chore(deps): patch toml and esbuild in the opencode plugin lockfiles

Two Dependabot alerts on the opencode plugin workspaces, both dev-scope: - #209 (high) toml@4.1.1 — prototype pollution via `__proto__` key-path desynchronization (GHSA-v5mp-jgw5-2x6j), pulled transitively by `effect` under `@opencode-ai/plugin`. Patched in 4.1.2. - #210 (low) esbuild@0.27.7 — arbitrary file read from the dev server on Windows (GHSA-g7r4-m6w7-qqqr), nested under `tsup`. Patched in 0.28.1. The top-level esbuild was already 0.28.1; only the nested copy lagged. Both are resolved with an `overrides` entry, reusing the pattern the v1 plugin already applies to esbuild. Neither package reaches the published runtime — they are build-time only — so this is hygiene, not an exposure fix. toml 4.1.1 -> 4.3.0, nested esbuild 0.27.7 dropped (single 0.28.2 remains). `npm install` reports 0 vulnerabilities in both workspaces; both plugins build and their suites pass (367 and 218 tests).
2026-09-22 14:52:22 +03:00 · 2026-09-07 11:14:49 -03:00
13050 changed files with 361272 additions and 4269675 deletions
--- a/.dockerignore
+++ b/.dockerignore
@@ -73,11 +73,6 @@ docs/i18n/**
 # so without this rule these land in /app/docs and become readable through the
 # dashboard's Docs viewer at runtime.
 docs/superpowers/**
-# Operator-internal security writeups: git only, not the image or /docs catalog.
-docs/security/STEALTH_GUIDE.md
-docs/security/SOCKET_DEV_FINDINGS.md
-docs/security/MITM-TPROXY-DECRYPT.md
-docs/security/PUBLIC_CREDS.md
 docs/diagrams/**/*.png
 docs/diagrams/**/*.jpg
 docs/diagrams/**/*.jpeg
--- a/.env.example
+++ b/.env.example
@@ -112,9 +112,8 @@ DISABLE_SQLITE_AUTO_BACKUP=false
 # 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 + warmup circuit breaker). Prevents key collisions when OmniRoute
-# shares a Redis instance with other apps (e.g. on 127.0.0.1:6379). Default when
-# unset: omniroute:
+# 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
@@ -125,21 +124,6 @@ DISABLE_SQLITE_AUTO_BACKUP=false
 # Host port for the compose Redis sidecar. Default: 6379.
 # REDIS_PORT=6379

-# Host interface docker-compose publishes the app's own ports (dashboard,
-# API, live-WS) on for the base/web/cli/host profiles and docker-compose.prod.yml.
-# Default: 127.0.0.1 (loopback only). Combined with REQUIRE_API_KEY=false
-# (the default below), an unqualified publish spec would expose the anonymous
-# /v1 LLM proxy to your whole LAN/WAN. Only set this to 0.0.0.0 once you've
-# confirmed REQUIRE_API_KEY=true, or that a reverse proxy in front of this
-# instance already enforces its own authentication. (#12568)
-# APP_BIND_HOST=127.0.0.1
-# Host interface docker-compose publishes the Qdrant memory sidecar on.
-# Default: 127.0.0.1 (loopback only). Same LAN-exposure reasoning as Redis.
-# QDRANT_BIND_HOST=127.0.0.1
-# Host interface docker-compose publishes the Bifrost router sidecar on.
-# Default: 127.0.0.1 (loopback only). Same LAN-exposure reasoning as Redis.
-# BIFROST_BIND_HOST=127.0.0.1
-
 # ═══════════════════════════════════════════════════════════════════════════════
 # 3. NETWORK & PORTS
 # ═══════════════════════════════════════════════════════════════════════════════
@@ -173,11 +157,6 @@ PORT=20128
 # stay consistent without relying on window.location.origin alone:
 # NEXT_PUBLIC_BASE_URL=https://host/omniroute
 #
-# Client-side fallback port for display URLs when no origin is known (SSR/tests):
-# read before PORT so a browser bundle built with a different public port still
-# renders the right http://localhost:<port> links (src/shared/hooks/useDisplayBaseUrl.ts).
-# NEXT_PUBLIC_PORT=20128
-#
 # Explicit path probed by the container health check. Unset, the probe derives it
 # from OMNIROUTE_BASE_PATH; setting it opts back into the deep monitoring endpoint.
 # Used by: scripts/dev/healthcheck.mjs
@@ -394,8 +373,6 @@ AUTH_COOKIE_SECURE=false
 # Require an API key for all /v1/* proxy endpoints.
 # Used by: API middleware — rejects unauthenticated requests to the proxy API.
 # Default: false  |  Set true for multi-user/public deployments.
-# Leaving this false is only safe when the app is reachable on loopback only
-# (see APP_BIND_HOST above) or sits behind a reverse proxy doing its own auth.
 REQUIRE_API_KEY=false

 # Allow revealing full API key values in the Dashboard UI.
@@ -546,48 +523,6 @@ ALLOW_API_KEY_REVEAL=false
 # When unset, OmniRoute uses the per-feature defaults. Set to "false"/"0" to disable.
 # OUTBOUND_SSRF_GUARD_ENABLED=true

-# ── Self-hosted unified OpenAI-compatible entry (RIC-738, D4) ────────────────────
-# When set, /v1/chat/completions diverts to the self-hosted provider adapters
-# (open-sse/services/selfHostedEntry.ts) instead of the cloud pipeline. YAML inline
-# (example) — or point OMNIROUTE_SELF_HOSTED_PROVIDERS_FILE at a YAML file. Secrets
-# are runtime-only, never logged. While ANY of these is set, the entry is active;
-# config present but unparseable returns a 500 (never silently falls through).
-# OMNIROUTE_SELF_HOSTED_PROVIDERS='
-#   providers:
-#     - id: local
-#       kind: openai
-#       baseUrl: http://127.0.0.1:11434/v1
-#       model: llama3
-#     - id: claude
-#       kind: anthropic
-#       baseUrl: http://127.0.0.1:8080
-#       model: claude-sonnet
-# '
-# OMNIROUTE_SELF_HOSTED_PROVIDERS_FILE=/etc/omniroute/providers.yaml
-# Optional shared API key for the unified entry (D5 reserved). When set, require
-# `Authorization: Bearer <key>`; empty = open loopback/trusted-network route.
-# OMNIROUTE_SELF_HOSTED_API_KEY=
-
-# ── Deterministic routing strategies (M2 / RIC-740, D3 可审计路由) ─────────────
-# Optional `strategy:` block — either inline in the providers document above, or a
-# standalone document via these env vars. One rule per line; every decision is
-# explainable via the `x-omniroute-route-decision` response header. No ML/predict.
-# Malformed strategy config returns a 500 (never silently becomes a no-op).
-# Example (inline, same shape as `strategy:` inside the providers YAML):
-# OMNIROUTE_SELF_HOSTED_STRATEGY='
-#   blacklist: []
-#   whitelist: [cheap, fast, premium]
-#   costPriority: true
-#   latencyAware:
-#     enabled: true
-#   cooldown:
-#     consecutiveFailures: 2
-#     cooldownMs: 30000
-#   fallbackChain: [cheap, fast, premium]
-# '
-# OMNIROUTE_SELF_HOSTED_STRATEGY_FILE=/etc/omniroute/strategy.yaml
-# See docs/routing/DETERMINISTIC_ROUTING.md for the full strategy surface.
-
 # ═══════════════════════════════════════════════════════════════════════════════
 # 5. INPUT SANITIZATION & PII PROTECTION (FASE-01)
 # ═══════════════════════════════════════════════════════════════════════════════
@@ -669,15 +604,6 @@ ALLOW_API_KEY_REVEAL=false
 # Validated to >= 1, clamped to <= 32.  |  Default: 3
 # COMBO_CONCURRENCY_PER_MODEL=3

-# Disable conversation-history tracking (#13150).
-# Used by: open-sse/services/conversationTracker.ts. resolveConversationId()
-# returns an untracked result before it reads SQLite or parses message history,
-# and the switch also covers client-supplied session IDs. Routing sessions are
-# unaffected and existing records are not deleted. Use it when the dashboard's
-# conversation view is unused and the turn table has grown large.
-# Set to 1 to disable.  |  Default: unset (tracking enabled)
-# OMNIROUTE_DISABLE_CONVERSATION_TRACKING=1
-
 # ═══════════════════════════════════════════════════════════════════════════════
 # 7. URLS & CLOUD SYNC
 # ═══════════════════════════════════════════════════════════════════════════════
@@ -768,26 +694,14 @@ NEXT_PUBLIC_CLOUD_URL=
 # OpenCode Go/Zen VPS egress (#5997): on a datacenter VPS, Cloudflare in front of
 # opencode.ai/zen/go 403s chat requests that lack OpenCode CLI identity headers.
 # When your clients don't already send them, set this to synthesize the CLI headers
-# (User-Agent, x-opencode-client, x-opencode-project, canonical request/session ids) on
-# absent keys. ON by default — a client value always wins, these only fill gaps.
+# (User-Agent, x-opencode-client, x-opencode-project, fresh request/session UUIDs) on
+# absent keys. OFF by default — forward-only is safer when clients already send them.
 # Values are overridable via OPENCODE_GO_USER_AGENT / OPENCODE_USER_AGENT / OPENCODE_CLIENT /
-# OPENCODE_PROJECT (defaults: opencode/1.18.31 / desktop / global).
+# OPENCODE_PROJECT (defaults: opencode-cli/1.0.0 / cli / default).
 #OPENCODE_SYNTHESIZE_CLI_HEADERS=true
-#OPENCODE_USER_AGENT=opencode/1.18.31
-#OPENCODE_CLIENT=desktop
-#OPENCODE_PROJECT=global
-
-# Keyless OpenCode models are answered only when the request declares a non-empty tool
-# list, and the upstream inspects which names it carries. OmniRoute reuses the list a
-# request of the same conversation was last seen getting through, so a request that
-# carries none — a title or a summary — goes out with the list its own client already
-# declared. Set to off to stop adjusting request bodies entirely; headers are unaffected.
-#OPENCODE_FREE_TIER_REQUEST_CONTRACT=off
-
-# Tool names to declare when nothing has been observed yet for a model, comma-separated.
-# Empty falls back to a single placeholder the model is told not to call. Only useful on
-# an install where no client sends tools, since there is then nothing to learn from.
-#OPENCODE_FREE_TIER_PLACEHOLDER_TOOLS=glob,grep,read
+#OPENCODE_USER_AGENT=opencode-cli/1.0.0
+#OPENCODE_CLIENT=cli
+#OPENCODE_PROJECT=default

 # Ollama Cloud quota scraping. Prefer configuring this per connection in
 # Dashboard → Providers → Ollama Cloud. The cookie is sensitive.
@@ -806,12 +720,6 @@ NEXT_PUBLIC_CLOUD_URL=
 ENABLE_SOCKS5_PROXY=true
 NEXT_PUBLIC_ENABLE_SOCKS5_PROXY=true

-# Opt-in feature flag (default off; a dashboard DB override wins over this value): proxy pools
-# and per-account rotation stop re-serving a member that just failed (TCP probe refused, or a
-# 429 received through it) for a period that doubles on each repeat, up to a cap. No proxy
-# status is written. "true" (or 1, yes) enables it; unset keeps plain selection.
-# PROXY_SKIP_RECENTLY_FAILED=false
-
 # Standard proxy variables (lowercase variants also supported).
 # HTTP_PROXY=http://127.0.0.1:7890
 # HTTPS_PROXY=http://127.0.0.1:7890
@@ -1109,12 +1017,6 @@ PROVIDER_LIMITS_SYNC_SPACING_MS=1500
 # Used by: src/lib/jobs/reasoningCacheCleanupJob.ts.
 #OMNIROUTE_REASONING_CACHE_CLEANUP_INTERVAL_MS=1800000

-# Opt-in minimum output budget (tokens) for reasoning models (#10281 follow-up).
-# When set, a caller max_tokens in [256, floor) on a thinking-capable model is
-# raised to the floor so reasoning tokens cannot consume the whole budget
-# (zero-content finish_reason=length turns). Unset = never enlarge client budgets (#9507).
-#OMNIROUTE_REASONING_MIN_BUDGET=4096
-
 # Spend write batcher cadence (ms) and buffer size before forced flush.
 # Used by: src/lib/spend/batchWriter.ts.  Defaults: 60000 ms / 1000 entries.
 #OMNIROUTE_SPEND_FLUSH_INTERVAL_MS=60000
@@ -1161,11 +1063,6 @@ PROVIDER_LIMITS_SYNC_SPACING_MS=1500
 # Used by: open-sse/services/compression/engines/rtk/filterLoader.ts.  Default: 0.
 #OMNIROUTE_RTK_TRUST_PROJECT_FILTERS=0

-# Character cap for Lite proactive tool-result truncation when lite.maxToolLength
-# is unset. Range 256-1000000. Dashboard setting wins over this env.
-# Used by: open-sse/services/compression/lite.ts.  Default: 2000.
-#OMNIROUTE_LITE_MAX_TOOL_LENGTH=2000
-
 # Maximum concurrent synchronous compression workers. Excess jobs wait FIFO.
 # Used by: open-sse/services/compression/compressionWorkerPool.ts. Default: 2.
 #OMNI_COMPRESSION_WORKERS=2
@@ -1222,38 +1119,10 @@ PROVIDER_LIMITS_SYNC_SPACING_MS=1500
 # Used by: src/lib/db/core.ts::getDbHealthCheckIntervalMs().
 #OMNIROUTE_DB_HEALTHCHECK_INTERVAL_MS=21600000

-# Removed: periodic live wal_checkpoint(TRUNCATE) could SIGBUS the process (issue
-# #13973). The variable is inert: a positive value logs a one-time deprecation warning,
-# while 0 or unset stays silent. The WAL is kept small
-# by the PASSIVE scheduler below and truncated by the shutdown checkpoint.
+# WAL truncate cadence override (ms).  Set to 0 to disable.  Default: 21600000 (6h).
+# Used by: src/lib/db/core.ts::getWalTruncateIntervalMs().
 #OMNIROUTE_WAL_TRUNCATE_INTERVAL_MS=21600000

-# Frequent wal_checkpoint(PASSIVE) cadence (ms).  Set to 0 to disable.  Default: 300000 (5m).
-# Used by: src/lib/db/walMaintenance.ts.
-#OMNIROUTE_WAL_PASSIVE_INTERVAL_MS=300000
-
-# WAL size (MB) above which a PASSIVE tick runs wal_checkpoint(RESTART) so the
-# WAL starts over without rewriting the mapped wal-index. Default: 256.
-# Used by: src/lib/db/walMaintenance.ts.
-#OMNIROUTE_WAL_GUARD_MAX_MB=256
-
-# Explicit path to sql-wasm.wasm for the sql.js fallback adapter.  Default: auto-detect.
-# Used by: src/lib/db/adapters/sqljsAdapter.ts.
-#OMNIROUTE_SQLJS_WASM_PATH=
-# Days a terminal (completed/failed/cancelled/expired) Batch API job's checkpoints,
-# referenced files, and row are kept by the automatic cleanup sweep.  Default: 30
-# (matches OpenAI's own Batch API output retention window). Only takes effect once
-# BATCH_AND_FILE_AUTO_CLEANUP_ENABLED is turned on.
-# Used by: src/lib/db/cleanup.ts::getBatchRetentionDays().
-#OMNIROUTE_BATCH_RETENTION_DAYS=30
-
-# Let the automatic cleanup sweep delete terminal Batch API jobs (and their
-# checkpoints) past OMNIROUTE_BATCH_RETENTION_DAYS, and clear the content of
-# uploaded files past their own expires_at. Off by default: every existing
-# install keeps this data exactly as before until an operator opts in.
-# Used by: src/lib/db/cleanup.ts (feature flag; see docs/reference/FEATURE_FLAGS.md).
-#BATCH_AND_FILE_AUTO_CLEANUP_ENABLED=false
-
 # Skip the Redis-backed auth cache used by API key lookups (forces DB reads).
 # Used by: src/lib/db/apiKeys.ts.  Set to 1 to disable.  Default: enabled.
 #OMNIROUTE_DISABLE_REDIS_AUTH_CACHE=0
@@ -1306,11 +1175,6 @@ CODEX_OAUTH_CLIENT_ID=app_EMoamEEZ73f0CkXaXp7hrann
 # Trae OAuth token override. Used by: open-sse/executors/trae.ts.
 # TRAE_TOKEN=

-# Trae web client Origin/Referer override (fleet-wide bump if Trae moves hosts
-# again without a code change). Default: https://work.trae.ai.
-# Used by: open-sse/executors/trae.ts.
-# TRAE_WEB_ORIGIN=https://work.trae.ai
-
 # ── Gemini / Antigravity (Google-based) ──
 # These providers ship public OAuth client_id/secret values embedded in their
 # public CLIs. Defaults are baked into the code via
@@ -1447,8 +1311,7 @@ CLAUDE_USER_AGENT="claude-cli/2.1.258 (external, cli)"
 # stream with a misleading 400 out-of-extra-usage placeholder. Set to true to
 # forward the original names verbatim (debugging only).
 # CLAUDE_DISABLE_TOOL_NAME_CLOAK=false
-# Optional override; leave unset to follow the shared Codex client version.
-# CODEX_USER_AGENT="codex-cli/0.153.4 (Windows 10.0.26200; x64)"
+CODEX_USER_AGENT="codex-cli/0.144.1 (Windows 10.0.26200; x64)"
 GITHUB_USER_AGENT="GitHubCopilotChat/0.54.0"
 ANTIGRAVITY_USER_AGENT="antigravity/2.0.1 linux/arm64 google-api-nodejs-client/10.3.0"
 KIRO_USER_AGENT="AWS-SDK-JS/3.0.0 kiro-ide/1.0.0"
@@ -1468,7 +1331,7 @@ CURSOR_USER_AGENT="Cursor/3.4"

 # Override Codex client version sent in headers independently of the
 # CODEX_USER_AGENT string. Used by: open-sse/config/codexClient.ts.
-# CODEX_CLIENT_VERSION=0.153.4
+# CODEX_CLIENT_VERSION=0.144.1
 #
 # Override the advertised Claude Code client version independently of
 # CLAUDE_USER_AGENT. Anthropic gates some models (Fable 5.1) on this
@@ -1479,13 +1342,6 @@ CURSOR_USER_AGENT="Cursor/3.4"
 # Override the advertised GitHub Copilot CLI version independently of
 # GITHUB_USER_AGENT. Used by: open-sse/config/providerHeaderProfiles.ts.
 # GITHUB_COPILOT_CLI_VERSION=1.0.82
-#
-# Pin the `copilot-integration-id` header sent to standard GitHub Copilot,
-# overriding the default copilot-developer-cli identity (and disabling the
-# automatic 403-identity fallback to copilot-chat). Set this only if your
-# Copilot account/org requires a specific integration id. Used by:
-# open-sse/config/providerHeaderProfiles.ts, open-sse/executors/copilotIdentityFallback.ts.
-# COPILOT_INTEGRATION_ID=copilot-chat

 # Kill-switch to strip non-standard `codex.*` SSE events (e.g. codex.rate_limits)
 # from the Codex Responses stream. These frames break the OpenAI SDK's
@@ -1593,7 +1449,7 @@ CURSOR_USER_AGENT="Cursor/3.4"
 #
 # Hierarchy: REQUEST_TIMEOUT_MS acts as a global override.
 # If set, it becomes the default for FETCH_TIMEOUT_MS, STREAM_IDLE_TIMEOUT_MS,
-# and STREAM_READINESS_TIMEOUT_MS. STREAM_ACTIVE_TIMEOUT_MS is independent.
+# and STREAM_READINESS_TIMEOUT_MS.
 # The fine-grained variables below override their respective defaults only when set.

 # ── Global shortcut ──
@@ -1614,18 +1470,6 @@ CURSOR_USER_AGENT="Cursor/3.4"
 #                                     # caller's deadline; on expiry the request retries
 #                                     # once on a fresh no-keep-alive socket. 0 disables
 #                                     # the bound (default: 30000 = 30s).
-# OMNIROUTE_DIRECT_RESPONSE_RETRY_TIMEOUT_MS=600000  # Ceiling (ms) for the fresh-socket
-#                                     # RETRY attempt above (#13703). Only applies when
-#                                     # the caller already attached its own deadline
-#                                     # signal (the resolved connection/model/provider/
-#                                     # FETCH_TIMEOUT_MS cascade) — that signal is the
-#                                     # real bound and fires first in the intended path,
-#                                     # so this is a generous backstop rather than a flat
-#                                     # cap: without it the retry reused the same short
-#                                     # OMNIROUTE_DIRECT_HEADERS_TIMEOUT_MS window as the
-#                                     # pooled attempt and 504'd healthy slow-TTFB
-#                                     # reasoning models. Never allowed below the flat
-#                                     # floor above (default: 600000 = 10 min).

