning-effort tiers (none/low/medium/high/max) for live-discovered and seed models, so the catalog, Playground, and Combo Builder surface <model>-<tier> aliases and requests resolve max upstream

changelog.d/features/kimi-coding-extra-usage.md

@@ -1 +0,0 @@
-- **feat(usage):** show Kimi Coding's fixed-order Code 5-hour/7-day quota windows plus Extra Usage status, balance, monthly spend/limit, and the official Additional Credits link on Dashboard → Quota cards.

changelog.d/features/multimodal-embeddings-alias.md

@@ -1 +0,0 @@
-- **feat(api):** add `GET`/`POST` `/v1/multimodal-embeddings` as an alias of `/v1/embeddings` so Jina-compatible clients do not receive HTTP 404 `unknown_route` — thanks @RaviTharuma

changelog.d/features/unreleased-exclusive-managed-session-leases.md

@@ -1 +0,0 @@
-- **feat(routing):** add client-, provider-, and model-neutral exclusive managed session connection leases with API-key-bound generation fencing, durable SQLite ownership, explicit allowlist policy, and bounded 429 capacity retry semantics.

changelog.d/fixes/10017-sse-control-lines-leak-openai-clients.md

@@ -1 +0,0 @@
-- **Passthrough streaming:** stop leaking upstream SSE control lines (`id:`/`event:`/`retry:`/`:` comments) to plain OpenAI Chat-Completions-format clients, while preserving `event:` framing for OpenAI Responses API and Claude Messages API passthrough ([#10017](https://github.com/diegosouzapw/OmniRoute/issues/10017)).

changelog.d/fixes/10077-chatgpt-web-max-thinking-effort.md

@@ -1 +0,0 @@
-- **fix(chatgpt-web):** Preserve native `max` thinking effort through ChatGPT Web routing ([#10077](https://github.com/diegosouzapw/OmniRoute/pull/10077)) — thanks @zannen7

changelog.d/fixes/10078-agentrouter-quota-missing-dashboard.md

@@ -1,2 +0,0 @@
-- Fix: wire AgentRouter's existing console balance fetcher into the Dashboard Quota UI (visibility gate + provider-limits data path + background sync) so its wallet balance renders instead of falling back to "Usage API not implemented" (#10078)
-- Fix: AgentRouter's dollar balance now renders as a currency-formatted "$X.XX" credits row in the Dashboard Quota UI instead of a bare percentage, and an exhausted wallet always shows exactly $0.00 (#10078)

changelog.d/fixes/10085-compatible-chat-credential-mismatch.md

@@ -1 +0,0 @@
-- fix(sse): bridge generic openai-compatible/anthropic-compatible provider type ids to their concrete uuid node id in credential lookup (#10085)

changelog.d/fixes/10096-kimi-coding-apikey-save.md

@@ -1 +0,0 @@
-- fix(dashboard): remap unified Kimi Code card API-key save to the admitted `kimi-coding-apikey` connection id, fixing 400 "Invalid provider" on Save (#10096)

changelog.d/fixes/10104-antigravity-trailing-model-turn.md

@@ -1 +0,0 @@
-- fix(antigravity): strip trailing model turn for native Gemini requests too, not just Claude (#10104)

changelog.d/fixes/10111-adaptive-admission-latency-collapse.md

@@ -1 +0,0 @@
-- **fix(admission):** stop the adaptive latency-gradient collapse from permanently locking out ordinary requests — individually valid requests now make solo progress when the system is idle and normal pressure, and the collapsed limit actively recovers on sustained idle windows instead of being stuck; the critical-pressure fuse still wins over solo progress (#10111)

changelog.d/fixes/10119-claude-haiku-45-capability-flags.md

@@ -1 +0,0 @@
-- fix(sse): downgrade client-supplied `thinking:{type:"adaptive"}` to `enabled` and gate the `context-1m-2025-08-07` beta on model eligibility when a combo/fallback re-routes a request to a non-adaptive/non-1M model like claude-haiku-4-5 (avoids "adaptive thinking is not supported on this model" and "long context beta is not yet available" 400s, #10119)

changelog.d/fixes/10123-async-call-log-artifacts.md

@@ -1 +0,0 @@
-- **fix(logging):** move call-log artifact serialization and filesystem writes to a bounded singleton worker to keep request handling responsive (#10123)

changelog.d/fixes/10125-incremental-call-log-rotation.md

@@ -1 +0,0 @@
-- **perf(logging):** bound each scheduled call-log rotation pass to incremental database and filesystem work (#10125)

changelog.d/fixes/10127-early-sse-heartbeat.md

@@ -1 +0,0 @@
-- **fix(streaming):** start early SSE heartbeats when Responses or Messages requests opt into streaming through the request body (#10127)

changelog.d/fixes/10136-combo-scoped-session-stickiness.md

@@ -1 +0,0 @@
-- **fix(combo):** scope session-stickiness bindings to their owning Combo so identical first messages cannot carry a successful target into another priority chain and bypass its configured order (fixes #10136)

changelog.d/fixes/10139-thinking-output-cap-provider-scope.md

@@ -1 +0,0 @@
-- **fix(translator):** resolve the Claude thinking output cap with the routed provider so a provider-scoped-only `max_output_tokens` override is no longer invisible to `fitThinkingToMaxTokens()`, which previously let the synthesized `max_tokens` (caller room + thinking budget) go out unbounded and 400 upstream ([#10139](https://github.com/diegosouzapw/OmniRoute/issues/10139))

changelog.d/fixes/10140-conol-web-import-depth.md

@@ -1,3 +0,0 @@
-- fix(providers): correct the conol-web registry fallback-models import depth, which pointed at a
-  non-existent `open-sse/config/services/` and made any suite loading the provider registry fail to
-  resolve (#10140)