 # Default timeout (ms) for src/shared/utils/fetchTimeout.ts. Acts as the
 # fallback when FETCH_TIMEOUT_MS is unset. Default: 120000 (2 min).
@@ -1787,8 +1631,6 @@ CURSOR_USER_AGENT="Cursor/3.4"
 # ── Stream idle detection ──
 # STREAM_IDLE_TIMEOUT_MS=600000      # Max silence between SSE chunks (default: 600000)
 #                                     # Extended-thinking models rarely pause >90s.
-# STREAM_ACTIVE_TIMEOUT_MS=1260000    # Max total active SSE lifetime (default: 21 min = the largest registered model timeoutMs + 1 min; 0 disables)
-#                                     # Independent of REQUEST_TIMEOUT_MS and byte activity.
 # STREAM_READINESS_TIMEOUT_MS=80000  # Time to receive the first non-ping SSE event
 # STREAM_READINESS_MAX_TIMEOUT_MS=180000 # Cap for adaptive first-event extensions
 #                                         # (large/tool-heavy/high-reasoning requests).
@@ -1804,11 +1646,6 @@ CURSOR_USER_AGENT="Cursor/3.4"

 # ── TLS client (wreq-js fingerprint proxy) ──
 # TLS_CLIENT_TIMEOUT_MS=600000       # Inherits from FETCH_TIMEOUT_MS by default
-# TLS_FIRST_BYTE_WATCHDOG_MS=10000   # #12656: bounds time-to-first-byte on the wreq body (0 disables)
-# OPENCODE_RESPONSES_STALL_ROTATION=false  # #13484 feature flag (Settings → Feature Flags wins): rotate once when a streamed Responses reply stalls before its first byte
-# OPENCODE_PARK_AND_RESUME=false  # #13924 feature flag (Settings → Feature Flags wins): park the request with a heartbeat after repeated transient 429s, then replay one capped leg of up to 3 accounts
-#OPENCODE_POOL_STRAIN_MARKER_PATH=/tmp/opencode-pool-strain.json  # #13924: pool-strain marker path (JSON {since, reason, ttl_s}); fresh marker parks without recounting
-# RESPONSES_FIRST_BYTE_TIMEOUT_MS=15000  # #13484: OpenCode Responses first-byte window, only used when the OPENCODE_RESPONSES_STALL_ROTATION flag is on (0 disables)

 # ── API Bridge (/v1 proxy server) ──
 # API_BRIDGE_PROXY_TIMEOUT_MS=600000             # Proxy hop timeout (default: 10min)
@@ -1897,8 +1734,8 @@ APP_LOG_TO_FILE=true
 # bodies is retained in the database.
 # Used by: open-sse/handlers/chatCore.ts — cloneBoundedChatLogPayload()
 # CHAT_LOG_TEXT_LIMIT=65536                  # Max string length before truncation (default: 64 KB)
-# CHAT_LOG_ARRAY_TAIL_ITEMS=1000             # Number of array items retained from tail (default: 1000)
-# CHAT_LOG_MAX_DEPTH=20                      # Max nesting depth before truncation (default: 20)
+# CHAT_LOG_ARRAY_TAIL_ITEMS=128              # Number of array items retained from tail (default: 128)
+# CHAT_LOG_MAX_DEPTH=6                       # Max nesting depth before truncation (default: 6)
 # CHAT_LOG_MAX_OBJECT_KEYS=80                # Max object keys retained (default: 80, 0 = no limit)
 # CHAT_LOG_MAX_BODY_KB=1024                  # Whole request/response body size before it's replaced by a bare
                                              # {_truncated, messageCount, ...} summary instead of the full clone
@@ -1939,13 +1776,6 @@ APP_LOG_TO_FILE=true
 # Override only to hand-tune for a known workload.
 # HEAP_PRESSURE_THRESHOLD_MB=

-# Exit the process after critical resource pressure persists, so a supervisor
-# (systemd Restart=always, Docker restart policy) brings back a clean process.
-# Accepts 1/true/yes/on.  Default: false.  Used by: open-sse/utils/resourcePressure.ts.
-# OMNIROUTE_PRESSURE_SELF_RESTART=false
-# How long (ms) critical pressure must persist before that exit fires.  Default: 120000 (2m).
-# OMNIROUTE_PRESSURE_SELF_RESTART_AFTER_MS=120000
-
 # ── CLI helpers (bin/cli/) ──
 # Override UI language for CLI output. Accepts BCP-47 locale (e.g. en, pt-BR).
 # Falls back to LC_ALL / LC_MESSAGES / LANG / en if unset.
@@ -1963,10 +1793,6 @@ APP_LOG_TO_FILE=true
 # Per-attempt HTTP timeout for CLI → server calls (milliseconds). Default: 30000.
 # OMNIROUTE_HTTP_TIMEOUT_MS=30000

-# How long `omniroute serve` waits for the health endpoint before printing the
-# readiness-timeout warning (milliseconds). Also --ready-timeout. Default: 60000.
-# OMNIROUTE_READY_TIMEOUT_MS=60000
-
 # Set to 1 to print retry/backoff details to stderr during CLI commands.
 # OMNIROUTE_VERBOSE=0

@@ -2112,12 +1938,6 @@ APP_LOG_TO_FILE=true
 # Default: 8000 (8 seconds). On timeout, a last-good 200 is served when available.
 # CATALOG_BUILD_TIMEOUT_MS=8000

-# Age after which a connection's synced model list stops being authoritative for routing (#12849).
-# A stale (or never-timestamped) synced catalog fails open to the provider registry.
-# Used by: src/lib/db/models/activeSyncedCatalog.ts
-# Default: 2592000000 (30 days)
-# OMNIROUTE_SYNCED_CATALOG_STALE_AFTER_MS=2592000000
-
 # ── NanoBanana (Image Generation) ──
 # Polling config for async image generation jobs.
 # Used by: open-sse/handlers/imageGeneration.ts
@@ -2257,13 +2077,6 @@ APP_LOG_TO_FILE=true
 # Management key for an externally managed instance. Embedded instances use
 # OmniRoute's encrypted service key.
 # CLIPROXYAPI_MANAGEMENT_KEY=
-# Host interface docker-compose publishes the cliproxyapi sidecar on (the
-# --profile cliproxyapi Docker service, port 8317). Default: 127.0.0.1
-# (loopback only) — its data volume holds provider OAuth/API credentials, and
-# the pinned image has no env-based data-plane api-keys override (only a
-# mounted config.yaml), so an unqualified publish spec would put a
-# credential-bearing service on your whole LAN. (#12578)
-# CLIPROXY_BIND_HOST=127.0.0.1

 # ── Mux embedded service ──
 # Override the port where the embedded Mux (coder/mux) agent-orchestration
@@ -2272,13 +2085,6 @@ APP_LOG_TO_FILE=true
 # Used by: src/lib/services/bootstrap.ts, src/app/api/services/mux/_lib.ts
 # MUX_SERVICE_PORT=8322

-# ── open-wa embedded service ──
-# Override the port where the embedded open-wa (WhatsApp Web automation)
-# daemon listens. Always bound to 127.0.0.1 — never configurable to 0.0.0.0.
-# Rarely needed — defaults to 8323.
-# Used by: src/lib/services/bootstrap.ts
-# OPENWA_SERVICE_PORT=8323
-
 # ── Dario embedded service ──
 # Override the host/port the embedded Dario (Claude Code subscription proxy)
 # daemon binds to and is reached at. Always bound to 127.0.0.1 — never
@@ -2361,20 +2167,15 @@ APP_LOG_TO_FILE=true
 # proxy — only the operator sets active/inactive (a flaky probe must not strand an
 # assigned proxy; #6246). Set "true" to restore the legacy test-and-set behaviour.
 # PROXY_HEALTH_AUTO_DEACTIVATE=false
-# Opt-in feature flag (default off; a dashboard DB override wins over this value): show,
-# under a proxy pool in the dashboard, how many observed egress IPs served its members over
-# the last 24 h and how many connections used them (read-only, computed from the proxy log,
-# never used for routing). "true" (or 1, yes) enables it.
-# PROXY_POOL_EGRESS_OBSERVATION=false

 # Allow OAuth and provider validation flows to bypass a pinned proxy and connect
 # directly when proxy reachability pre-checks fail. Default: false.
 # Also configurable from Dashboard > Settings > Feature Flags.
 # OMNIROUTE_CONTROL_PLANE_PROXY_DIRECT_FALLBACK=false

-# Rate limit maximum wait time before failing a request (ms).  Default: 30000 (30s)
+# Rate limit maximum wait time before failing a request (ms).  Default: 15000 (15s)
 # Used by: open-sse/services/rateLimitManager.ts
-# RATE_LIMIT_MAX_WAIT_MS=30000
+# RATE_LIMIT_MAX_WAIT_MS=15000

 # Limiter-managed execution backstop (Bottleneck `expiration`): bounds a job's
 # post-dispatch execution, never queue wait. Must stay ABOVE upstream
@@ -2479,10 +2280,6 @@ APP_LOG_TO_FILE=true
 # Cursor stream idle timeout (ms). Default: 300000 (5 min).
 # Used by: open-sse/executors/cursor.ts.
 # CURSOR_STREAM_TIMEOUT_MS=300000
-# Grace window (ms) after a composer kv_after_text soft terminator when bytes remain
-# buffered — gives a trailing exec_mcp tool call time to complete its frame. 2s covers
-# every exec_mcp-behind-kv ordering observed live.
-# CURSOR_KV_GRACE_MS=2000

 # Cursor tool-commit directive toggle. Default-on: when a request declares
 # tools, a directive is prepended so composer-2.5 reliably issues tool calls
@@ -2490,22 +2287,6 @@ APP_LOG_TO_FILE=true
 # Used by: open-sse/executors/cursor.ts.
 # CURSOR_TOOL_DIRECTIVE=1

-# Operator-defined system prompt text appended to the system message AFTER
-# translation (post-translation injection), so it reaches codex/Responses and
-# /v1/messages paths. Also used as the directive prefix stripped from echoed
-# system preamble blocks. Leave unset to disable.
-# Used by: open-sse/translator/request/claude-to-openai.ts, open-sse/translator/response/openai-to-claude.ts.
-# OMNIROUTE_SYSTEM_INSTRUCTION_APPEND=
-
-# Set to "1" to also strip echoed system-prompt PREAMBLE blocks
-# (<analysis>/<system-reminder>/<summary> blocks, prose reproductions of the skill
-# section) from the start of an openai->claude stream. OFF by default: it recognises
-# constructs by English-prose heuristics and DOES mutate the response payload, so a
-# reply that genuinely opens with such a section would lose it. Turn it on only when
-# you actually hit the system-echo leak.
-# Used by: open-sse/translator/response/openai-to-claude.ts, open-sse/utils/directivePreambleStripper.ts.
-# OMNIROUTE_STRIP_SYSTEM_PREAMBLE=0
-
 # Per-image fetch timeout (ms) for remote image_url vision input. Default: 15000.
 # Used by: open-sse/utils/cursorImages.ts.
 # CURSOR_IMAGE_FETCH_TIMEOUT_MS=15000
@@ -2702,16 +2483,6 @@ APP_LOG_TO_FILE=true
 # for root-less / user-namespaced deployments (e.g. rootless Docker/Podman)
 # where the operator trusts the CA manually (e.g. via Node's extra-CA-certs mechanism).
 # OMNIROUTE_NO_SUDO=0
-
-# ── Antigravity MITM bridge (bin/antigravity-bridge.mjs) ──
-# Local HTTPS listener that fronts the Antigravity IDE and forwards to the router.
-# BRIDGE_PORT: port the bridge listens on. Defaults to 20129.
-# ROUTER_URL: where it forwards /v1/antigravity traffic. Defaults to the local router.
-# CERT_DIR: directory holding server.key/server.crt for the bridge's TLS listener.
-# Defaults to ~/.omniroute/mitm (the MITM CA directory).
-# BRIDGE_PORT=20129
-# ROUTER_URL=http://127.0.0.1:20128/v1/antigravity
-# CERT_DIR=~/.omniroute/mitm
 # Explicit opt-out: skip provisioning /etc/hosts DNS entries for the Antigravity
 # proxy hostnames entirely (containers with no sudo/root available).
 # Used by: src/mitm/dns/provision.ts.
@@ -2748,16 +2519,6 @@ APP_LOG_TO_FILE=true
 # When enabled, the node authenticates with the API key stored on its connection.
 # AUDIO_REMOTE_PROVIDER_NODES=false

-# Used by: src/app/api/v1/_shared/rerankProviderNodes.ts — lets POST /v1/rerank (and
-# the memory engine's loopback rerank step) use an OpenAI-compatible provider node
-# hosted outside localhost, e.g. a LAN box or Tailscale peer running TEI/Infinity/vLLM.
-# OFF by default: routing to a remote host changes egress identity, so it must be an
-# explicit operator decision. Loopback/private nodes (localhost, 127.0.0.1,
-# 172.16-31.x) are always allowed and unaffected by this flag. Remote nodes must also
-# pass the provider outbound URL policy (see OMNIROUTE_ALLOW_LOCAL_PROVIDER_URLS);
-# cloud-metadata hosts are never routed to.
-# RERANK_REMOTE_PROVIDER_NODES=false
-
 # ── Free Proxy Pool (auto-sync scheduler) ──
 # Background refresh of the free-proxy pool. Opt-in, OFF by default (parallels
 # Hard Rule #20's default-off posture for data-mutating background features).
@@ -2910,13 +2671,6 @@ APP_LOG_TO_FILE=true
 # tokens (accessToken / refreshToken / providerSpecificData). Default OFF —
 # only non-credential metadata is synced. See docs/security/SOCKET_DEV_FINDINGS.md §5.
 # OMNIROUTE_CLOUD_SYNC_SECRETS=false
-#
-# Set to "true" to reject an UNSIGNED Cloud sync response when no local secret
-# is configured (#13679). Default OFF keeps v3.8.x back-compat for peers that
-# have not rotated in a shared secret yet; v3.9 flips the default to enforced.
-# A signature that IS present is always verified, and always rejected when
-# OMNIROUTE_CLOUD_SYNC_SECRET is unset, regardless of this flag.
-# OMNIROUTE_CLOUD_SYNC_ENFORCE_SIGNATURE=false

 # ─── Zed import legacy compat (v3.8.6) ──────────────────────────────────────
 # Set to "true" to fall back to the v3.8.5 one-step "import everything from
@@ -2967,10 +2721,6 @@ PLAYGROUND_COMPARE_MAX_COLUMNS=4
 # MEMORY_VEC_TOP_K=20                           # default top-K for vector search
 # MEMORY_RRF_K=60                               # RRF k constant (sqlite-vec hybrid recipe)
 # HF_HUB_ENDPOINT=https://huggingface.co        # override Hugging Face Hub base URL for static potion downloads
-# Test/diagnostic seam (src/lib/memory/vectorStore.ts) — forces getVectorStore() to
-# return null (simulates a cloud/WASM environment without sqlite-vec), degrading
-# memory retrieval to FTS5 keyword search. Default off; leave unset in production.
-# VECTOR_STORE_DISABLE_VEC=false
 # TV6 typed memory decay (OPT-IN, default off — the sweep DELETES decayed memories)
 # MEMORY_TYPED_DECAY_ENABLED=false              # master switch for the destructive sweep (default off)
 # MEMORY_TYPED_DECAY_EPISODIC_DAYS=30           # episodic TTL in days; 0 = episodic immune too
@@ -3212,13 +2962,6 @@ QUOTA_STORE_DRIVER=sqlite
 # CHATGPT_WEB_CODEX_CHROME_PATH=/usr/bin/chromium
 # CHROME_PATH=/usr/bin/chromium
 # CHATGPT_WEB_CODEX_CDP_URL=http://chatgpt-web-codex-browser:9223
-# CDP_PROXY_TOKEN required by docker/chatgpt-web-codex-browser/cdp-proxy.mjs (#13679):
-# when set, every request to the CDP proxy sidecar must present it as an
-# `X-Omni-Cdp-Token` header. Left unset, the proxy keeps forwarding requests
-# unauthenticated (network isolation via docker-compose.yml's dedicated
-# `chatgpt-web-codex-net` is the default mitigation). Generate with:
-# `openssl rand -hex 32`
-# CDP_PROXY_TOKEN=
 # CHATGPT_WEB_CODEX_TUNNEL_ID=tunnel_0123456789abcdef0123456789abcdef
 # CHATGPT_WEB_CODEX_RUNTIME_KEY=
 # CHATGPT_WEB_CODEX_CONNECTOR_NAME=OmniRoute Codex v2
@@ -3247,7 +2990,6 @@ QUOTA_STORE_DRIVER=sqlite
 # OMNIROUTE_VNC_READY_MS=45000
 # OMNIROUTE_VNC_HARVEST_MS=20000
 # OMNIROUTE_VNC_CHROMIUM_ARGS=--remote-debugging-port=9222 --no-first-run --no-default-browser-check
-# OMNIROUTE_VNC_NETWORK=omniroute-vnc-browser-login

 # ─────────────────────────────────────────────────────────────────────────────
 # Data-dir alias (optional — open-sse/services/notionThreadSessions.ts)
@@ -3328,11 +3070,6 @@ QUOTA_STORE_DRIVER=sqlite
 # Telegram Mini App bridge. The update endpoint remains disabled while the bot
 # token is unset. Used by: src/lib/telegram/* and src/app/api/telegram/update/route.ts.
 # TELEGRAM_BOT_TOKEN=
-# Shared secret registered with setWebhook and echoed back by Telegram as the
-# X-Telegram-Bot-Api-Secret-Token header. REQUIRED for the webhook path: without
-# it the webhook is rejected with 503, because an unauthenticated update lets any
-# caller mint API keys and spend upstream quota. The Mini App path does not use it.
-# TELEGRAM_WEBHOOK_SECRET=
 # TELEGRAM_DEFAULT_MODEL=auto/chat
 # TELEGRAM_BOT_API_BASE=https://api.telegram.org
 # TELEGRAM_WEBHOOK_TIMEOUT_MS=60000
--- a/.env.selfhost.example
+++ b/.env.selfhost.example
@@ -1,41 +0,0 @@
-# ──────────────────────────────────────────────────────────────────────
-#  OmniRoute — Self-Host env (minimal, zero-fee self-host)
-# ──────────────────────────────────────────────────────────────────────
-#  cp .env.selfhost.example .env
-#  Edit only the two lines marked `# EDIT ME`. Everything else has a sane
-#  default. No secrets are baked in — OmniRoute never ships credentials.
-#
-#  Full variable reference: docs/guides/DOCKER_GUIDE.md and .env.example
-# ──────────────────────────────────────────────────────────────────────
-
-# ── Ports (host-side) ──────────────────────────────────────────────────
-# Dashboard + API + Live-WS. Already match the image defaults.
-DASHBOARD_PORT=20128
-API_PORT=20129
-LIVE_WS_PORT=20132
-
-# ── Bind address ───────────────────────────────────────────────────────
-# 127.0.0.1 = loopback only (safe with REQUIRE_API_KEY=false, the default).
-# Set to 0.0.0.0 ONLY when REQUIRE_API_KEY=true OR a reverse proxy
-# enforces auth upstream. Exposing an unauthenticated /v1 proxy on the
-# LAN/WAN lets anyone burn your provider quotas. # EDIT ME if you must.
-APP_BIND_HOST=127.0.0.1
-
-# ── Auth ──────────────────────────────────────────────────────────────
-# false = the dashboard and /v1 proxy are open to APP_BIND_HOST's network.
-# true  = every request needs an API key / dashboard login. The dashboard
-#         auto-creates INITIAL_PASSWORD on first boot (read it from the logs:
-#         `docker logs omniroute | grep -i password`). # EDIT ME — set true.
-REQUIRE_API_KEY=false
-# INITIAL_PASSWORD=                  # uncomment to pre-seed the dashboard password
-
-# ── Memory ceiling (V8 old-space) ──────────────────────────────────────
-# 1024 = dashboard + light chat. Coding agents (long POST /v1/responses
-# bodies) need more — see SELF_HOST_GUIDE.md "sizing". 2048 is a safe
-# default for a single user who runs Claude Code / Codex through it.
-OMNIROUTE_MEMORY_MB=2048
-
-# ── Browser-facing origin (optional) ───────────────────────────────────
-# Set ONLY if you expose OmniRoute behind a domain via a reverse proxy.
-# NEXT_PUBLIC_BASE_URL=https://your-domain.example.com
-# BASE_URL=http://omniroute:20128
--- a/.github/ISSUE_TEMPLATE/bug_report.yml
+++ b/.github/ISSUE_TEMPLATE/bug_report.yml
@@ -1,6 +1,6 @@
 name: Bug Report
 description: Report a bug or unexpected behavior in OmniRoute
-title: "fix(): "
+title: "[BUG] "
 labels: ["bug"]
 body:
  - type: markdown
@@ -8,8 +8,6 @@ body:
      value: |
        Thanks for taking the time to report a bug. Please fill out the sections below so we can reproduce and fix the issue.

-        The title is prefilled as `fix(): ` to match the [Conventional Commits](https://github.com/diegosouzapw/OmniRoute/blob/main/CONTRIBUTING.md#commit-messages) convention — pick a scope from the list documented there (e.g. `providers`, `resilience`, `dashboard`, `api`).
-
  - type: input
    id: version
    attributes:
--- a/.github/ISSUE_TEMPLATE/feature_request.yml
+++ b/.github/ISSUE_TEMPLATE/feature_request.yml
@@ -1,6 +1,6 @@
 name: Feature Request
 description: Suggest a new feature or improvement for OmniRoute
-title: "feat(): "
+title: "[Feature] "
 labels: ["enhancement"]
 body:
  - type: markdown
@@ -8,8 +8,6 @@ body:
      value: |
        Thanks for suggesting a feature! Please describe the problem you're trying to solve and how you'd like it to work.

-        The title is prefilled as `feat(): ` to match the [Conventional Commits](https://github.com/diegosouzapw/OmniRoute/blob/main/CONTRIBUTING.md#commit-messages) convention — pick a scope from the list documented there (e.g. `providers`, `resilience`, `dashboard`, `api`).
-
  - type: textarea
    id: problem
    attributes:
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -142,14 +142,7 @@ jobs:
      - run: npm run check:known-symbols
      - run: npm run check:route-guard-membership
      - run: npm run check:test-discovery
-      - run: npm run check:radar-sentinels
      - run: npm run check:tracked-artifacts
-      # A test parked in vitest.config.ts's exclude list does not run, and looks like
-      # coverage to whoever reads the tree. 62 files accumulated behind a comment pointing
-      # at #8618 — closed in August while the list grew to 62; 51 of them passed when
-      # finally measured (#13204). This gate requires every exclusion to name a tracker and
-      # to appear in config/quality/vitest-exclusions.json, so the debt stays reviewable.
-      - run: npm run check:vitest-exclusions
      # (gap 30) Also lives in quality.yml's PR-only "Merge integrity" job — because the
      # CHANGELOG half of that job needs a base to diff against. This half does NOT: the
      # generator either reproduces the committed SKILL.md files or it does not.
@@ -453,11 +446,8 @@ jobs:
      # One FS inventory of src/app/api for both anti-hallucination directions.
      - name: API docs refs (openapi + prose → routes)
        run: npm run check:api-docs-refs
-      # Blocking since the 2026-09 docs re-sync: a core doc edited without `npm run i18n:run
-      # --files=<doc>` (or `--adopt` for a mechanical edit) leaves 65 stale mirrors behind;
-      # the run only retranslates the `## ` sections whose text changed, so it is cheap.
-      - name: i18n docs drift (sources changed since their translation)
-        run: node scripts/i18n/check-translation-drift.mjs
+      - name: i18n translation drift (warn)
+        run: node scripts/i18n/check-translation-drift.mjs --warn

  docs-lint:
    name: Docs Lint (prose — advisory)
@@ -514,11 +504,9 @@ jobs:
      - run: node scripts/i18n/check-ui-keys-coverage.mjs --threshold=65
      # Real-translation ratchet: a leaf copied verbatim from en.json passes key
      # parity above but is still English to the user (es shipped 55% English).
-      # Blocking since PR-4 retranslated the verbatim-English backlog: the share of
-      # untranslated leaves per locale may only fall (ratchet baseline in
-      # config/quality/i18n-translation-baseline.json; `npm run i18n:check-ratio:update`).
-      - name: i18n real-translation ratio
-        run: node scripts/i18n/check-translation-ratio.mjs
+      # Advisory in PR-0; flipped to blocking once the backlog is retranslated (PR-4).
+      - name: i18n real-translation ratio (advisory)
+        run: node scripts/i18n/check-translation-ratio.mjs --warn
      # #8463: a rewritten English value used to leave its 39 translations behind
      # silently (googleOAuthWarning shipped wrong copy in 39 locales for months).
      # Key parity above cannot see it — a stale translation counts as covered.
@@ -526,30 +514,6 @@ jobs:
        env:
          BASE_REF: ${{ github.base_ref && format('origin/{0}', github.base_ref) || '' }}
        run: node scripts/i18n/check-ui-value-drift.mjs
-      # Sibling of the drift gate above. That one catches an English value that was
-      # REWRITTEN; this one catches an English key that was ADDED while some locales never
-      # got it. The coverage gate at the top of this job cannot: it is a percentage per
-      # locale, and 11 absent keys out of ~13,000 leaves coverage at 99.9%. Incident: the
-      # Phase 3 canvas keys were translated across the 42 locales that existed, then the EU
-      # batch (#13044) took the repo to 51 and the nine newcomers shipped untranslated.
-      - name: i18n new-key coverage (a new key must reach every locale)
-        env:
-          BASE_REF: ${{ github.base_ref && format('origin/{0}', github.base_ref) || '' }}
-        run: node scripts/i18n/check-new-key-coverage.mjs
-      # Absolute complement of the two gates above: every locale must carry exactly the key
-      # set of en.json, whatever the age of the key. A locale batch is generated from the
-      # en.json of the day the branch is cut and translates for days while the base keeps
-      # adding keys — the batch PR adds no key itself, so the new-key gate stays silent and
-      # 43 absent keys out of ~13,000 still read 99.7 % coverage. Incident 2026-09-15:
-      # batch 1 (#13044) landed 43 keys short in nine locales, batch 2 (#13660) 10 keys short
-      # in eight. Fix is `sync-ui-keys --locale=<codes> --translate-markers`.
-      - name: i18n key completeness (every locale carries every en.json key)
-        run: node scripts/i18n/check-key-completeness.mjs
-      # Same gate for the CLI catalogs (bin/cli/locales). check:cli-i18n only compares
-      # pt-BR / zh-CN / zh-TW; 38 locales shipped with 1–24 of 830 keys for months
-      # (audit 2026-09-16) and the CLI silently fell back to English for them.
-      - name: i18n key completeness (CLI catalogs)
-        run: node scripts/i18n/check-key-completeness.mjs --catalog=cli

  # #8038: cheap glossary/protected-terms consistency gate —
  # complements i18n-ui-coverage (key parity) and the ICU `i18n` job below
--- a/.github/workflows/docker-publish.yml
+++ b/.github/workflows/docker-publish.yml
@@ -411,12 +411,16 @@ jobs:
          path: /tmp/digests/bun-web
          merge-multiple: true

-      - name: Create Docker Hub version manifests
+      - name: Create Docker Hub manifest
        run: |
          set -euo pipefail

          create_manifest() {
            local image="$1" suffix="$2" dir="$3" optional="${4:-}"
+            local tags=(-t "${image}:${VERSION}${suffix}")
+            if [ "$PROMOTE_LATEST" = "true" ]; then
+              tags+=(-t "${image}:latest${suffix}")
+            fi
            local refs=()
            while IFS= read -r digest_file; do
              refs+=("${image}@sha256:$(basename "$digest_file")")
@@ -429,7 +433,7 @@ jobs:
              echo "No image digests in $dir" >&2
              exit 1
            fi
-            docker buildx imagetools create -t "${image}:${VERSION}${suffix}" "${refs[@]}"
+            docker buildx imagetools create "${tags[@]}" "${refs[@]}"
          }

          create_manifest "${IMAGE_NAME}" "" /tmp/digests/base
@@ -437,12 +441,16 @@ jobs:
          create_manifest "${IMAGE_NAME}" "-bun" /tmp/digests/bun-base optional
          create_manifest "${IMAGE_NAME}" "-web-bun" /tmp/digests/bun-web optional

-      - name: Create GHCR version manifests
+      - name: Create GHCR manifest
        run: |
          set -euo pipefail

          create_manifest() {
            local image="$1" suffix="$2" dir="$3" optional="${4:-}"
+            local tags=(-t "${image}:${VERSION}${suffix}")
+            if [ "$PROMOTE_LATEST" = "true" ]; then
+              tags+=(-t "${image}:latest${suffix}")
+            fi
            local refs=()
            while IFS= read -r digest_file; do
              refs+=("${image}@sha256:$(basename "$digest_file")")
@@ -455,7 +463,7 @@ jobs:
              echo "No image digests in $dir" >&2
              exit 1
            fi
-            docker buildx imagetools create -t "${image}:${VERSION}${suffix}" "${refs[@]}"
+            docker buildx imagetools create "${tags[@]}" "${refs[@]}"
          }

          create_manifest "${GHCR_IMAGE_NAME}" "" /tmp/digests/base
@@ -463,59 +471,6 @@ jobs:
          create_manifest "${GHCR_IMAGE_NAME}" "-bun" /tmp/digests/bun-base optional
          create_manifest "${GHCR_IMAGE_NAME}" "-web-bun" /tmp/digests/bun-web optional

-      - name: Smoke-test published Docker image
-        if: needs.prepare.outputs.version != 'main'
-        run: |
-          set -euo pipefail
-          container="omniroute-smoke-${VERSION//[^a-zA-Z0-9_.-]/-}"
-          trap 'docker rm -f "$container" >/dev/null 2>&1 || true' EXIT
-          docker run --detach --name "$container" "${IMAGE_NAME}:${VERSION}"
-          for attempt in $(seq 1 30); do
-            status="$(docker inspect --format '{{.State.Health.Status}}' "$container")"
-            if [ "$status" = "healthy" ]; then
-              exit 0
-            fi
-            if [ "$status" = "unhealthy" ] || [ "$(docker inspect --format '{{.State.Status}}' "$container")" = "exited" ]; then
-              docker logs "$container"
-              exit 1
-            fi
-            sleep 2
-          done
-          docker logs "$container"
-          exit 1
-
-      - name: Promote Docker Hub latest tags
-        if: needs.prepare.outputs.promote_latest == 'true'
-        run: |
-          set -euo pipefail
-          promote_tag() {
-            local suffix="$1"
-            docker buildx imagetools create -t "${IMAGE_NAME}:latest${suffix}" "${IMAGE_NAME}:${VERSION}${suffix}"
-          }
-          promote_tag ""
-          promote_tag "-web"
-          for suffix in -bun -web-bun; do
-            if docker buildx imagetools inspect "${IMAGE_NAME}:${VERSION}${suffix}" >/dev/null 2>&1; then
-              promote_tag "$suffix"
-            fi
-          done
-
-      - name: Promote GHCR latest tags
-        if: needs.prepare.outputs.promote_latest == 'true'
-        run: |
-          set -euo pipefail
-          promote_tag() {
-            local suffix="$1"
-            docker buildx imagetools create -t "${GHCR_IMAGE_NAME}:latest${suffix}" "${GHCR_IMAGE_NAME}:${VERSION}${suffix}"
-          }
-          promote_tag ""
-          promote_tag "-web"
-          for suffix in -bun -web-bun; do
-            if docker buildx imagetools inspect "${GHCR_IMAGE_NAME}:${VERSION}${suffix}" >/dev/null 2>&1; then
-              promote_tag "$suffix"
-            fi
-          done
-
      - name: Inspect image
        if: needs.prepare.outputs.version != 'main'
        run: |
--- a/.github/workflows/radar-export.yml
+++ b/.github/workflows/radar-export.yml
@@ -10,11 +10,7 @@ name: Radar Export
 on:
  workflow_dispatch: # o operador pode publicar sob demanda (de qualquer ref)
  push:
-    # `main` e a release ativa (default branch) publicam no mesmo asset estável: o
-    # radar-server só consome o asset, então um merge de catálogo na release que ficasse
-    # à espera do cron semanal deixava o feed até 7 dias atrás do README (2026-09-14: a
-    # linha da Together removida em d6e62ae só saiu do feed com dispatch manual).
-    branches: [main, "release/**"]
+    branches: [main] # produção: só o catálogo do main clobra o asset estável
    paths:
      - open-sse/config/freeModelCatalog.data.ts
      - open-sse/config/freeModelCatalog.ts
@@ -23,9 +19,7 @@ on:
      - scripts/release/radar-export.mjs
      - .github/workflows/radar-export.yml
  schedule:
-    # Diário 03:17 UTC — antes do `radar-feed.timer` do servidor (04:23 UTC), para o ciclo
-    # do dia já enxergar o export do dia; também mantém geradoEm/proveniência frescos.
-    - cron: "17 3 * * *"
+    - cron: "17 6 * * 1" # semanal (segunda 06:17 UTC): mantém geradoEm/proveniência frescos

 permissions:
  contents: read
--- a/.github/workflows/release-acceptance.yml
+++ b/.github/workflows/release-acceptance.yml
@@ -1,42 +0,0 @@
-name: Release acceptance
-
-on:
-  push:
-    branches: ["release/v*"]
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-concurrency:
-  group: release-acceptance-${{ github.ref }}
-  cancel-in-progress: false
-
-jobs:
-  acceptance:
-    name: Release acceptance
-    if: github.event_name != 'pull_request'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v5
-        with:
-          node-version: "22"
-          cache: npm
-      - run: npm ci
-      - name: Emit shadow acceptance report
-        run: |
-          node scripts/quality/validate-release-acceptance.mjs \
-            --plan tests/fixtures/release-acceptance/plan-lint.json \
-            --manifests tests/fixtures/release-acceptance/shadow-manifests \
-            --out release-acceptance-report.json
-        continue-on-error: true
-      - uses: actions/upload-artifact@v4
-        if: always()
-        with:
-          name: release-acceptance-report
-          path: release-acceptance-report.json
-          if-no-files-found: ignore
-          retention-days: 30
--- a/.gitignore
+++ b/.gitignore
@@ -74,7 +74,6 @@ yarn-error.log*
 # Local gitleaks artifacts (do not commit)
 gitleaks-local.json
 !.env.example
-!.env.selfhost.example
 !.env.homolog.example
 !.env.devin-bridge.example
 # Provider API keys (never commit)
@@ -219,7 +218,6 @@ scripts/i18n/_pending-keys.json

 # PR Reviews and local feedback files
 pr_reviews*.json
-/review/

 #hidden local data directories (never commit)
 .local-data/
--- a/.gitleaks.toml
+++ b/.gitleaks.toml
@@ -97,11 +97,4 @@
      # credential; the generic-api-key rule flags the long hyphenated string.
      '''omniroute-cheaperinference-sponsor-banner-dismissed-v\d+''',
      '''SunbreakWebUI1''',
-      # Uzbek dashboard catalog (#13727, src/i18n/messages/uz.json `outputTokenDesc`):
-      # "Yakunlash/javob tokenlari" = "completion/response tokens". The rule reads the
-      # `...TokenDesc` key as a token assignment and the translated words as its value.
-      '''Yakunlash/javob''',
-      # Feature-flag id from #13439 (src/shared/constants/featureFlagDefinitions.ts):
-      # `key: "PROTECTED_PRIORITY_INFRA_502_ENABLED"` is a flag name, not a credential.
-      '''PROTECTED_PRIORITY_INFRA_502_ENABLED''',
    ]
--- a/.i18n-state.json
+++ b/.i18n-state.json
--- a/.prettierignore
+++ b/.prettierignore
@@ -1,7 +1,3 @@
-# wasm-bindgen glue + embedded WASM_BASE64. Prettier rewrites the generated JS
-# (quotes, wrapping) on any touch of this file; format tinycmsDomMocks.ts instead.
-open-sse/executors/tinycmsSigner.ts
-
 # Long reference tables are manually aligned; formatting the whole file causes noisy diffs.
 docs/reference/ENVIRONMENT.md

--- a/@omniroute/opencode-plugin-v2/README.md
+++ b/@omniroute/opencode-plugin-v2/README.md
@@ -56,14 +56,8 @@ explicitly:
 }
 ```

-The token can also come from the `OMNIROUTE_MANAGEMENT_API_KEY` environment
-variable (the option wins when both are set). Resolution order:
-`managementReadToken` option, then `OMNIROUTE_MANAGEMENT_API_KEY`, then the
-`apiKey` fallback.
-
 Left unset, `managementReadToken` falls back to `apiKey` for backwards
-compatibility, and the plugin warns once at startup that the fallback is
-active. When a gateway rejects that fallback, the catalog still
+compatibility. When a gateway rejects that fallback, the catalog still
 publishes — but with raw model ids instead of display names, no canonical
 alias dedupe, no pricing and no combos. The plugin warns once per endpoint
 when this happens, naming the endpoint and the consequence, so the degraded
@@ -71,25 +65,25 @@ catalog is never a mystery.

 ## Options

-| Key                              | Default                                                    | Notes                                                                                                                 |
-| -------------------------------- | ---------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- |
-| `providerId`                     | `"omniroute"`                                              | Provider id and integration id; models publish under `<providerId>/…`                                                 |
-| `baseURL`                        | required                                                   | OmniRoute gateway root (no `/v1` suffix needed)                                                                       |
-| `apiKey`                         | connected credential, then `OMNIROUTE_API_KEY`             | Chat key for `/v1/*` — see [Credentials](#credentials)                                                                |
-| `managementReadToken`            | option, then `OMNIROUTE_MANAGEMENT_API_KEY`, then `apiKey` | Management key for `/api/*` (combos, providers, enrichment) — usually **not** the same key                            |
-| `displayName`                    | `"OmniRoute"`                                              | Provider display name                                                                                                 |
-| `timeoutMs`                      | `10000`                                                    | Per-endpoint fetch timeout (auto-combos use 5s)                                                                       |
-| `modelCacheTtlMs`                | `300000`                                                   | Catalog cache TTL; disk snapshot warms cold starts                                                                    |
-| `timeouts`                       | per-endpoint override                                      | `{ models, combos, autoCombos, enrichment }` in ms; falls back to `timeoutMs`                                         |
-| `enrichment`                     | `true`                                                     | Fetch names + pricing (`/api/pricing*`, `/api/free-tier/summary`)                                                     |
-| `providerTag`                    | `true`                                                     | Prefix a display name with the upstream provider it routes to                                                         |
-| `geminiSanitization`             | `true`                                                     | Strip `$schema`/`additionalProperties` from tool schemas sent to Gemini models (`$ref` tools are forwarded untouched) |
-| `usableOnly`                     | `false`                                                    | Filter to healthy provisioned providers (`/api/providers`)                                                            |
-| `visibleModels` / `hiddenModels` | `[]`                                                       | Exact-or-suffix allowlists, deny wins                                                                                 |
-| `apiFormat.allowAnthropic`       | `false`                                                    | Route allowlisted ids to the Anthropic API block                                                                      |
-| `apiFormat.anthropicModels`      | `[]`                                                       | Full model ids routed to Anthropic                                                                                    |
-| `apiFormat.anthropicPrefixes`    | v1 defaults                                                | Deprecated, warns once — prefer `anthropicModels`                                                                     |
-| `logLevel` / `startupDebug`      | `warn` / `false`                                           | Logger verbosity                                                                                                      |
+| Key                              | Default                                        | Notes                                                                                                                 |
+| -------------------------------- | ---------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- |
+| `providerId`                     | `"omniroute"`                                  | Provider id and integration id; models publish under `<providerId>/…`                                                 |
+| `baseURL`                        | required                                       | OmniRoute gateway root (no `/v1` suffix needed)                                                                       |
+| `apiKey`                         | connected credential, then `OMNIROUTE_API_KEY` | Chat key for `/v1/*` — see [Credentials](#credentials)                                                                |
+| `managementReadToken`            | falls back to `apiKey`                         | Management key for `/api/*` (combos, providers, enrichment) — usually **not** the same key                            |
+| `displayName`                    | `"OmniRoute"`                                  | Provider display name                                                                                                 |
+| `timeoutMs`                      | `10000`                                        | Per-endpoint fetch timeout (auto-combos use 5s)                                                                       |
+| `modelCacheTtlMs`                | `300000`                                       | Catalog cache TTL; disk snapshot warms cold starts                                                                    |
+| `timeouts`                       | per-endpoint override                          | `{ models, combos, autoCombos, enrichment }` in ms; falls back to `timeoutMs`                                         |
+| `enrichment`                     | `true`                                         | Fetch names + pricing (`/api/pricing*`, `/api/free-tier/summary`)                                                     |
+| `providerTag`                    | `true`                                         | Prefix a display name with the upstream provider it routes to                                                         |
+| `geminiSanitization`             | `true`                                         | Strip `$schema`/`additionalProperties` from tool schemas sent to Gemini models (`$ref` tools are forwarded untouched) |
+| `usableOnly`                     | `false`                                        | Filter to healthy provisioned providers (`/api/providers`)                                                            |
+| `visibleModels` / `hiddenModels` | `[]`                                           | Exact-or-suffix allowlists, deny wins                                                                                 |
+| `apiFormat.allowAnthropic`       | `false`                                        | Route allowlisted ids to the Anthropic API block                                                                      |
+| `apiFormat.anthropicModels`      | `[]`                                           | Full model ids routed to Anthropic                                                                                    |
+| `apiFormat.anthropicPrefixes`    | v1 defaults                                    | Deprecated, warns once — prefer `anthropicModels`                                                                     |
+| `logLevel` / `startupDebug`      | `warn` / `false`                               | Logger verbosity                                                                                                      |

 ## Tool calling on Gemini models

--- a/@omniroute/opencode-plugin-v2/src/cache.ts
+++ b/@omniroute/opencode-plugin-v2/src/cache.ts
@@ -1,6 +1,6 @@
 import { createHash } from "node:crypto";
 import { homedir } from "node:os";
-import { mkdir, readFile, rename, unlink, writeFile } from "node:fs/promises";
+import { mkdir, readFile, unlink, writeFile } from "node:fs/promises";
 import { dirname, join } from "node:path";
 import type {
  OmniRouteEnrichmentEntry,
@@ -10,7 +10,6 @@ import type {
  OmniRouteRawCombo,
  OmniRouteRawModelEntry,
 } from "./shared/index.js";
-import { isHttpUrl } from "./shared/index.js";

 export const DEFAULT_MODEL_CACHE_TTL_MS = 300_000 as const;

@@ -35,9 +34,8 @@ export const SNAPSHOT_FORMAT_VERSION = 2 as const;

 /**
 * A raw snapshot entry is stale when it cannot be mapped to a publishable
- * model: no string `id` (unroutable), or a pre-mapped `api` block missing a
- * valid `npm` package (the runner would reject it as `Unsupported package`)
- * or a usable `url` (the host would reach the AI SDK with no baseURL).
+ * model: no string `id` (unroutable) or a pre-mapped `api` block without a
+ * valid `npm` package (the runner would reject it as `Unsupported package`).
 * Plain `/v1/models` entries carry no `api` block -- it is synthesized at
 * publish time -- so only a present-but-invalid block drops the entry.
 */
@@ -49,11 +47,7 @@ export function isStaleSnapshotModel(entry: unknown): boolean {
  if (api === undefined) return false;
  if (!api || typeof api !== "object") return true;
  const npm = (api as { npm?: unknown }).npm;
-  if (typeof npm !== "string" || npm.length === 0) return true;
-  // Same requirement as `npm`, and the same predicate the options schema
-  // applies to `baseURL`: a pre-mapped block without a callable `url` publishes
-  // a model the host cannot route -- see `legacyApiToInfoApi`.
-  return !isHttpUrl((api as { url?: unknown }).url);
+  return typeof npm !== "string" || npm.length === 0;
 }

 interface DiskSnapshotV2 {
@@ -81,12 +75,6 @@ interface DiskSnapshotV2 {
 */
 const MAX_SNAPSHOT_BYTES = 32 * 1024 * 1024;

-// Suffix for the temp file each write publishes via rename. Monotone per
-// process: two writes for one provider (for example across a credential
-// rotation) must not share a temp name. Built after the empty-models and
-// size-cap guards, so only real attempts consume a value.
-let snapshotWriteCounter = 0;
-
 function trimTrailingSlashes(value: string): string {
  let i = value.length;
  while (i > 0 && value.charCodeAt(i - 1) === 0x2f) i -= 1;
@@ -139,7 +127,7 @@ export async function readDiskSnapshot(
    if (
      !parsed ||
      typeof parsed.v !== "number" ||
-      parsed.v !== SNAPSHOT_FORMAT_VERSION ||
+      parsed.v < SNAPSHOT_FORMAT_VERSION ||
      typeof parsed.identityFingerprint !== "string" ||
      parsed.identityFingerprint !== identityFingerprint
    ) {
@@ -157,7 +145,7 @@ export async function readDiskSnapshot(
      (entry) => !isStaleSnapshotModel(entry)
    );
    if (stale > 0) {
-      logger?.warn(`[omniroute-v2] dropping ${stale} stale snapshot entries with an unusable api block`);
+      logger?.warn(`[omniroute-v2] dropping ${stale} stale snapshot entries without api block`);
    }
    if (models.length === 0) return undefined;
    return {
@@ -185,14 +173,8 @@ export async function readDiskSnapshot(
 export async function writeDiskSnapshot(
  providerId: string,
  snapshot: CatalogSnapshot,
-  identityFingerprint: string,
-  logger?: { warn: (message: string) => void }
+  identityFingerprint: string
 ): Promise<void> {
-  // Monotone per-process suffix: two writes for one provider (for example
-  // across a credential rotation) must not share a temp name. Declared here
-  // so the catch below can clean it up; assigned after the guards so only
-  // real attempts consume a counter value.
-  let tmp = "";
  try {
    if (snapshot.models.length === 0) return;
    const file = diskSnapshotPath(providerId);
@@ -208,33 +190,14 @@ export async function writeDiskSnapshot(
      writtenAt: Date.now(),
    };
    let payload = JSON.stringify(envelope);
-    if (
-      Buffer.byteLength(payload, "utf8") > MAX_SNAPSHOT_BYTES &&
-      envelope.enrichment !== undefined
-    ) {
+    if (payload.length > MAX_SNAPSHOT_BYTES && envelope.enrichment !== undefined) {
      delete envelope.enrichment;
      payload = JSON.stringify(envelope);
    }
-    if (Buffer.byteLength(payload, "utf8") > MAX_SNAPSHOT_BYTES) {
-      logger?.warn(
-        `[omniroute-v2] snapshot for ${providerId} exceeds the size cap, skipping disk write`
-      );
-      return;
-    }
-    tmp = `${file}.${process.pid}.${snapshotWriteCounter++}`;
-    await writeFile(tmp, payload, { encoding: "utf8", mode: 0o600 });
-    await rename(tmp, file);
-  } catch (err) {
+    if (payload.length > MAX_SNAPSHOT_BYTES) return;
+    await writeFile(file, payload, { encoding: "utf8", mode: 0o600 });
+  } catch {
    // Best-effort: callers already hold the in-memory entry.
-    logger?.warn(
-      `[omniroute-v2] snapshot write failed for ${providerId}: ` +
-        `${err instanceof Error ? err.message : String(err)}, keeping the in-memory entry`
-    );
-    try {
-      await unlink(tmp);
-    } catch {
-      // Ignore: the temp file may not exist (mkdir failed first).
-    }
  }
 }

--- a/@omniroute/opencode-plugin-v2/src/catalog.ts
+++ b/@omniroute/opencode-plugin-v2/src/catalog.ts
@@ -3,7 +3,6 @@ import { type HostContract, detectHostContract, emitsLegacyFields } from "./comp
 import type { Model as LegacyModelV2 } from "@opencode-ai/sdk/v2";
 import type { ModelV2Info, ProviderV2Info } from "@opencode-ai/sdk/v2/types";
 import {
-  isHttpUrl,
  type ApiFormatV2,
  type LogLevel,
  type Logger,
@@ -143,15 +142,6 @@ export function legacyApiToInfoApi(api: LegacyModelV2["api"]): ModelV2Info["api"
      "[omniroute-v2] refusing to publish a model without an api block (missing api.npm)"
    );
  }
-  // The host reads `api.url` in `prepareOptions` and never falls back to the
-  // provider's own, so a model published without one reaches the AI SDK with no
-  // baseURL and fails at call time with a bare `Invalid URL` — no request on the
-  // wire, nothing in the gateway logs, no model named.
-  if (!isHttpUrl(api.url)) {
-    throw new Error(
-      "[omniroute-v2] refusing to publish a model whose api block carries no http(s) url"
-    );
-  }
  return { id: api.id, type: "aisdk", package: api.npm, url: api.url };
 }

--- a/@omniroute/opencode-plugin-v2/src/index.ts
+++ b/@omniroute/opencode-plugin-v2/src/index.ts
@@ -31,14 +31,7 @@ import { assertContext } from "./compat.js";
 import { type ApiKeyOrigin, resolveApiKey, warnIfMissing } from "./credentials.js";
 import { createSourceErrorReporter } from "./enrichment-report.js";
 import { sanitizeToolSchemasFor } from "./gemini-language.js";
-import {
-  MANAGEMENT_TOKEN_ENV_VAR,
-  PLUGIN_ID,
-  parsePluginOptions,
-  resolveManagementReadToken,
-  resolveTimeouts,
-  type PluginOptions,
-} from "./options.js";
+import { PLUGIN_ID, parsePluginOptions, resolveTimeouts, type PluginOptions } from "./options.js";

 /**
 * A fetch result that says whether it succeeded. Returning a bare `[]` on
@@ -68,7 +61,7 @@ function toResolvedOptions(parsed: PluginOptions): ResolvedOptions {
    providerId: parsed.providerId,
    baseURL: parsed.baseURL,
    apiKey: parsed.apiKey ?? process.env.OMNIROUTE_API_KEY ?? "",
-    managementReadToken: resolveManagementReadToken(parsed.managementReadToken),
+    managementReadToken: parsed.managementReadToken,
    timeoutMs: parsed.timeoutMs,
    timeouts: parsed.timeouts,
    logLevel: parsed.logLevel,
@@ -100,16 +93,6 @@ export default define({
    resolved.logLevel = parsed.logLevel;
    resolved.startupDebug = parsed.startupDebug;
    log.info(`[omniroute-v2] init providerId=${X}`);
-    // The inference key stands in below when no management token is set, and
-    // gateways usually reject that stand-in with 401/403. Say so once here,
-    // before any fetch, instead of letting the refusal surface per endpoint.
-    if (resolved.managementReadToken === undefined) {
-      log.warn(
-        `[omniroute-v2] no management token configured: management endpoints (/api/*) will reuse the inference key, ` +
-          `which gateways usually reject with 401/403. Set "managementReadToken" in the plugin options ` +
-          `or export ${MANAGEMENT_TOKEN_ENV_VAR}.`
-      );
-    }

    // v1 parity port: in-memory TTL + disk snapshot. The memory key
    // `baseURL::sha256(creds)` isolates credential tuples (prod vs
@@ -314,7 +297,7 @@ export default define({
      };
      if (models.length > 0) {
        state.entries.set(cacheKey, snapshot);
-        await writeDiskSnapshot(X, snapshot, identityFingerprint, log);
+        await writeDiskSnapshot(X, snapshot, identityFingerprint);
      }
      void optional.then(
        (parts) => upgradeWithOptional(snapshot, parts),
@@ -361,7 +344,7 @@ export default define({
      if (unchanged) return;
      state.entries.set(cacheKey, upgraded);
      if (upgraded.models.length > 0) {
-        await writeDiskSnapshot(X, upgraded, identityFingerprint, log);
+        await writeDiskSnapshot(X, upgraded, identityFingerprint);
      }
      // Reload only when the optional tier actually moved: the catalog
      // fingerprint covers ids alone, so without this the host would rebuild
--- a/@omniroute/opencode-plugin-v2/src/options.ts
+++ b/@omniroute/opencode-plugin-v2/src/options.ts
@@ -1,7 +1,5 @@
 import { z } from "zod";

-import { isHttpUrl } from "./shared/models-map.js";
-
 const apiFormatSchema = z
  .object({
    allowAnthropic: z.boolean().optional(),
@@ -30,10 +28,7 @@ const pluginOptionsSchema = z
      .regex(/^[A-Za-z0-9._-]+$/, "providerId may only contain letters, digits, '.', '_' and '-'")
      .refine((v) => v !== "." && v !== "..", "providerId cannot be a path segment")
      .default("omniroute"),
-    baseURL: z
-      .string()
-      .trim()
-      .refine(isHttpUrl, "baseURL must be an http(s) URL, for example http://localhost:20128"),
+    baseURL: z.string().url(),
    apiKey: z.string().optional(),
    displayName: z.string().optional(),
    managementReadToken: z.string().optional(),
@@ -61,21 +56,6 @@ const pluginOptionsSchema = z

 export type PluginOptions = z.infer<typeof pluginOptionsSchema>;

-/** Environment source for the management token (option wins over this). */
-export const MANAGEMENT_TOKEN_ENV_VAR = "OMNIROUTE_MANAGEMENT_API_KEY";
-
-/**
- * Resolve the management token: a non-empty option wins, then a non-empty
- * environment value, else absent. Empty counts as absent on both inputs, the
- * same rule the inference key follows; no trimming, the token is opaque.
- */
-export function resolveManagementReadToken(optionValue: string | undefined): string | undefined {
-  if (optionValue !== undefined && optionValue.length > 0) return optionValue;
-  const fromEnv = process.env[MANAGEMENT_TOKEN_ENV_VAR];
-  if (fromEnv !== undefined && fromEnv.length > 0) return fromEnv;
-  return undefined;
-}
-
 /** Per-endpoint timeout defaults (v1 parity). `timeoutMs` is the global fallback. */
 export const DEFAULT_TIMEOUT_MS = 10_000 as const;
 /** Auto-combos keep the v1 5s budget; the field is resolved now for the P3 port. */
--- a/@omniroute/opencode-plugin-v2/src/shared/models-map.ts
+++ b/@omniroute/opencode-plugin-v2/src/shared/models-map.ts
@@ -111,22 +111,6 @@ function trimTrailingSlashes(value: string): string {
 * (it appends `/v1/messages` automatically), so callers should branch on
 * format first.
 */
-/**
- * A url the AI SDK can actually call. `new URL()` alone is not enough: it
- * parses `localhost:20128` as the scheme `localhost:` and `ftp://host` as ftp,
- * both of which reach `fetch` and fail there. Mirrors the `isHttpUrl` guard the
- * settings schema applies to `headroomUrl`.
- */
-export function isHttpUrl(value: unknown): boolean {
-  if (typeof value !== "string") return false;
-  try {
-    const { protocol } = new URL(value);
-    return protocol === "http:" || protocol === "https:";
-  } catch {
-    return false;
-  }
-}
-
 export function ensureV1Suffix(url: string): string {
  const trimmed = trimTrailingSlashes(url);
  return trimmed.endsWith("/v1") ? trimmed : `${trimmed}/v1`;
--- a/@omniroute/opencode-plugin-v2/tests/disk-snapshot-atomicity.test.ts
+++ b/@omniroute/opencode-plugin-v2/tests/disk-snapshot-atomicity.test.ts
@@ -1,251 +0,0 @@
-import { describe, it } from "node:test";
-import assert from "node:assert/strict";
-import {
-  existsSync,
-  mkdirSync,
-  mkdtempSync,
-  readdirSync,
-  readFileSync,
-  rmSync,
-  statSync,
-  writeFileSync,
-} from "node:fs";
-import { tmpdir } from "node:os";
-import { dirname, join } from "node:path";
-import {
-  diskSnapshotPath,
-  readDiskSnapshot,
-  writeDiskSnapshot,
-  type CatalogSnapshot,
-} from "../src/cache.js";
-
-function isolateDisk(): { dir: string; restore: () => void } {
-  const dir = mkdtempSync(join(tmpdir(), "omniroute-disk-atomic-"));
-  const prev = process.env.OPENCODE_DATA_DIR;
-  process.env.OPENCODE_DATA_DIR = dir;
-  return {
-    dir,
-    restore: () => {
-      if (prev === undefined) delete process.env.OPENCODE_DATA_DIR;
-      else process.env.OPENCODE_DATA_DIR = prev;
-    },
-  };
-}
-
-function makeSnapshot(models: string[] = ["m-a"]): CatalogSnapshot {
-  return {
-    models: models.map((id) => ({ id })),
-    combos: [],
-    autoCombos: [],
-    providers: [],
-    fetchedAt: Date.now(),
-  } as unknown as CatalogSnapshot;
-}
-
-function makeLogger() {
-  const messages: string[] = [];
-  return {
-    messages,
-    logger: { warn: (message: string) => void messages.push(message) },
-  };
-}
-
-// Entries next to the destination other than the destination itself: any
-// leftover temp file after a successful write shows up here.
-function strayEntries(file: string): string[] {
-  let entries: string[];
-  try {
-    entries = readdirSync(dirname(file));
-  } catch {
-    return [];
-  }
-  return entries.filter((entry) => entry !== file.split("/").pop());
-}
-
-// The writer names its temp file `${file}.${pid}.${counter}` with a
-// module-monotone counter starting at 0, built after the empty-models and
-// size-cap guards (an over-cap call consumes no counter value). Tests in this
-// file run sequentially in one process, so the attempt table below predicts
-// every temp path exactly:
-//   over-cap: no counter use | failed write A: 0, failed write B: 1 |
-//   interrupted overwrite A: 2, interrupted overwrite B: 3 | mkdir failure: 4 |
-//   truncated read: 5 | success: 6 | permissions: 7 | round-trip: 8, 9.
-function predictedTmp(file: string, counter: number): string {
-  return `${file}.${process.pid}.${counter}`;
-}
-
-describe("disk snapshot atomic write, strict version, traced give-ups", () => {
-  it("ignores a newer snapshot version without throwing", async () => {
-    const disk = isolateDisk();
-    try {
-      const file = diskSnapshotPath("t1-future");
-      mkdirSync(dirname(file), { recursive: true });
-      // A writer from the future persists version 3; this reader must
-      // treat it as "no snapshot" instead of trusting unknown data.
-      writeFileSync(
-        file,
-        JSON.stringify({
-          v: 3,
-          identityFingerprint: "fp-1",
-          models: [{ id: "m-future" }],
-          combos: [],
-          writtenAt: Date.now(),
-        })
-      );
-      const back = await readDiskSnapshot("t1-future", "fp-1");
-      assert.equal(back, undefined);
-    } finally {
-      disk.restore();
-      rmSync(disk.dir, { recursive: true, force: true });
-    }
-  });
-
-  it("traces an over-cap write and leaves no destination behind", async () => {
-    const disk = isolateDisk();
-    try {
-      const { messages, logger } = makeLogger();
-      const bigId = `huge-${"x".repeat(33 * 1024 * 1024)}`;
-      await writeDiskSnapshot("t2-cap", makeSnapshot([bigId]), "fp-1", logger);
-      const file = diskSnapshotPath("t2-cap");
-      assert.equal(existsSync(file), false);
-      assert.deepEqual(strayEntries(file), []);
-      assert.match(messages.join("\n"), /exceeds|too large|size cap/i);
-    } finally {
-      disk.restore();
-      rmSync(disk.dir, { recursive: true, force: true });
-    }
-  });
-
-  it("a failed write leaves no destination behind and is traced", async () => {
-    const disk = isolateDisk();
-    const file = diskSnapshotPath("t3a-fail");
-    const blocker = predictedTmp(file, 1);
-    try {
-      const { messages, logger } = makeLogger();
-      await writeDiskSnapshot("t3a-fail", makeSnapshot(["m-before"]), "fp-1", logger);
-      // Plant a directory at the next temp path: the write fails with
-      // EISDIR before any rename, deterministically, on every platform.
-      mkdirSync(dirname(file), { recursive: true });
-      mkdirSync(blocker, { recursive: true });
-      await writeDiskSnapshot("t3a-fail", makeSnapshot(["m-after"]), "fp-1", logger);
-      assert.equal(existsSync(file), true);
-      const back = await readDiskSnapshot("t3a-fail", "fp-1");
-      assert.deepEqual(
-        (back?.models ?? []).map((entry) => entry.id),
-        ["m-before"]
-      );
-      assert.match(messages.join("\n"), /failed|EISDIR|error/i);
-    } finally {
-      rmSync(blocker, { recursive: true, force: true });
-      disk.restore();
-      rmSync(disk.dir, { recursive: true, force: true });
-    }
-  });
-
-  it("an interrupted overwrite keeps the previous snapshot", async () => {
-    const disk = isolateDisk();
-    const file = diskSnapshotPath("t3b-keep");
-    const blocker = predictedTmp(file, 3);
-    try {
-      const { messages, logger } = makeLogger();
-      await writeDiskSnapshot("t3b-keep", makeSnapshot(["m-before"]), "fp-1", logger);
-      const before = readFileSync(file, "utf8");
-      mkdirSync(blocker, { recursive: true });
-      await writeDiskSnapshot("t3b-keep", makeSnapshot(["m-after"]), "fp-1", logger);
-      assert.equal(readFileSync(file, "utf8"), before);
-      const back = await readDiskSnapshot("t3b-keep", "fp-1");
-      assert.deepEqual(
-        (back?.models ?? []).map((entry) => entry.id),
-        ["m-before"]
-      );
-      assert.match(messages.join("\n"), /failed|EISDIR|error/i);
-    } finally {
-      rmSync(blocker, { recursive: true, force: true });
-      disk.restore();
-      rmSync(disk.dir, { recursive: true, force: true });
-    }
-  });
-
-  it("a mkdir failure is traced and writes nothing", async () => {
-    const disk = isolateDisk();
-    try {
-      const { messages, logger } = makeLogger();
-      // A file planted at the plugins path makes mkdir fail
-      // deterministically (EEXIST on mkdir, ENOTDIR on direct writeFile).
-      writeFileSync(join(disk.dir, "plugins"), "blocker");
-      await writeDiskSnapshot("t3b-bis", makeSnapshot(["m-a"]), "fp-1", logger);
-      assert.equal(existsSync(diskSnapshotPath("t3b-bis")), false);
-      assert.match(messages.join("\n"), /failed|EEXIST|ENOTDIR|error/i);
-    } finally {
-      disk.restore();
-      rmSync(disk.dir, { recursive: true, force: true });
-    }
-  });
-
-  it("a truncated file reads as no snapshot without throwing", async () => {
-    const disk = isolateDisk();
-    try {
-      const { logger } = makeLogger();
-      await writeDiskSnapshot("t4-truncated", makeSnapshot(["m-a"]), "fp-1", logger);
-      const file = diskSnapshotPath("t4-truncated");
-      const full = readFileSync(file, "utf8");
-      writeFileSync(file, full.slice(0, Math.floor(full.length / 2)));
-      const back = await readDiskSnapshot("t4-truncated", "fp-1");
-      assert.equal(back, undefined);
-    } finally {
-      disk.restore();
-      rmSync(disk.dir, { recursive: true, force: true });
-    }
-  });
-
-  it("a successful write leaves no entry but the destination", async () => {
-    const disk = isolateDisk();
-    try {
-      await writeDiskSnapshot("t5-clean", makeSnapshot(["m-a"]), "fp-1");
-      const file = diskSnapshotPath("t5-clean");
-      assert.deepEqual(strayEntries(file), []);
-    } finally {
-      disk.restore();
-      rmSync(disk.dir, { recursive: true, force: true });
-    }
-  });
-
-  it("the replaced snapshot stays owner-only", async (t) => {
-    if (process.platform === "win32") {
-      t.skip("file mode semantics are POSIX-only");
-      return;
-    }
-    const disk = isolateDisk();
-    try {
-      await writeDiskSnapshot("t6-mode", makeSnapshot(["m-a"]), "fp-1");
-      const file = diskSnapshotPath("t6-mode");
-      assert.equal((statSync(file).mode & 0o077) === 0, true);
-    } finally {
-      disk.restore();
-      rmSync(disk.dir, { recursive: true, force: true });
-    }
-  });
-
-  it("round-trips a valid snapshot with and without a logger", async () => {
-    const disk = isolateDisk();
-    try {
-      const { logger } = makeLogger();
-      const snapshot = makeSnapshot(["m-a"]);
-      await writeDiskSnapshot("t7-roundtrip", snapshot, "fp-1");
-      const plain = await readDiskSnapshot("t7-roundtrip", "fp-1");
-      assert.deepEqual(
-        (plain?.models ?? []).map((entry) => entry.id),
-        ["m-a"]
-      );
-      await writeDiskSnapshot("t7-roundtrip", snapshot, "fp-1", logger);
-      const logged = await readDiskSnapshot("t7-roundtrip", "fp-1", logger);
-      assert.deepEqual(
-        (logged?.models ?? []).map((entry) => entry.id),
-        ["m-a"]
-      );
-    } finally {
-      disk.restore();
-      rmSync(disk.dir, { recursive: true, force: true });
-    }
-  });
-});
--- a/@omniroute/opencode-plugin-v2/tests/index.test.ts
+++ b/@omniroute/opencode-plugin-v2/tests/index.test.ts
@@ -6,33 +6,6 @@ interface CapturedCall {
  kind: "catalog" | "integration";
 }

-/**
- * Wait until `read()` stops changing, then return the settled value.
- *
- * The plugin's optional tier lands asynchronously after a publish. Waiting for
- * it with a fixed `sleep(5)` raced the work: under load the tier arrived after
- * the sleep, so the *next* assertion counted its reload and read 2 where it
- * expected 1. Polling until the value holds steady for a few consecutive turns
- * ties the wait to the work instead of to the clock.
- */
-async function settle<T>(read: () => T, quietTurns = 3, timeoutMs = 5000): Promise<T> {
-  const { setTimeout: sleep } = await import("node:timers/promises");
-  const deadline = Date.now() + timeoutMs;
-  let last = read();
-  let stable = 0;
-  while (stable < quietTurns && Date.now() < deadline) {
-    await sleep(5);
-    const current = read();
-    if (current === last) {
-      stable += 1;
-    } else {
-      last = current;
-      stable = 0;
-    }
-  }
-  return last;
-}
-
 interface FakeCtx {
  options: Record<string, unknown>;
  catalog: {
@@ -190,6 +163,7 @@ describe("plugin-v2 entrypoint", () => {
    const { mkdtempSync } = await import("node:fs");
    const { tmpdir } = await import("node:os");
    const { join } = await import("node:path");
+    const { setTimeout: sleep } = await import("node:timers/promises");
    const dir = mkdtempSync(join(tmpdir(), "omniroute-lazy-"));
    const prevDataDir = process.env.OPENCODE_DATA_DIR;
    process.env.OPENCODE_DATA_DIR = dir;
@@ -248,15 +222,16 @@ describe("plugin-v2 entrypoint", () => {
      await cb(draft);
      assert.equal(reloads, 0, "the first publish sets the baseline, it does not reload");
      assert.equal(modelsCall, 1);
+      await sleep(5);
      // The optional tier lands after that first publish and brings combos and
      // the overlay with it — one reload, so the picker shows them without
      // waiting for the next refresh.
-      const afterFirstUpgrade = await settle(() => reloads);
+      const afterFirstUpgrade = reloads;
      assert.ok(afterFirstUpgrade <= 1, `at most one reload for the first upgrade, got ${reloads}`);
      await cb(draft);
      assert.equal(reloads, afterFirstUpgrade + 1, "a new model id reloads once");
      assert.equal(modelsCall, 2);
-      await settle(() => reloads);
+      await sleep(5);
      await cb(draft);
      assert.equal(reloads, afterFirstUpgrade + 1, "an identical run never reloads");
      assert.equal(modelsCall, 3);
--- a/@omniroute/opencode-plugin-v2/tests/management-token-env.test.ts
+++ b/@omniroute/opencode-plugin-v2/tests/management-token-env.test.ts
@@ -1,371 +0,0 @@
-import { describe, it } from "node:test";
-import assert from "node:assert/strict";
-import { mkdtempSync } from "node:fs";
-import { tmpdir } from "node:os";
-import { join } from "node:path";
-import plugin from "../src/index.js";
-import { publishCatalog } from "../src/catalog.js";
-import type { CatalogDraft } from "@opencode-ai/plugin/v2/promise";
-import type { ModelV2Info, ProviderV2Info } from "@opencode-ai/sdk/v2/types";
-
-const MODELS_URL = "https://gw.example.com/v1/models";
-const COMBOS_URL = "https://gw.example.com/api/combos";
-const PRICING_MODELS_URL = "https://gw.example.com/api/pricing/models";
-
-const MGMT_ENV_VAR = "OMNIROUTE_MANAGEMENT_API_KEY";
-const INFERENCE_ENV_VAR = "OMNIROUTE_API_KEY";
-
-function okJson(body: unknown) {
-  return { ok: true, status: 200, statusText: "OK", json: async () => body };
-}
-
-interface Harness {
-  seen: Map<string, string>;
-  warns: string[];
-  restore: () => void;
-}
-
-function installHarness(combos: unknown[]): Harness {
-  const seen = new Map<string, string>();
-  const warns: string[] = [];
-  const origFetch = globalThis.fetch;
-  const origWarn = console.warn;
-  const origLog = console.log;
-  const origError = console.error;
-  console.warn = (...args: unknown[]) => {
-    warns.push(String(args[0]));
-  };
-  console.log = () => {};
-  console.error = (...args: unknown[]) => {
-    warns.push(String(args[0]));
-  };
-  globalThis.fetch = (async (url: unknown, init?: { headers?: Record<string, string> }) => {
-    const href = String(url);
-    seen.set(href, String(init?.headers?.Authorization ?? ""));
-    if (href.includes("/api/combos/auto")) return okJson({ combos: [] });
-    if (href.includes("/api/pricing/models")) {
-      return okJson({
-        providers: {
-          demo: {
-            id: "demo",
-            name: "Demo",
-            models: [{ id: "team-combo", name: "Team Combo" }],
-          },
-        },
-      });
-    }
-    if (href.includes("/api/pricing")) return okJson({});
-    if (href.includes("/api/free-tier/summary")) return okJson({ perModel: [] });
-    if (href.includes("/api/combos")) return okJson({ combos });
-    return okJson({ data: [{ id: "m1" }] });
-  }) as typeof fetch;
-  return {
-    seen,
-    warns,
-    restore() {
-      globalThis.fetch = origFetch;
-      console.warn = origWarn;
-      console.log = origLog;
-      console.error = origError;
-    },
-  };
-}
-
-async function withIsolatedEnv<T>(
-  mgmt: string | undefined,
-  inference: string | undefined,
-  fn: () => Promise<T>
-): Promise<T> {
-  const prevMgmt = process.env[MGMT_ENV_VAR];
-  const prevInference = process.env[INFERENCE_ENV_VAR];
-  // Like tests/management-token.test.ts:176-180: a fresh OPENCODE_DATA_DIR
-  // per case keeps the real disk snapshot out of the run, so a filtered 'it'
-  // never gets a warm snapshot served without fetch.
-  const prevDataDir = process.env.OPENCODE_DATA_DIR;
-  process.env.OPENCODE_DATA_DIR = mkdtempSync(join(tmpdir(), "omniroute-mgmt-env-"));
-  if (mgmt === undefined) delete process.env[MGMT_ENV_VAR];
-  else process.env[MGMT_ENV_VAR] = mgmt;
-  if (inference === undefined) delete process.env[INFERENCE_ENV_VAR];
-  else process.env[INFERENCE_ENV_VAR] = inference;
-  try {
-    return await fn();
-  } finally {
-    if (prevDataDir === undefined) delete process.env.OPENCODE_DATA_DIR;
-    else process.env.OPENCODE_DATA_DIR = prevDataDir;
-    if (prevMgmt === undefined) delete process.env[MGMT_ENV_VAR];
-    else process.env[MGMT_ENV_VAR] = prevMgmt;
-    if (prevInference === undefined) delete process.env[INFERENCE_ENV_VAR];
-    else process.env[INFERENCE_ENV_VAR] = prevInference;
-  }
-}
-
-function setupHarness(options: Record<string, unknown>) {
-  const catalogCallbacks: Array<(draft: unknown) => Promise<void>> = [];
-  const ctx = {
-    options,
-    catalog: {
-      transform: (cb: (draft: unknown) => Promise<void>) => {
-        catalogCallbacks.push(cb);
-        return Promise.resolve({ dispose: async () => {} });
-      },
-    },
-    integration: {
-      transform: () => Promise.resolve({ dispose: async () => {} }),
-    },
-  };
-  return { catalogCallbacks, ctx };
-}
-
-function stubDraft() {
-  const published = new Map<string, Record<string, unknown>>();
-  const draft = {
-    provider: { update: (_id: string, fn: (p: Record<string, unknown>) => void) => fn({}) },
-    model: {
-      update: (pid: string, mid: string, fn: (m: Record<string, unknown>) => void) => {
-        const key = pid + "/" + mid;
-        let entry = published.get(key);
-        if (entry === undefined) {
-          entry = { id: mid, providerID: pid };
-          published.set(key, entry);
-        }
-        fn(entry);
-      },
-    },
-  };
-  return { draft, published };
-}
-
-function fallbackWarns(warns: string[]): string[] {
-  return warns.filter((w) => w.includes("managementReadToken"));
-}
-
-async function runSetup(ctx: unknown): Promise<void> {
-  await (plugin as unknown as { setup: (ctx: unknown) => Promise<void> }).setup(ctx);
-}
-
-describe("plugin-v2 management token environment source", () => {
-  it("uses the managementReadToken option for /api/* while models keep apiKey", async () => {
-    await withIsolatedEnv(undefined, undefined, async () => {
-      const h = installHarness([]);
-      try {
-        const { catalogCallbacks, ctx } = setupHarness({
-          baseURL: "https://gw.example.com",
-          providerId: "omniroute",
-          apiKey: "chat-key",
-          managementReadToken: "mgmt-option-token",
-        });
-        await runSetup(ctx);
-        assert.deepEqual(fallbackWarns(h.warns), []);
-        const { draft } = stubDraft();
-        await catalogCallbacks[0](draft);
-        assert.equal(h.seen.get(COMBOS_URL), "Bearer mgmt-option-token");
-        assert.equal(h.seen.get(MODELS_URL), "Bearer chat-key");
-      } finally {
-        h.restore();
-      }
-    });
-  });
-
-  it("reads the management token from the environment when the option is absent", async () => {
-    await withIsolatedEnv("mgmt-env-token", undefined, async () => {
-      const h = installHarness([]);
-      try {
-        const { catalogCallbacks, ctx } = setupHarness({
-          baseURL: "https://gw.example.com",
-          providerId: "omniroute",
-          apiKey: "chat-key",
-        });
-        await runSetup(ctx);
-        assert.deepEqual(fallbackWarns(h.warns), []);
-        const { draft } = stubDraft();
-        await catalogCallbacks[0](draft);
-        assert.equal(h.seen.get(COMBOS_URL), "Bearer mgmt-env-token");
-        assert.equal(h.seen.get(MODELS_URL), "Bearer chat-key");
-      } finally {
-        h.restore();
-      }
-    });
-  });
-
-  it("prefers the option over the environment", async () => {
-    await withIsolatedEnv("mgmt-env-token", undefined, async () => {
-      const h = installHarness([]);
-      try {
-        const { catalogCallbacks, ctx } = setupHarness({
-          baseURL: "https://gw.example.com",
-          providerId: "omniroute",
-          apiKey: "chat-key",
-          managementReadToken: "mgmt-option-token",
-        });
-        await runSetup(ctx);
-        assert.deepEqual(fallbackWarns(h.warns), []);
-        const { draft } = stubDraft();
-        await catalogCallbacks[0](draft);
-        assert.equal(h.seen.get(COMBOS_URL), "Bearer mgmt-option-token");
-      } finally {
-        h.restore();
-      }
-    });
-  });
-
-  it("falls back to the inference key with a single early warning when neither is set", async () => {
-    await withIsolatedEnv(undefined, undefined, async () => {
-      const h = installHarness([]);
-      try {
-        const { catalogCallbacks, ctx } = setupHarness({
-          baseURL: "https://gw.example.com",
-          providerId: "omniroute",
-          apiKey: "chat-key",
-        });
-        await runSetup(ctx);
-        const atSetup = fallbackWarns(h.warns);
-        assert.equal(
-          atSetup.length,
-          1,
-          `expected exactly one early fallback warning, got: ${JSON.stringify(h.warns)}`
-        );
-        assert.match(atSetup[0] ?? "", /managementReadToken/);
-        assert.match(atSetup[0] ?? "", new RegExp(MGMT_ENV_VAR));
-        assert.ok(!(atSetup[0] ?? "").includes("chat-key"), "warning must not leak the key");
-        const { draft } = stubDraft();
-        await catalogCallbacks[0](draft);
-        assert.equal(h.seen.get(COMBOS_URL), "Bearer chat-key");
-        assert.equal(
-          fallbackWarns(h.warns).length,
-          1,
-          "the fallback warning stays a single setup-time notice"
-        );
-      } finally {
-        h.restore();
-      }
-    });
-  });
-
-  it("treats an empty option as absent so the environment wins", async () => {
-    await withIsolatedEnv("mgmt-env-token", undefined, async () => {
-      const h = installHarness([]);
-      try {
-        const { catalogCallbacks, ctx } = setupHarness({
-          baseURL: "https://gw.example.com",
-          providerId: "omniroute",
-          apiKey: "chat-key",
-          managementReadToken: "",
-        });
-        await runSetup(ctx);
-        assert.deepEqual(fallbackWarns(h.warns), []);
-        const { draft } = stubDraft();
-        await catalogCallbacks[0](draft);
-        assert.equal(h.seen.get(COMBOS_URL), "Bearer mgmt-env-token");
-      } finally {
-        h.restore();
-      }
-    });
-  });
-
-  it("treats an empty environment value as absent so the option wins", async () => {
-    await withIsolatedEnv("", undefined, async () => {
-      const h = installHarness([]);
-      try {
-        const { catalogCallbacks, ctx } = setupHarness({
-          baseURL: "https://gw.example.com",
-          providerId: "omniroute",
-          apiKey: "chat-key",
-          managementReadToken: "mgmt-option-token",
-        });
-        await runSetup(ctx);
-        assert.deepEqual(fallbackWarns(h.warns), []);
-        const { draft } = stubDraft();
-        await catalogCallbacks[0](draft);
-        assert.equal(h.seen.get(COMBOS_URL), "Bearer mgmt-option-token");
-      } finally {
-        h.restore();
-      }
-    });
-  });
-
-  it("falls back with a warning when both the option and the environment are empty", async () => {
-    await withIsolatedEnv("", undefined, async () => {
-      const h = installHarness([]);
-      try {
-        const { catalogCallbacks, ctx } = setupHarness({
-          baseURL: "https://gw.example.com",
-          providerId: "omniroute",
-          apiKey: "chat-key",
-          managementReadToken: "",
-        });
-        await runSetup(ctx);
-        assert.equal(fallbackWarns(h.warns).length, 1);
-        const { draft } = stubDraft();
-        await catalogCallbacks[0](draft);
-        assert.equal(h.seen.get(COMBOS_URL), "Bearer chat-key");
-      } finally {
-        h.restore();
-      }
-    });
-  });
-
-  it("enriches the catalog from the environment token alone", async () => {
-    const providers = new Map<string, ProviderV2Info>();
-    const models = new Map<string, ModelV2Info>();
-    const draft = {
-      provider: {
-        list: () => [],
-        get: (id: string) => providers.get(id) as never,
-        update: (id: string, fn: (p: ProviderV2Info) => void) => {
-          const p = (providers.get(id) ?? { id }) as ProviderV2Info;
-          fn(p);
-          providers.set(id, p);
-        },
-        remove: () => {},
-      },
-      model: {
-        get: () => undefined,
-        update: (pid: string, mid: string, fn: (m: ModelV2Info) => void) => {
-          const k = pid + "/" + mid;
-          const m = (models.get(k) ?? { id: mid, providerID: pid }) as ModelV2Info;
-          fn(m);
-          models.set(k, m);
-        },
-        remove: () => {},
-        default: { get: () => undefined, set: () => {} },
-      },
-    } as unknown as CatalogDraft;
-    let seenCombos = "";
-    let seenPricing = "";
-    const res = await withIsolatedEnv("mgmt-env-token", undefined, async () =>
-      publishCatalog(
-        draft,
-        {
-          providerId: "omniroute",
-          baseURL: "https://gw.example.com",
-          apiKey: "chat-key",
-          managementReadToken: process.env[MGMT_ENV_VAR],
-          timeoutMs: 1000,
-          modelCacheTtlMs: 300000,
-          usableOnly: false,
-        },
-        {
-          fetcher: async () => [{ id: "m1" }],
-          combosFetcher: async (_base, token) => {
-            seenCombos = token;
-            return [{ id: "team-combo", models: [{ kind: "model", model: "m1" }] }];
-          },
-          enrichmentFetcher: async (_base, token) => {
-            seenPricing = token;
-            // The process env is the source under test: the resolver output
-            // flows in through the option above, so report success only when
-            // the flow under test actually carried it.
-            if (token !== "mgmt-env-token") return new Map();
-            return new Map([["team-combo", { name: "Team Combo" }]]);
-          },
-        }
-      )
-    );
-    assert.deepEqual(res, { models: 1, combos: 1, autoCombos: 0 });
-    assert.equal(seenCombos, "mgmt-env-token");
-    assert.equal(seenPricing, "mgmt-env-token");
-    const entry = models.get("omniroute/team-combo");
-    assert.ok(entry, "expected the combo entry in the published catalog");
-    assert.equal(entry?.name, "Team Combo");
-  });
-});
--- a/@omniroute/opencode-plugin-v2/tests/options.test.ts
+++ b/@omniroute/opencode-plugin-v2/tests/options.test.ts
@@ -29,38 +29,6 @@ describe("parsePluginOptions", () => {
  it("requires baseURL", () => {
    assert.throws(() => parsePluginOptions({}), /baseURL/);
  });
-  it("rejects a baseURL that is not an http(s) URL", () => {
-    // `new URL()` reads "localhost:20128" as the scheme "localhost:" followed
-    // by a path, so a gateway address typed without "http://" parses. Every
-    // model would then be published with "localhost:20128/v1" as its api url
-    // and every call would fail in the client on an unknown scheme, with no
-    // request on the wire and nothing in the gateway logs.
-    for (const baseURL of [
-      "localhost:20128",
-      "localhost:20128/v1",
-      "ftp://gw.example.com/v1",
-      "gw.example.com/v1",
-    ]) {
-      assert.throws(
-        () => parsePluginOptions({ baseURL }),
-        /baseURL must be an http\(s\) URL/,
-        `expected ${baseURL} to be rejected`
-      );
-    }
-  });
-  it("accepts http and https baseURLs, with or without a port or path", () => {
-    for (const baseURL of [
-      "http://localhost:20128/v1",
-      "http://localhost:20128",
-      "https://gw.example.com/v1",
-      "https://gw.example.com/omniroute/v1",
-    ]) {
-      assert.equal(parsePluginOptions({ baseURL }).baseURL, baseURL);
-      // Padding a copied address is trimmed rather than rejected, matching the
-      // treatment `headroomUrl` already gets in the settings schema.
-      assert.equal(parsePluginOptions({ baseURL: `  ${baseURL}  ` }).baseURL, baseURL);
-    }
-  });
  it("rejects unknown top-level keys (strict)", () => {
    assert.throws(() => parsePluginOptions({ baseURL: "https://gw.example.com", bogus: 1 }));
  });
--- a/@omniroute/opencode-plugin-v2/tests/snapshot-stale-entries.test.ts
+++ b/@omniroute/opencode-plugin-v2/tests/snapshot-stale-entries.test.ts
@@ -5,11 +5,7 @@ import { tmpdir } from "node:os";
 import { join } from "node:path";
 import { createHash } from "node:crypto";
 import plugin from "../src/index.js";
-import {
-  diskSnapshotPath,
-  isStaleSnapshotModel,
-  snapshotIdentityFingerprint,
-} from "../src/cache.js";
+import { diskSnapshotPath, snapshotIdentityFingerprint } from "../src/cache.js";
 import { legacyApiToInfoApi } from "../src/catalog.js";

 function isolateDisk(): { dir: string; restore: () => void } {
@@ -101,7 +97,7 @@ function downFetch(): typeof fetch {
 const fingerprint = snapshotIdentityFingerprint("https://gw.example.com", "k-snapfix", "k-snapfix");

 describe("plugin-v2 snapshot stale-entry filter", () => {
-  it("snapshot with 3 unusable pre-mapped entries + 1 valid: only the valid one is published + warn emitted", async () => {
+  it("snapshot with 2 entries without api block + 1 valid: only the valid one is published + warn emitted", async () => {
    const disk = isolateDisk();
    const providerId = "snapfix-mixed";
    mkdirSync(join(disk.dir, "plugins"), { recursive: true });
@@ -110,15 +106,11 @@ describe("plugin-v2 snapshot stale-entry filter", () => {
      JSON.stringify({
        v: 2,
        identityFingerprint: fingerprint,
-        // Three pre-mapped entries with an unusable api block — missing npm,
-        // empty npm, and a well-formed npm with no url (the shape a snapshot
-        // written by an older build carries, and the one that reaches the host
-        // as a bare `Invalid URL`) — plus one plain raw entry, which has no api
-        // block at all and gets one synthesized at publish time.
+        // Two pre-mapped entries with a broken api block (missing npm) plus
+        // one plain raw entry (no api block: synthesized at publish time).
        models: [
          { id: "stale-a", api: {} },
          { id: "stale-b", api: { npm: "" } },
-          { id: "stale-c", api: { id: "openai-compatible", npm: "@ai-sdk/openai-compatible" } },
          { id: "good-1", context_length: 128000 },
        ],
        combos: [],
@@ -145,7 +137,7 @@ describe("plugin-v2 snapshot stale-entry filter", () => {
        );
      });
      assert.ok(
-        warns.some((w) => w.includes("dropping 3 stale snapshot entries with an unusable api block")),
+        warns.some((w) => w.includes("dropping 2 stale snapshot entries without api block")),
        `expected stale-drop warn, got: ${JSON.stringify(warns)}`
      );
    } finally {
@@ -224,56 +216,4 @@ describe("plugin-v2 snapshot stale-entry filter", () => {
    // Sanity: sha256 helper used above matches the plugin identity scheme.
    assert.equal(createHash("sha256").update("x").digest("hex").length, 64);
  });
-
-  it("legacyApiToInfoApi throws unless api.url is an http(s) url", () => {
-    const npm = "@ai-sdk/openai-compatible";
-    for (const api of [
-      { id: "openai-compatible", npm },
-      { id: "openai-compatible", npm, url: "" },
-      { id: "openai-compatible", npm, url: "   " },
-      // Non-empty but uncallable: the AI SDK reaches `fetch` and fails there.
-      { id: "openai-compatible", npm, url: "/v1" },
-      { id: "openai-compatible", npm, url: "gw.example.com/v1" },
-      { id: "openai-compatible", npm, url: "ftp://gw.example.com/v1" },
-    ]) {
-      assert.throws(
-        () => legacyApiToInfoApi(api as unknown as { id: string; npm: string; url: string }),
-        /api block carries no http\(s\) url/,
-        `expected a publish-time refusal for ${JSON.stringify(api)}`
-      );
-    }
-    // A complete block still publishes unchanged.
-    assert.deepEqual(
-      legacyApiToInfoApi({
-        id: "openai-compatible",
-        npm: "@ai-sdk/openai-compatible",
-        url: "https://gw.example.com/v1",
-      }),
-      {
-        id: "openai-compatible",
-        type: "aisdk",
-        package: "@ai-sdk/openai-compatible",
-        url: "https://gw.example.com/v1",
-      }
-    );
-  });
-
-  it("isStaleSnapshotModel drops a pre-mapped entry whose api.url is unusable", () => {
-    const npm = "@ai-sdk/openai-compatible";
-    // Present-but-unusable url: stale, for the same reason a missing npm is.
-    for (const url of [undefined, "", "   ", "/v1", "gw.example.com/v1", "ftp://gw/v1"]) {
-      assert.equal(
-        isStaleSnapshotModel({ id: "a/b", api: { id: "x", npm, ...(url === undefined ? {} : { url }) } }),
-        true,
-        `expected ${JSON.stringify(url)} to be treated as stale`
-      );
-    }
-    // Complete block: publishable.
-    assert.equal(
-      isStaleSnapshotModel({ id: "a/b", api: { id: "x", npm, url: "https://gw/v1" } }),
-      false
-    );
-    // No api block at all stays publishable: it is synthesized at publish time.
-    assert.equal(isStaleSnapshotModel({ id: "a/b" }), false);
-  });
 });
--- a/@omniroute/opencode-plugin/package.json
+++ b/@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/telemetry.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 tests/naming.test.ts tests/free-budget-magnitude.test.ts tests/models-fetcher.test.ts tests/issue-13000-cold-start-combo-limit.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/telemetry.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 tests/naming.test.ts tests/free-budget-magnitude.test.ts tests/models-fetcher.test.ts",
    "prepublishOnly": "npm run clean && npm run build && npm test"
  },
  "keywords": [
--- a/@omniroute/opencode-plugin/src/index.ts
+++ b/@omniroute/opencode-plugin/src/index.ts
@@ -220,11 +220,7 @@ const optionsSchema = z
     * to 60000. Default when unset: 300000.
     */
    autoSyncIntervalMs: z.number().int().nonnegative().optional(),
-    baseURL: z
-      .string()
-      .trim()
-      .refine(isHttpUrl, "baseURL must be an http(s) URL, for example http://localhost:20128")
-      .optional(),
+    baseURL: z.string().url().optional(),
    managementReadToken: z.string().min(1).optional(),
    features: featuresSchema.optional(),
  })
@@ -486,22 +482,6 @@ export const DEFAULT_ANTHROPIC_PREFIXES = ["cc", "claude", "anthropic", "kiro",
 * (it appends `/v1/messages` automatically), so callers should branch on
 * format first.
 */
-/**
- * A url the AI SDK can actually call. `new URL()` alone is not enough: it
- * parses `localhost:20128` as the scheme `localhost:` and `ftp://host` as ftp,
- * both of which reach `fetch` and fail there. Mirrors the `isHttpUrl` guard the
- * settings schema applies to `headroomUrl`.
- */
-export function isHttpUrl(value: unknown): boolean {
-  if (typeof value !== "string") return false;
-  try {
-    const { protocol } = new URL(value);
-    return protocol === "http:" || protocol === "https:";
-  } catch {
-    return false;
-  }
-}
-
 export function ensureV1Suffix(url: string): string {
  const trimmed = trimTrailingSlashes(url);
  return trimmed.endsWith("/v1") ? trimmed : `${trimmed}/v1`;
@@ -4631,21 +4611,9 @@ export function buildStaticProviderEntry(
          .map((m) => m.max_output_tokens)
          .filter((v): v is number => typeof v === "number" && v > 0);

-        // Prefer the server-computed aggregate (accounts for explicit
-        // context_length overrides and members outside memberEntries, e.g.
-        // not yet resolved in /v1/models) over the raw Math.min(member)
-        // lower bound. Mirrors mapComboToModelV2's limit.context logic
-        // (#13000) so the static catalog and the dynamic hook agree.
-        const preferredContext =
-          typeof combo.computed_context_length === "number" && combo.computed_context_length > 0
-            ? combo.computed_context_length
-            : contextValues.length > 0
-              ? Math.min(...contextValues)
-              : undefined;
-
-        if (preferredContext !== undefined && outputValues.length > 0) {
+        if (contextValues.length > 0 && outputValues.length > 0) {
          entry.limit = {
-            context: preferredContext,
+            context: Math.min(...contextValues),
            output: Math.min(...outputValues),
          };
        }
@@ -5523,32 +5491,6 @@ export function createOmniRouteConfigHook(

        const modelsFetchOk = !modelsFetchThrew && localRawModels.length > 0;

-        // Snapshot backfill for computed_context_length: a live /api/combos
-        // response can come back without this field (server hasn't finished
-        // recomputing it yet, e.g. just after a restart) even though the
-        // combo's members and identity are otherwise unchanged. When that
-        // happens, prefer the last-known-good value from the warm disk
-        // snapshot over the Math.min(member) fallback in
-        // mapComboToModelV2() — never overwrite any other combo field
-        // (models/name/etc.) with stale data, only this one derived number.
-        if (warmSnapshot) {
-          const snapshotComboById = new Map(warmSnapshot.rawCombos.map((c) => [c.id, c]));
-          for (const combo of localRawCombos) {
-            const hasLive =
-              typeof combo.computed_context_length === "number" &&
-              combo.computed_context_length > 0;
-            if (hasLive) continue;
-            const stale = snapshotComboById.get(combo.id);
-            if (
-              stale &&
-              typeof stale.computed_context_length === "number" &&
-              stale.computed_context_length > 0
-            ) {
-              combo.computed_context_length = stale.computed_context_length;
-            }
-          }
-        }
-
        // Disk-cache fallback (cold first run, no warm snapshot): when the
        // live fetch returned no models AND features.diskCache !== false,
        // hydrate from the last-known-good snapshot so OC still surfaces a
@@ -5556,17 +5498,9 @@ export function createOmniRouteConfigHook(
        if (modelsFetchThrew && wantDiskCache && !warmSnapshot) {
          const snapshot = await diskSnapshotReader(resolved.providerId, snapshotFingerprint);
          if (snapshot && snapshot.rawModels.length > 0) {
-            // Report snapshot age like the warm-startup path already does:
-            // "stale" alone reads as a transient blip, so a week-old catalog
-            // is indistinguishable from a five-minute-old one.
-            const snapshotAge = snapshot.writtenAt;
-            const snapshotAgeLabel =
-              typeof snapshotAge === "number"
-                ? `${Math.round((Date.now() - snapshotAge) / 3_600_000)}h`
-                : "unknown";
            logAt(
              "warn",
-              `config shim: /v1/models unreachable; using stale disk cache (${snapshot.rawModels.length} models, age ${snapshotAgeLabel})`
+              `config shim: /v1/models unreachable; using stale disk cache (${snapshot.rawModels.length} models)`
            );
            localRawModels = snapshot.rawModels;
            localRawCombos = snapshot.rawCombos;
--- a/@omniroute/opencode-plugin/tests/config-shim.test.ts
+++ b/@omniroute/opencode-plugin/tests/config-shim.test.ts
@@ -481,7 +481,10 @@ test("config: combos fetcher throws → emit models-only catalog (no combos in m
  ];
  assert.ok(entry);
  const ids = Object.keys(entry.models).sort();
-  assert.deepEqual(ids, ["claude-sonnet-4-6", "gemini-3-flash"]);
+  assert.deepEqual(ids, [
+    "claude-sonnet-4-6",
+    "gemini-3-flash",
+  ]);
  assert.equal(entry.models["claude-tier"], undefined, "no combo entry");
  assert.ok(
    logger.entries.some((e) => String(e[0]).includes("/api/combos fetch failed")),
@@ -1038,7 +1041,11 @@ test("config: features.enrichment=false skips enrichment fetch + keeps raw-id na
  ];
  assert.ok(entry);
  assert.equal(enrichmentFetcher.callCount(), 0, "enrichment fetch suppressed by feature flag");
-  assert.equal(entry.models["claude-sonnet-4-6"].name, "claude-sonnet-4-6", "raw id retained");
+  assert.equal(
+    entry.models["claude-sonnet-4-6"].name,
+    "claude-sonnet-4-6",
+    "raw id retained"
+  );
 });

 test("config: enrichment fetcher throws → soft-fail (warn + raw-id static catalog)", async () => {
@@ -1061,7 +1068,11 @@ test("config: enrichment fetcher throws → soft-fail (warn + raw-id static cata
    "opencode-omniroute"
  ];
  assert.ok(entry, "static block still published on enrichment failure");
-  assert.equal(entry.models["claude-sonnet-4-6"].name, "claude-sonnet-4-6", "raw id retained");
+  assert.equal(
+    entry.models["claude-sonnet-4-6"].name,
+    "claude-sonnet-4-6",
+    "raw id retained"
+  );
  assert.equal(enrichmentFetcher.callCount(), 1);
  assert.ok(
    logger.entries.some((e) => String(e[0]).includes("/api/pricing/models fetch failed")),
@@ -1259,7 +1270,10 @@ test("config: diskCache hydrates stale snapshot when /v1/models throws", async (
  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
    "opencode-omniroute"
  ];
-  assert.ok(entry.models["claude-sonnet-4-6"], "stale snapshot hydrated into static block");
+  assert.ok(
+    entry.models["claude-sonnet-4-6"],
+    "stale snapshot hydrated into static block"
+  );
  assert.equal(
    entry.models["claude-sonnet-4-6"].name,
    "Claude Sonnet 4.6 (cached)",
@@ -1267,95 +1281,14 @@ test("config: diskCache hydrates stale snapshot when /v1/models throws", async (
  );
  assert.equal(writes, 0, "disk write skipped when live fetch failed");
  assert.ok(
-    logger.entries.some(
-      (e) =>
-        String(e[0]).includes("using stale disk cache") ||
-        String(e[0]).includes("warm startup from disk snapshot")
+    logger.entries.some((e) =>
+      String(e[0]).includes("using stale disk cache") ||
+      String(e[0]).includes("warm startup from disk snapshot")
    ),
    "disk-cache hydration breadcrumb emitted"
  );
 });

-// The stale-fallback branch (`modelsFetchThrew && wantDiskCache && !warmSnapshot`)
-// only runs when the warm-startup read found nothing — a snapshot can appear on
-// disk between that first read and the live fetch failing (e.g. another OC
-// process instance wrote one concurrently). A stateful reader simulates that:
-// empty on the warm-startup read, populated by the time the fallback re-reads.
-function emptyThenSnapshotReader(
-  snapshot: Omit<
-    Awaited<ReturnType<typeof import("../src/index.js").defaultDiskSnapshotReader>> & object,
-    never
-  >
-): typeof import("../src/index.js").defaultDiskSnapshotReader {
-  let calls = 0;
-  return (async () => {
-    calls++;
-    return calls === 1 ? undefined : snapshot;
-  }) as typeof import("../src/index.js").defaultDiskSnapshotReader;
-}
-
-test("config: stale-fallback warning reports the disk snapshot age in hours", async () => {
-  const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
-  });
-  const fetcher = throwingModelsFetcher();
-  const combosFetcher = stubCombosFetcher([]);
-  const logger = captureWarn();
-
-  const writtenAt = Date.now() - 2 * 3_600_000; // 2h old
-  const diskSnapshotReader = emptyThenSnapshotReader({
-    rawModels: [MODEL_CLAUDE],
-    rawCombos: [],
-    rawEnrichment: new Map(),
-    rawCompressionCombos: [],
-    rawConnections: [],
-    writtenAt,
-  });
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute", features: { diskCache: true } },
-    { readAuthJson, fetcher, combosFetcher, diskSnapshotReader, logger }
-  );
-
-  await hook(makeInput());
-
-  assert.ok(
-    logger.entries.some((e) => String(e[0]).includes("using stale disk cache (1 models, age 2h)")),
-    "stale-fallback warning includes the computed snapshot age"
-  );
-});
-
-test('config: stale-fallback warning falls back to "unknown" age without writtenAt', async () => {
-  const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
-  });
-  const fetcher = throwingModelsFetcher();
-  const combosFetcher = stubCombosFetcher([]);
-  const logger = captureWarn();
-
-  const diskSnapshotReader = emptyThenSnapshotReader({
-    rawModels: [MODEL_CLAUDE],
-    rawCombos: [],
-    rawEnrichment: new Map(),
-    rawCompressionCombos: [],
-    rawConnections: [],
-  });
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute", features: { diskCache: true } },
-    { readAuthJson, fetcher, combosFetcher, diskSnapshotReader, logger }
-  );
-
-  await hook(makeInput());
-
-  assert.ok(
-    logger.entries.some((e) =>
-      String(e[0]).includes("using stale disk cache (1 models, age unknown)")
-    ),
-    'stale-fallback warning falls back to "unknown" when writtenAt is absent'
-  );
-});
-
 test("config: cached rawEnrichment from earlier provider hook is reused (no refetch)", async () => {
  const readAuthJson = stubReadAuthJson({
    "opencode-omniroute": { type: "api", key: "sk-shared", baseURL: "https://or.example/v1" },
@@ -1443,7 +1376,10 @@ test("config: providerTag (default-on) prepends '<provider> - ' to enriched raw-
    "opencode-omniroute"
  ];
  assert.ok(entry);
-  assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude - Claude Sonnet 4.6");
+  assert.equal(
+    entry.models["claude-sonnet-4-6"].name,
+    "Claude - Claude Sonnet 4.6"
+  );
  assert.equal(entry.models["gemini-3-flash"].name, "Gemini - Gemini 3 Flash");
  // Combos stay untouched — `Combo: ` prefix already conveys multi-upstream.
  assert.equal(entry.models["claude-tier"].name, "Claude Tier");
@@ -1559,7 +1495,10 @@ test("config: providerTag is idempotent — second hook call doesn't double-suff
  const entryA = (inputA as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
    "opencode-omniroute"
  ];
-  assert.equal(entryA.models["claude-sonnet-4-6"].name, "Claude - Claude Sonnet 4.6");
+  assert.equal(
+    entryA.models["claude-sonnet-4-6"].name,
+    "Claude - Claude Sonnet 4.6"
+  );

  // Second invocation (cache hit) — name must still be single-suffixed.
  const inputB = makeInput();
@@ -1567,7 +1506,10 @@ test("config: providerTag is idempotent — second hook call doesn't double-suff
  const entryB = (inputB as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
    "opencode-omniroute"
  ];
-  assert.equal(entryB.models["claude-sonnet-4-6"].name, "Claude - Claude Sonnet 4.6");
+  assert.equal(
+    entryB.models["claude-sonnet-4-6"].name,
+    "Claude - Claude Sonnet 4.6"
+  );
 });

 // ────────────────────────────────────────────────────────────────────────────
--- a/@omniroute/opencode-plugin/tests/issue-13000-cold-start-combo-limit.test.ts
+++ b/@omniroute/opencode-plugin/tests/issue-13000-cold-start-combo-limit.test.ts
@@ -1,221 +0,0 @@
-/**
- * Repro for #13000: combo context limits fall back to Math.min(member)
- * instead of using computed_context_length after cold start — no disk
- * snapshot fallback.
- *
- * Scenario (mirrors the report): a warm disk snapshot holds the combo with
- * its correct server-computed `computed_context_length` (245000, from all 6
- * members). After a restart, the live refresh's combos fetch returns the
- * SAME combo but without `computed_context_length` (e.g. the value hasn't
- * propagated yet), and the live models fetch only resolves 2 of the 6
- * members (the rest not yet in /v1/models). The background refresh then
- * republishes the provider block built from this degraded live data,
- * downgrading a previously-known-good 245000 limit to Math.min(163840,
- * 1_000_000) = 163840 — exactly the member-minimum described in the issue.
- */
-
-import test from "node:test";
-import assert from "node:assert/strict";
-import type { Config } from "@opencode-ai/plugin";
-
-import {
-  createOmniRouteConfigHook,
-  _resetInflightRefresh,
-  type OmniRouteAutoCombosFetcher,
-  type OmniRouteCombosFetcher,
-  type OmniRouteCompressionMetaFetcher,
-  type OmniRouteEnrichmentFetcher,
-  type OmniRouteFetchCache,
-  type OmniRouteModelsFetcher,
-  type OmniRouteProvidersFetcher,
-  type OmniRouteRawCombo,
-  type OmniRouteRawModelEntry,
-  type OmniRouteReadAuthJson,
-  type OmniRouteStaticProviderEntry,
-  type OmniRouteDiskSnapshotReader,
-  type OmniRouteDiskSnapshotWriter,
-} from "../src/index.js";
-
-test.beforeEach(() => {
-  _resetInflightRefresh();
-});
-
-function stubReadAuthJson(value: Record<string, unknown>): OmniRouteReadAuthJson {
-  return async () => value as never;
-}
-
-function authStub() {
-  return stubReadAuthJson({
-    "opencode-omniroute": {
-      type: "api",
-      key: "sk-test",
-      baseURL: "https://or.example.com/v1",
-    },
-  });
-}
-
-function makeInput(): Config {
-  return { provider: {} } as unknown as Config;
-}
-
-// The two members resolvable in the degraded live /v1/models response.
-const MEMBER_DEEPSEEK: OmniRouteRawModelEntry = {
-  id: "deepseek-v4-pro",
-  capabilities: { tool_calling: true, reasoning: true, vision: false, thinking: false },
-  context_length: 163_840,
-  max_output_tokens: 64_000,
-  input_modalities: ["text"],
-  output_modalities: ["text"],
-};
-
-const MEMBER_GLM: OmniRouteRawModelEntry = {
-  id: "glm-5.2",
-  capabilities: { tool_calling: true, reasoning: true, vision: false, thinking: false },
-  context_length: 1_000_000,
-  max_output_tokens: 16_384,
-  input_modalities: ["text"],
-  output_modalities: ["text"],
-};
-
-// The other member that IS present once the server is fully warm.
-const MEMBER_GLM_53_HIGH: OmniRouteRawModelEntry = {
-  id: "GLM-5.3-high",
-  capabilities: { tool_calling: true, reasoning: true, vision: false, thinking: false },
-  context_length: 245_000,
-  max_output_tokens: 128_000,
-  input_modalities: ["text"],
-  output_modalities: ["text"],
-};
-
-const COMBO_MODELS: OmniRouteRawCombo["models"] = [
-  { kind: "model", model: "deepseek-v4-pro", weight: 25 },
-  { kind: "model", model: "glm-5.2", weight: 25 },
-  { kind: "model", model: "GLM-5.3-high", weight: 50 },
-];
-
-test("issue #13000: warm combo limit (245000) survives a degraded post-restart refresh instead of downgrading to Math.min(member)", async () => {
-  const warmSnapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> = {
-    rawModels: [MEMBER_DEEPSEEK, MEMBER_GLM, MEMBER_GLM_53_HIGH],
-    rawCombos: [
-      {
-        id: "orchestrator",
-        name: "orchestrator",
-        models: COMBO_MODELS,
-        computed_context_length: 245_000,
-      },
-    ],
-    rawAutoCombos: [],
-    rawEnrichment: new Map(),
-    rawCompressionCombos: [],
-    rawConnections: [],
-  };
-
-  const fetcher: OmniRouteModelsFetcher = async () => [MEMBER_DEEPSEEK, MEMBER_GLM];
-  const combosFetcher: OmniRouteCombosFetcher = async () => [
-    {
-      id: "orchestrator",
-      name: "orchestrator",
-      models: COMBO_MODELS,
-      // computed_context_length intentionally omitted.
-    },
-  ];
-  const autoCombosFetcher: OmniRouteAutoCombosFetcher = async () => [];
-  const enrichmentFetcher: OmniRouteEnrichmentFetcher = async () => new Map();
-  const compressionMetaFetcher: OmniRouteCompressionMetaFetcher = async () => [];
-  const providersFetcher: OmniRouteProvidersFetcher = async () => [];
-
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => warmSnapshot;
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
-
-  const sharedCache: OmniRouteFetchCache = new Map();
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute", modelCacheTtl: 60_000 },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      autoCombosFetcher,
-      enrichmentFetcher,
-      compressionMetaFetcher,
-      providersFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      cache: sharedCache,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  // Let the detached background refresh (degraded live data) complete and
-  // republish the block.
-  await new Promise((r) => setTimeout(r, 100));
-
-  const entryAfter = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  const comboModelAfter = entryAfter.models["orchestrator"];
-  assert.ok(comboModelAfter, "combo model still published after refresh");
-
-  assert.equal(
-    comboModelAfter.limit.context,
-    245_000,
-    `expected the combo limit to stay at the known-good 245000, but got ${comboModelAfter.limit.context} ` +
-      `(Math.min(member) fallback — the exact bug described in #13000)`
-  );
-});
-
-test("issue #13000 (control): no warm snapshot exists — Math.min(member) fallback is still used (expected, documented behavior)", async () => {
-  const fetcher: OmniRouteModelsFetcher = async () => [MEMBER_DEEPSEEK, MEMBER_GLM];
-  const combosFetcher: OmniRouteCombosFetcher = async () => [
-    {
-      id: "orchestrator",
-      name: "orchestrator",
-      models: COMBO_MODELS,
-      // computed_context_length intentionally omitted.
-    },
-  ];
-  const autoCombosFetcher: OmniRouteAutoCombosFetcher = async () => [];
-  const enrichmentFetcher: OmniRouteEnrichmentFetcher = async () => new Map();
-  const compressionMetaFetcher: OmniRouteCompressionMetaFetcher = async () => [];
-  const providersFetcher: OmniRouteProvidersFetcher = async () => [];
-
-  // No prior snapshot on disk.
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
-
-  const sharedCache: OmniRouteFetchCache = new Map();
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute", modelCacheTtl: 60_000 },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      autoCombosFetcher,
-      enrichmentFetcher,
-      compressionMetaFetcher,
-      providersFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      cache: sharedCache,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  const entryAfter = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  const comboModelAfter = entryAfter.models["orchestrator"];
-  assert.ok(comboModelAfter, "combo model published on cold first run");
-
-  // No snapshot to backfill from — Math.min(163840, 1_000_000) = 163840.
-  assert.equal(
-    comboModelAfter.limit.context,
-    163_840,
-    "pure cold start with no snapshot must keep using the Math.min(member) fallback"
-  );
-});
--- a/@omniroute/opencode-plugin/tests/options-schema.test.ts
+++ b/@omniroute/opencode-plugin/tests/options-schema.test.ts
@@ -59,26 +59,6 @@ test("parseOmniRoutePluginOptions: invalid baseURL (not a URL) → throws", () =
  assert.throws(() => parseOmniRoutePluginOptions({ baseURL: "not-a-url" }), /baseURL/i);
 });

-test("parseOmniRoutePluginOptions: baseURL without an http(s) scheme → throws", () => {
-  // `new URL()` reads "localhost:20128" as the scheme "localhost:" followed by
-  // a path, so the address parses and the models are published with an api url
-  // no client can call.
-  for (const baseURL of ["localhost:20128", "localhost:20128/v1", "ftp://or.example.com", "or.example.com"]) {
-    assert.throws(
-      () => parseOmniRoutePluginOptions({ baseURL }),
-      /baseURL must be an http\(s\) URL/,
-      `expected ${baseURL} to be rejected`
-    );
-  }
-});
-
-test("parseOmniRoutePluginOptions: http and https baseURLs are accepted, padding trimmed", () => {
-  for (const baseURL of ["http://localhost:20128", "https://or.example.com/v1"]) {
-    assert.equal(parseOmniRoutePluginOptions({ baseURL }).baseURL, baseURL);
-    assert.equal(parseOmniRoutePluginOptions({ baseURL: `  ${baseURL}  ` }).baseURL, baseURL);
-  }
-});
-
 test("parseOmniRoutePluginOptions: unknown key → throws (strict mode catches typos)", () => {
  assert.throws(
    () =>
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -46,7 +46,7 @@ Repository map and Reference Documentation sections below.

 ## Project at a Glance

-**OmniRoute** — unified AI proxy/router. One endpoint, 359 LLM providers, auto-fallback.
+**OmniRoute** — unified AI proxy/router. One endpoint, 356 LLM providers, auto-fallback.

 | Layer         | Location                | Purpose                                                                                                                                                                   |
 | ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
@@ -56,7 +56,7 @@ 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 (178 migrations)                                                                                                                                    |
+| Database      | `src/lib/db/`           | SQLite domain modules (169 migrations)                                                                                                                                    |
 | Domain/Policy | `src/domain/`           | Policy engine, cost rules, fallback logic                                                                                                                                 |
 | MCP Server    | `open-sse/mcp-server/`  | 110 tools (45 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                                                                                                                                               |
@@ -578,31 +578,14 @@ own dedicated branch, and you MUST confirm the base branch with the operator bef
   # HARD LINKS (`cp -al`), never a symlink: ~5s for the whole tree and near-zero extra
   # disk (the inodes are shared), and unlike a symlink it does not break the dev server.
   cp -al "$(git -C <main_checkout> rev-parse --show-toplevel)/node_modules" node_modules
-   # `.husky/_` is gitignored, so a fresh worktree does NOT have it and
-   # `core.hooksPath=.husky/_` then points at a directory that does not exist —
-   # every pre-commit gate goes silently mute. Copy it too.
-   cp -a "$(git -C <main_checkout> rev-parse --show-toplevel)/.husky/_" .husky/_
   ```

-   `scripts/dev/new-worktree.sh <branch> [base]` does all of the above (canonical path,
-   hard-linked `node_modules`, `.husky/_`) and then **verifies** the hook is actually
-   executable, so prefer it over running the steps by hand.
-
   **Never `ln -s` node_modules.** Turbopack rejects a symlink that resolves outside the
   project root, so `npm run dev` dies with a FATAL panic (`Symlink [project]/node_modules
 is invalid, it points out of the filesystem root`) while typecheck, lint and the test
   runners all keep passing — the error names "filesystem root", not the worktree, so it
   reads like a Next/build bug and costs real time to trace (incident 2026-07-31, #9043).

-   **A worktree without `.husky/_` runs NO pre-commit gate — and says nothing.** `git`
-   resolves `core.hooksPath` relative to the worktree top; when the directory is missing it
-   simply finds no hook and commits. Nothing is printed, the commit succeeds, and the
-   identity/lint/docs gates never ran. This is how 59 commits carrying a stale identity
-   override (name of a contributor + the maintainer's e-mail) got past
-   `scripts/check/check-git-identity.sh` between 2026-08-29 and 09-02 — they were all made in
-   `cp -al` worktrees. Verify with `ls .husky/_/pre-commit` inside a new worktree, or just use
-   `scripts/dev/new-worktree.sh`, which fails loudly when the hook is not executable.
-
 3. **Work, commit, push, open the PR — all from inside the worktree.** Never `git checkout` a
   different branch inside a worktree another session might share.
 4. **Tear down only your own** worktree + branch when done, from the main checkout:
@@ -664,7 +647,7 @@ focused checks, and use a Conventional Commit message (for example, `docs: slim
 ## Environment

 - **Runtime**: Node.js ≥22.22.2 <23 || ≥24.0.0 <27, ES Modules. This is the **only supported** runtime for the published `omniroute` CLI, the server, and the test suites (`node:test` + vitest) — `engines.node` is authoritative and end users never need Bun. A **best-effort `bun:sqlite` compatibility path** exists so a global Bun install (`bun install -g omniroute`) can start without `better-sqlite3` (driver adapter + Bun-aware process spawning); it is **not** a supported runtime — no support guarantees — and every Bun-specific runtime change MUST preserve the Node driver/fallback chain and ship a Bun test (`test:bun:db`) or an explicit reason why the path is Node-only.
- **Bun (build/dev script runner + compatibility smoke only)**: Bun `1.4.2` is pinned as an **exact devDependency** (provisioned through the existing `npm ci` via the lockfile's `@oven/bun-*` platform binaries — no `setup-bun`/ad-hoc install). It is used **only** to execute a small, allow-listed set of TypeScript **gate/generator scripts** (replacing `node --import tsx` for startup speed): the CI checks `check:provider-consistency`, `check:compression-budget`, `check:known-symbols`, and the non-CI `gen:provider-reference`, `bench:compression` — plus the focused `test:bun:db` compatibility smoke suite for the best-effort `bun:sqlite` path. **Do NOT** widen Bun to `npm install`, the build (`build:cli*`), `check:pack-artifact`, the supported published runtime, or the main test runners — those stay on Node. Any new Bun-invoking gate/generator script must be validated byte-identical against its `node --import tsx` output first. After pulling the lockfile change, run `npm install` so `bun` resolves locally (a stale `node_modules` will fail those scripts with `bun: not found`).
+- **Bun (build/dev script runner + compatibility smoke only)**: Bun `1.4.0` is pinned as an **exact devDependency** (provisioned through the existing `npm ci` via the lockfile's `@oven/bun-*` platform binaries — no `setup-bun`/ad-hoc install). It is used **only** to execute a small, allow-listed set of TypeScript **gate/generator scripts** (replacing `node --import tsx` for startup speed): the CI checks `check:provider-consistency`, `check:compression-budget`, `check:known-symbols`, and the non-CI `gen:provider-reference`, `bench:compression` — plus the focused `test:bun:db` compatibility smoke suite for the best-effort `bun:sqlite` path. **Do NOT** widen Bun to `npm install`, the build (`build:cli*`), `check:pack-artifact`, the supported published runtime, or the main test runners — those stay on Node. Any new Bun-invoking gate/generator script must be validated byte-identical against its `node --import tsx` output first. After pulling the lockfile change, run `npm install` so `bun` resolves locally (a stale `node_modules` will fail those scripts with `bun: not found`).
 - **TypeScript**: 6.0+, target ES2022, module esnext, resolution bundler
 - **Path aliases**: `@/*` → `src/`, `@omniroute/open-sse` → `open-sse/`, `@omniroute/open-sse/*` → `open-sse/*`
 - **Default port**: 20128 (API + dashboard on same port)
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
--- a/34
+++ b/34
@@ -106,8 +106,7 @@ RUN test -f package-lock.json \
 RUN --mount=type=cache,id=s/92ca8a61-c1ba-421f-a389-d48ac7258c2d-npm-cache,target=/root/.npm \
  npm ci --include=optional --no-audit --no-fund --legacy-peer-deps --ignore-scripts \
  && (cd node_modules/better-sqlite3 \
-      && node /usr/local/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js rebuild --force_build=1) \
-  && test -f node_modules/better-sqlite3/build/Release/better_sqlite3.node \
+      && node /usr/local/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js rebuild) \
  && node -e "require('better-sqlite3')(':memory:').close()" \
  && node -e "const wreq=require('wreq-js'); if(typeof wreq.createTransport!=='function') process.exit(1)"

@@ -226,19 +225,7 @@ ENV NODE_OPTIONS="--max-old-space-size=${OMNIROUTE_MEMORY_MB}"

 # Data directory inside Docker — must match the volume mount in docker-compose.yml
 ENV DATA_DIR=/app/data
-RUN mkdir -p /app/data && chown node:node /app /app/data
-
-# #13679: default the PUBLISHED image to requiring an API key. A bare
-# `docker run -p 20128:20128 … diegosouzapw/omniroute` (README/QUICK-START
-# one-liners) does not pass `--env-file .env`, so without this default the
-# anonymous /v1 LLM proxy would be both keyless AND world-reachable on the
-# published container. This does NOT change the npm/CLI local-dev default
-# (`REQUIRE_API_KEY` stays `"false"` in featureFlagDefinitions.ts) — only the
-# shipped deployment artifact's posture. docker-compose.yml is unaffected: it
-# loads the operator's own `.env` (env_file:) which overrides this ENV, and
-# already binds loopback-only by default (#12568). Override with
-# `-e REQUIRE_API_KEY=false` for an intentionally keyless deployment.
-ENV REQUIRE_API_KEY=true
+RUN mkdir -p /app/data

 # `npm run build` (build-next-isolated → assembleStandalone) bundles ALL runtime
 # files into .build/next/standalone/ — .next, node_modules, migrations, scripts,
@@ -248,24 +235,23 @@ ENV REQUIRE_API_KEY=true
 # The old per-module overrides were therefore pure duplication and were removed
 # (build-output-isolation cleanup). See scripts/build/assembleStandalone.mjs
 # (EXTRA_MODULE_ENTRIES) for the single source of truth.
-COPY --chown=node:node --from=builder /app/.build/next/standalone ./
+COPY --from=builder /app/.build/next/standalone ./
 # better-sqlite3 is the one exception still copied explicitly: assembleStandalone
 # only syncs its native build/ dir; the JS wrapper (lib/, package.json) is left to
 # Next.js tracing. bootstrap-env requires SQLite BEFORE the standalone server
 # starts, so guarantee the complete package independent of trace behaviour.
-COPY --chown=node:node --from=builder /app/node_modules/better-sqlite3 ./node_modules/better-sqlite3
-RUN test -f /app/node_modules/better-sqlite3/build/Release/better_sqlite3.node
+COPY --from=builder /app/node_modules/better-sqlite3 ./node_modules/better-sqlite3
 # migrations land at <standalone>/migrations via assembleStandalone; point the runtime at them.
 ENV OMNIROUTE_MIGRATIONS_DIR=/app/migrations

 # Docker healthcheck script — not traced by Next.js standalone output, so copy
 # it explicitly. The HEALTHCHECK CMD references it as `node healthcheck.mjs`.
-COPY --chown=node:node --from=builder /app/scripts/dev/healthcheck.mjs ./healthcheck.mjs
+COPY --from=builder /app/scripts/dev/healthcheck.mjs ./healthcheck.mjs

-# Every COPY above hands its files to the baked-in `node` non-root user
-# (UID/GID 1000) at copy time. Do NOT add a `RUN chown -R node:node /app`
-# afterwards: in the overlay filesystem changing ownership rewrites every file
-# into a new layer, which stored the ~2 GB standalone build twice (#13990).
+# Hand /app over to the baked-in `node` non-root user (UID/GID 1000) so the
+# runtime process never holds root privileges. The chown happens after all
+# COPYs so it covers files originally owned by root in the builder stage.
+RUN chown -R node:node /app

 EXPOSE 20128

@@ -354,7 +340,7 @@ RUN --mount=type=cache,id=s/92ca8a61-c1ba-421f-a389-d48ac7258c2d-apt-cache,targe
 #      build, not the floating `@latest`.
 RUN --mount=type=cache,id=s/92ca8a61-c1ba-421f-a389-d48ac7258c2d-npm-cache,target=/root/.npm \
  npm install -g --no-audit --no-fund \
-    @openai/codex@0.153.4 \
+    @openai/codex@0.153.2 \
    @anthropic-ai/claude-code@2.1.260 \
    droid@0.212.0 \
    openclaw@2026.9.1
--- a/Dockerfile.bun
+++ b/Dockerfile.bun
@@ -1,5 +1,5 @@
 # ── Multi-stage Dockerfile for Native Bun Runtime (web-latest-bun) ───────────
-FROM oven/bun:1.4.2-slim AS base
+FROM oven/bun:1.4.0-slim AS base
 WORKDIR /app

 RUN apt-get update \
@@ -56,7 +56,7 @@ ENV NODE_ENV=production
 RUN bun run --quiet build

 # ── Runner Base stage (100% Bun Native Production Runtime) ──────────────────
-FROM oven/bun:1.4.2-slim AS runner-base
+FROM oven/bun:1.4.0-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)" \
--- a/README.md
+++ b/README.md
@@ -7,19 +7,19 @@

 # 🚀 OmniRoute — The Free AI Gateway

-<img src="./docs/diagrams/readme-hero.svg" width="100%" alt="OmniRoute — Never stop coding. Every AI tool → 359 providers — 150+ 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. 359 AI providers · 150+ free tiers · ~1.62B 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 → 356 providers — 150+ 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. 356 AI providers · 150+ free tiers · ~1.47B free tokens/mo · 19 routing strategies · $0 to start."/>

 </div>

 <div align="center">

-## 💰 ~1.62B Free Tokens / Month
+## 💰 ~1.47B Free Tokens / Month

 </div>

-> Stacking free tiers by hand is painful — dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute catalogs **489 free-tier entries across 35 recurring pool keys** and computes the token headline from the **17 pools with a published positive monthly budget plus five per-model Groq caps**, deduplicated by shared pool. Quotas that only open after a regional identity check (today: ModelScope) are shown apart, +~6M behind regional identity verification, and never summed into the headline. The result stays visible 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 **444 free-tier entries across 34 recurring pool keys** and computes the token headline from the **16 pools with a published positive monthly budget plus five per-model Groq caps**, deduplicated by shared pool. Quotas that only open after a regional identity check (today: ModelScope) are shown apart, +~6M behind regional identity verification, and never summed into the headline. 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: ~1.62B free tokens per month steady, up to ~2.22B in the first month with signup credits, from 35 documented recurring pool keys covering 489 cataloged free-tier entries behind one endpoint. Honest pool-deduped math — each shared pool counted once, including 17 recurring pools with a published positive monthly token budget plus five per-model Groq caps; 13 providers are marked avoid in the terms-risk catalog so you decide. Budget bar includes Mistral 1B, Nara 210M, LLM7 150M, xKiro 150M, Groq 30M (five per-model caps) 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."/>
+<img src="./docs/diagrams/free-tier-budget.svg" width="100%" alt="OmniRoute free-tier budget card: ~1.47B free tokens per month steady, up to ~2.10B in the first month with signup credits, from 34 documented recurring pool keys covering 444 cataloged free-tier entries behind one endpoint. Honest pool-deduped math — each shared pool counted once, including 16 recurring pools with a published positive monthly token budget plus five per-model Groq caps; 13 providers are marked avoid in the terms-risk catalog so you decide. Budget bar includes Mistral 1B, Nara 210M, LLM7 150M, Groq 30M (five per-model caps) 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)**.
 >
@@ -63,7 +63,7 @@

 |                           | v3.8.49 |        **v3.8.50**        | `v3.8.51+`  |
 | ------------------------- | :-----: | :-----------------------: | :---------: |
-| 🌐 Providers              |   290   |          **357**          | more queued |
+| 🌐 Providers              |   290   |          **352**          | more queued |
 | 🧠 Unique chat model IDs  |  1185   |         **1312**          |      —      |
 | 🖼️ Modality Bridge        |    —    | 🆕 vision + audio + video |      —      |
 | 📡 Radar free catalog     |    —    |         🆕 opt-in         |      —      |
@@ -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="#-357-ai-providers--152-catalog-marked-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>
@@ -133,7 +133,7 @@
 </div>

 <div align="center">
-  <b>🌐 In 66 languages</b>
+  <b>🌐 In 42 languages</b>
  <br/><br/>
  <a href="README.md"><img src="docs/assets/flags/us.svg" width="30" alt="English (en)" title="English (en)"></a>
  <a href="docs/i18n/pt-BR/README.md"><img src="docs/assets/flags/br.svg" width="30" alt="Português — Brasil (pt-BR)" title="Português — Brasil (pt-BR)"></a>
@@ -177,30 +177,6 @@
  <a href="docs/i18n/tr/README.md"><img src="docs/assets/flags/tr.svg" width="30" alt="Türkçe (tr)" title="Türkçe (tr)"></a>
  <a href="docs/i18n/az/README.md"><img src="docs/assets/flags/az.svg" width="30" alt="Azərbaycan (az)" title="Azərbaycan (az)"></a>
  <a href="docs/i18n/sw/README.md"><img src="docs/assets/flags/tz.svg" width="30" alt="Kiswahili (sw)" title="Kiswahili (sw)"></a>
-  <a href="docs/i18n/el/README.md"><img src="docs/assets/flags/gr.svg" width="30" alt="Ελληνικά (el)" title="Ελληνικά (el)"></a>
-  <a href="docs/i18n/hr/README.md"><img src="docs/assets/flags/hr.svg" width="30" alt="Hrvatski (hr)" title="Hrvatski (hr)"></a>
-  <a href="docs/i18n/sr/README.md"><img src="docs/assets/flags/rs.svg" width="30" alt="Српски (sr)" title="Српски (sr)"></a>
-  <a href="docs/i18n/lt/README.md"><img src="docs/assets/flags/lt.svg" width="30" alt="Lietuvių (lt)" title="Lietuvių (lt)"></a>
-  <a href="docs/i18n/et/README.md"><img src="docs/assets/flags/ee.svg" width="30" alt="Eesti (et)" title="Eesti (et)"></a>
-  <a href="docs/i18n/lv/README.md"><img src="docs/assets/flags/lv.svg" width="30" alt="Latviešu (lv)" title="Latviešu (lv)"></a>
-  <a href="docs/i18n/sl/README.md"><img src="docs/assets/flags/si.svg" width="30" alt="Slovenščina (sl)" title="Slovenščina (sl)"></a>
-  <a href="docs/i18n/mt/README.md"><img src="docs/assets/flags/mt.svg" width="30" alt="Malti (mt)" title="Malti (mt)"></a>
-  <a href="docs/i18n/ga/README.md"><img src="docs/assets/flags/ie.svg" width="30" alt="Gaeilge (ga)" title="Gaeilge (ga)"></a>
-  <a href="docs/i18n/kn/README.md"><img src="docs/assets/flags/in.svg" width="30" alt="ಕನ್ನಡ (kn)" title="ಕನ್ನಡ (kn)"></a>
-  <a href="docs/i18n/ml/README.md"><img src="docs/assets/flags/in.svg" width="30" alt="മലയാളം (ml)" title="മലയാളം (ml)"></a>
-  <a href="docs/i18n/or/README.md"><img src="docs/assets/flags/in.svg" width="30" alt="ଓଡ଼ିଆ (or)" title="ଓଡ଼ିଆ (or)"></a>
-  <a href="docs/i18n/pa/README.md"><img src="docs/assets/flags/in.svg" width="30" alt="ਪੰਜਾਬੀ (pa)" title="ਪੰਜਾਬੀ (pa)"></a>
-  <a href="docs/i18n/ne/README.md"><img src="docs/assets/flags/np.svg" width="30" alt="नेपाली (ne)" title="नेपाली (ne)"></a>
-  <a href="docs/i18n/si/README.md"><img src="docs/assets/flags/lk.svg" width="30" alt="සිංහල (si)" title="සිංහල (si)"></a>
-  <a href="docs/i18n/my/README.md"><img src="docs/assets/flags/mm.svg" width="30" alt="မြန်မာ (my)" title="မြန်မာ (my)"></a>
-  <a href="docs/i18n/km/README.md"><img src="docs/assets/flags/kh.svg" width="30" alt="ខ្មែរ (km)" title="ខ្មែរ (km)"></a>
-  <a href="docs/i18n/ha/README.md"><img src="docs/assets/flags/ng.svg" width="30" alt="Hausa (ha)" title="Hausa (ha)"></a>
-  <a href="docs/i18n/yo/README.md"><img src="docs/assets/flags/ng.svg" width="30" alt="Yorùbá (yo)" title="Yorùbá (yo)"></a>
-  <a href="docs/i18n/ig/README.md"><img src="docs/assets/flags/ng.svg" width="30" alt="Igbo (ig)" title="Igbo (ig)"></a>
-  <a href="docs/i18n/am/README.md"><img src="docs/assets/flags/et.svg" width="30" alt="አማርኛ (am)" title="አማርኛ (am)"></a>
-  <a href="docs/i18n/uz/README.md"><img src="docs/assets/flags/uz.svg" width="30" alt="Oʻzbekcha (uz)" title="Oʻzbekcha (uz)"></a>
-  <a href="docs/i18n/ka/README.md"><img src="docs/assets/flags/ge.svg" width="30" alt="ქართული (ka)" title="ქართული (ka)"></a>
-  <a href="docs/i18n/hy/README.md"><img src="docs/assets/flags/am.svg" width="30" alt="Հայերեն (hy)" title="Հայերեն (hy)"></a>
 </div>

 <br/>
@@ -233,7 +209,7 @@ curl http://localhost:20128/v1/chat/completions \

 </div>

-<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint and 359 providers. Automatic fallback keeps routing while another healthy target is available. Six pillars: resilient fallback across 359 providers · up to 95% token savings on eligible workloads · $0 to start with 150+ free tiers and 54 recurring/keyless free-forever providers · 36 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."/>
+<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint and 356 providers. Automatic fallback keeps routing while another healthy target is available. Six pillars: resilient fallback across 356 providers · up to 95% token savings on eligible workloads · $0 to start with 150+ free tiers and 52 recurring/keyless free-forever providers · 36 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/>
@@ -486,7 +462,7 @@ All **19** strategies — mix & match per combo step:

 </div>

-<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: 359 providers, 150+ 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 42 i18n UI locales. OmniRoute is MIT-licensed and self-hostable. Competitor capabilities and counts may change; see the linked methodology."/>
+<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: 356 providers, 150+ 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 42 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>

@@ -542,9 +518,9 @@ Pix copia-e-cola:

 ## 📡 OmniRoute Radar

-The main free-tier headline remains **~1.62B tokens/month** from the documented,
+The main free-tier headline remains **~1.47B tokens/month** from the documented,
 pool-deduplicated catalog above. Temporary provider signup credits can separately lift the first
-month to **~2.22B**. Radar is an optional, signed catalog overlay for people who want fresher
+month to **~2.10B**. 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.

@@ -629,13 +605,13 @@ the current catalog at **[radar.omniroute.online/planos](https://radar.omniroute
    <td align="center" width="76"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/goose.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/goose.svg" width="40" alt="Goose"/></picture><br/><sub><b>Goose</b></sub><br/><sub>                           </sub></td>
    <td align="center" width="76"><img src="./public/providers/cli-generic.svg" width="40" alt="Open Interpreter"/><br/><sub><b>Open Interpreter</b></sub><br/><sub>                           </sub></td>
    <td align="center" width="76"><img src="./public/providers/cli-generic.svg" width="40" alt="Warp AI"/><br/><sub><b>Warp AI</b></sub><br/><sub>                           </sub></td>
-    <td align="center" width="76"><a href="https://deyin.ai"><img src="./public/deyin.svg" width="40" alt="deyin.ai"/><br/><sub><b>deyin.ai</b></sub><br/><sub>                           </sub></a></td>
+    <td align="center" width="76"><img src="./public/providers/cli-generic.svg" width="40" alt="Agent Deck"/><br/><sub><b>Agent Deck</b></sub><br/><sub>                           </sub></td>
  </tr>
 </table>
 </div>

 <div align="center">
-<b>＋ also works with</b> · Agent Deck · Kiro · Command Code · Antigravity · Windsurf · AMP · <b>any OpenAI-compatible tool</b>
+<b>＋ also works with</b> · Kiro · Command Code · Antigravity · Windsurf · AMP · <b>any OpenAI-compatible tool</b>
 </div>

 <sub>📖 Per-tool setup for all 36 tools (26 CLI Code's + 10 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>
@@ -668,11 +644,11 @@ of your shell history. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)

 <div align="center">

-## 🌐 357 AI Providers — 152 Catalog-Marked Free
+## 🌐 352 AI Providers — 152 Catalog-Marked Free

 </div>

-> **357 registered providers** across the canonical chat, media, search, local, cloud-agent and system collections, including **152 carrying `hasFree: true` discovery metadata**. The chat model registry covers **229 providers / 2,554 distinct provider-model pairs / 1,283 raw model IDs**; the separate free-budget catalog has **491 per-model rows**, **35 recurring pools** and **54 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).
+> **352 registered providers** across the canonical chat, media, search, local, cloud-agent and system collections, including **152 carrying `hasFree: true` discovery metadata**. The chat model registry covers **229 providers / 2,554 distinct provider-model pairs / 1,283 raw model IDs**; the separate free-budget catalog has **444 per-model rows**, **34 recurring pools** and **52 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">

@@ -1268,7 +1244,7 @@ Métricas canônicas em 2026-08-24: **1.029 vídeos únicos** · **11.132.922 vi
  <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) — 122 domain modules, 178 migrations</td></tr>
+  <tr><td nowrap><b>Database</b></td><td>better-sqlite3 (SQLite, WAL journaling) + LowDB (JSON legacy) — 122 domain modules, 169 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>
@@ -1331,7 +1307,7 @@ Métricas canônicas em 2026-08-24: **1.029 vídeos únicos** · **11.132.922 vi
  <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>16-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>Consolidated directory: 35 documented recurring pools / 489 cataloged free-tier entries</td></tr>
+  <tr><td nowrap><b><a href="docs/reference/FREE_TIERS.md">Free Tiers</a></b></td><td>Consolidated directory: 34 documented recurring pools / 444 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>
--- a/SECURITY.md
+++ b/SECURITY.md
@@ -218,8 +218,6 @@ These rules are enforced by tooling and reviewers:

 ## Supply-chain scanner findings (Socket.dev / Snyk / similar)

-> **Scope note:** `socket.yml` at the repository root only shapes `projectIgnorePaths` for Socket.dev's registry-side post-publish scan of the published npm artifact — it is not an enforced CI/PR merge gate. No workflow in `.github/workflows`, no `package.json` script, and no `Makefile` target invokes Socket.dev.
-
 The published `omniroute` npm artifact bundles the Next.js `output: "standalone"`
 build, which means every route handler — including documented privileged
 features (MITM, Zed import, Cloud Sync, embedded service supervisor) — ends
--- a/bin/antigravity-bridge.mjs
+++ b/bin/antigravity-bridge.mjs
@@ -1,582 +0,0 @@
-#!/usr/bin/env node
-/**
- * OmniRoute Antigravity Bridge Proxy
- *
- * Intercepts Antigravity CLI and IDE requests:
- * - Directs Gemini 3.8 models directly to Google backend (100% native, untouched).
- * - Directs other models (Claude Sonnet 4.5/4.6, Opus, Gemini 3.7, GPT-OSS, etc.) to OmniRoute /v1/antigravity.
- * - Passes all non-model Google requests (auth, onboarding, telemetry) directly to Google backend.
- * - Transparently forwards all other non-target internet traffic.
- */
-
-import net from "node:net";
-import http from "node:http";
-import https from "node:https";
-import tls from "node:tls";
-import fs from "node:fs";
-import path from "node:path";
-import { fileURLToPath } from "node:url";
-
-const PORT = parseInt(process.env.BRIDGE_PORT || "20129", 10);
-const ROUTER_URL = process.env.ROUTER_URL || "http://127.0.0.1:20128/v1/antigravity";
-const ROUTER_API_KEY =
-  process.env.ROUTER_API_KEY || process.env.OMNIROUTE_API_KEY || "sk-omniroute-bridge-local";
-
-// Connection pool agents with TCP keep-alive
-const httpAgent = new http.Agent({
-  keepAlive: true,
-  keepAliveMsecs: 60000,
-  maxSockets: 64,
-  maxFreeSockets: 16,
-  timeout: 120000,
-});
-
-const httpsAgent = new https.Agent({
-  keepAlive: true,
-  keepAliveMsecs: 60000,
-  maxSockets: 64,
-  maxFreeSockets: 16,
-  timeout: 120000,
-});
-
-let cachedSslOptions = null;
-function getSslOptions() {
-  if (cachedSslOptions) return cachedSslOptions;
-  const certDir =
-    process.env.CERT_DIR || path.join(process.env.HOME || process.cwd(), ".omniroute", "mitm");
-  const serverKey = path.join(certDir, "server.key");
-  const serverCrt = path.join(certDir, "server.crt");
-
-  if (!fs.existsSync(serverKey) || !fs.existsSync(serverCrt)) {
-    console.error("❌ Certificate files not found in", certDir);
-    process.exit(1);
-  }
-
-  cachedSslOptions = {
-    key: fs.readFileSync(serverKey),
-    cert: fs.readFileSync(serverCrt),
-  };
-  return cachedSslOptions;
-}
-
-const TARGET_HOSTS = new Set([
-  "cloudcode-pa.googleapis.com",
-  "daily-cloudcode-pa.googleapis.com",
-  "daily-cloudcode-pa.sandbox.googleapis.com",
-  "autopush-cloudcode-pa.sandbox.googleapis.com",
-  "preprod-daily-cloudcode-pa.sandbox.googleapis.com",
-  "antigravity-unleash.goog",
-]);
-
-function isGenerationRequest(url) {
-  if (!url) return false;
-  return (
-    url.includes(":generateContent") ||
-    url.includes(":streamGenerateContent") ||
-    url.includes("/GenerateChat") ||
-    url.includes("/StreamGenerateChat") ||
-    url.includes("/GenerateCode") ||
-    url.includes("/CompleteCode")
-  );
-}
-
-function extractModel(body, url) {
-  if (body && typeof body === "object") {
-    if (typeof body.model === "string" && body.model) return body.model;
-    if (body.request && typeof body.request.model === "string" && body.request.model) {
-      return body.request.model;
-    }
-  }
-  if (url) {
-    try {
-      const parsed = new URL(url, "https://cloudcode-pa.googleapis.com");
-      const m = parsed.searchParams.get("model");
-      if (m) return m;
-    } catch {}
-  }
-  return null;
-}
-
-const MODEL_ROUTING_MAP = {
-  // Official OmniRoute Auto Groups
-  "auto/best-fast": "groq/openai/gpt-oss-120b",
-  "auto/best-coding": "mistral/codestral-latest",
-  "auto/best-reasoning": "nvidia/nvidia/nemotron-3-super-120b-a12b",
-  "auto/best-free": "groq/qwen/qwen3.8-27b",
-  "auto/best-vision": "nvidia/meta/llama-3.2-90b-vision-instruct",
-  "auto/coding:pro": "mistral/codestral-latest",
-  "auto/coding:fast": "groq/openai/gpt-oss-120b",
-  "auto/coding:free": "groq/qwen/qwen3.8-27b",
-  "auto/coding:reliable": "mistral/codestral-latest",
-  "auto/reasoning:pro": "nvidia/nvidia/nemotron-3-super-120b-a12b",
-  "auto/smart": "nvidia/nvidia/nemotron-3-super-120b-a12b",
-  "auto/claude-sonnet": "mistral/codestral-latest",
-  "auto/claude-opus": "nvidia/nvidia/nemotron-3-super-120b-a12b",
-  "auto/gemini": "gemini/gemini-2.5-flash",
-  "auto/llama": "groq/openai/gpt-oss-120b",
-  "auto/gemma": "groq/qwen/qwen3.8-27b",
-
-  // Human-readable Display Names (in case CLI sends displayName in envelope)
-  "Auto: Best Fast (OmniRoute)": "groq/openai/gpt-oss-120b",
-  "Auto: Best Coding (OmniRoute)": "mistral/codestral-latest",
-  "Auto: Best Reasoning (OmniRoute)": "nvidia/nvidia/nemotron-3-super-120b-a12b",
-  "Auto: Best Free (OmniRoute)": "groq/qwen/qwen3.8-27b",
-  "Auto: Best Vision (OmniRoute)": "nvidia/meta/llama-3.2-90b-vision-instruct",
-  "Auto: Coding Pro (OmniRoute)": "mistral/codestral-latest",
-  "Auto: Coding Fast (OmniRoute)": "groq/openai/gpt-oss-120b",
-  "Auto: Coding Free (OmniRoute)": "groq/qwen/qwen3.8-27b",
-  "Auto: Coding Reliable (OmniRoute)": "mistral/codestral-latest",
-  "Auto: Reasoning Pro (OmniRoute)": "nvidia/nvidia/nemotron-3-super-120b-a12b",
-  "Auto: Smart (OmniRoute)": "nvidia/nvidia/nemotron-3-super-120b-a12b",
-  "Auto: Claude Sonnet (OmniRoute)": "mistral/codestral-latest",
-  "Auto: Claude Opus (OmniRoute)": "nvidia/nvidia/nemotron-3-super-120b-a12b",
-  "Auto: Gemini (OmniRoute)": "gemini/gemini-2.5-flash",
-  "Auto: Llama (OmniRoute)": "groq/openai/gpt-oss-120b",
-  "Auto: Gemma (OmniRoute)": "groq/qwen/qwen3.8-27b",
-
-  // Fail-safe self-healing for dead/retired models
-  "nvidia/deepseek-ai/deepseek-v4-pro-0813": "groq/openai/gpt-oss-120b",
-  "deepseek-ai/deepseek-v4-pro-0813": "groq/openai/gpt-oss-120b",
-  "NVIDIA: DeepSeek V4 Pro": "groq/openai/gpt-oss-120b",
-  "nvidia/openai/gpt-oss-120b": "groq/openai/gpt-oss-120b",
-  "openai/gpt-oss-120b": "groq/openai/gpt-oss-120b",
-  "groq/llama-3.3-70b-versatile": "groq/openai/gpt-oss-120b",
-  "llama-3.3-70b-versatile": "groq/openai/gpt-oss-120b",
-};
-
-function resolveTargetModel(model) {
-  if (!model) return "groq/openai/gpt-oss-120b";
-  if (MODEL_ROUTING_MAP[model]) return MODEL_ROUTING_MAP[model];
-  const clean = model.replace(/^models\//, "").trim();
-  if (MODEL_ROUTING_MAP[clean]) return MODEL_ROUTING_MAP[clean];
-  for (const [k, v] of Object.entries(MODEL_ROUTING_MAP)) {
-    if (k.toLowerCase() === model.toLowerCase() || k.toLowerCase() === clean.toLowerCase()) {
-      return v;
-    }
-  }
-  if (
-    clean.includes("deepseek-v4-pro") ||
-    (clean.startsWith("nvidia") && clean.includes("gpt-oss-120b")) ||
-    clean.includes("llama-3.3-70b-versatile")
-  ) {
-    return "groq/openai/gpt-oss-120b";
-  }
-  return clean;
-}
-
-const OMNIROUTE_BUILTIN_GROUPS = [
-  {
-    id: "auto/best-coding",
-    displayName: "Auto: Best Coding (OmniRoute)",
-    descriptionText:
-      "OmniRoute dynamic routing to the highest benchmark coding model available (Mistral Codestral)",
-  },
-  {
-    id: "auto/best-reasoning",
-    displayName: "Auto: Best Reasoning (OmniRoute)",
-    descriptionText:
-      "OmniRoute dynamic routing to the highest benchmark reasoning model available (Nemotron 3 Super 120B)",
-  },
-  {
-    id: "auto/best-fast",
-    displayName: "Auto: Best Fast (OmniRoute)",
-    descriptionText: "OmniRoute sub-second lowest latency high-throughput model (Groq LPUs)",
-  },
-  {
-    id: "auto/best-vision",
-    displayName: "Auto: Best Vision (OmniRoute)",
-    descriptionText: "OmniRoute multimodal & computer vision routing",
-  },
-  {
-    id: "auto/best-free",
-    displayName: "Auto: Best Free (OmniRoute)",
-    descriptionText: "OmniRoute 100% unmetered free tier model routing (Qwen 3.8 27B)",
-  },
-  {
-    id: "auto/coding:pro",
-    displayName: "Auto: Coding Pro (OmniRoute)",
-    descriptionText: "OmniRoute frontier pro-tier coding model (Codestral)",
-  },
-  {
-    id: "auto/coding:fast",
-    displayName: "Auto: Coding Fast (OmniRoute)",
-    descriptionText: "OmniRoute fast sub-second daily coding model (Groq 120B)",
-  },
-  {
-    id: "auto/coding:free",
-    displayName: "Auto: Coding Free (OmniRoute)",
-    descriptionText: "OmniRoute zero-cost free coding model",
-  },
-  {
-    id: "auto/coding:reliable",
-    displayName: "Auto: Coding Reliable (OmniRoute)",
-    descriptionText: "OmniRoute maximum uptime and reliability coding model",
-  },
-  {
-    id: "auto/reasoning:pro",
-    displayName: "Auto: Reasoning Pro (OmniRoute)",
-    descriptionText: "OmniRoute deep reasoning frontier model",
-  },
-  {
-    id: "auto/smart",
-    displayName: "Auto: Smart (OmniRoute)",
-    descriptionText: "OmniRoute highest intelligence general-purpose model",
-  },
-  {
-    id: "auto/claude-sonnet",
-    displayName: "Auto: Claude Sonnet (OmniRoute)",
-    descriptionText: "OmniRoute automated routing across Claude Sonnet providers",
-  },
-  {
-    id: "auto/claude-opus",
-    displayName: "Auto: Claude Opus (OmniRoute)",
-    descriptionText: "OmniRoute automated routing across Claude Opus providers",
-  },
-  {
-    id: "auto/gemini",
-    displayName: "Auto: Gemini (OmniRoute)",
-    descriptionText: "OmniRoute automated routing across Gemini providers",
-  },
-  {
-    id: "auto/llama",
-    displayName: "Auto: Llama (OmniRoute)",
-    descriptionText: "OmniRoute automated routing across Llama providers",
-  },
-  {
-    id: "auto/gemma",
-    displayName: "Auto: Gemma (OmniRoute)",
-    descriptionText: "OmniRoute automated routing across Gemma providers",
-  },
-  // Active, verified provider models
-  {
-    id: "groq/openai/gpt-oss-120b",
-    displayName: "Groq: GPT-OSS 120B (Ultra-Fast 0.02s)",
-    descriptionText: "Ultra-fast inference on Groq LPUs at sub-second speeds",
-  },
-  {
-    id: "groq/qwen/qwen3.8-27b",
-    displayName: "Groq: Qwen 3.8 27B",
-    descriptionText: "High-speed Qwen 3.8 27B model on Groq",
-  },
-  {
-    id: "mistral/codestral-latest",
-    displayName: "Mistral: Codestral Latest",
-    descriptionText: "Mistral flagship frontier code reasoning model",
-  },
-  {
-    id: "nvidia/nvidia/nemotron-3-super-120b-a12b",
-    displayName: "NVIDIA: Nemotron 3 Super 120B",
-    descriptionText: "Nemotron 3 Super 120B Deep Reasoning model on NVIDIA NIM",
-  },
-  {
-    id: "gemini/gemini-2.5-flash",
-    displayName: "Gemini: Gemini 2.5 Flash (AI Studio)",
-    descriptionText: "Google AI Studio direct Gemini 2.5 Flash route",
-  },
-  {
-    id: "gemini/gemini-2.5-pro",
-    displayName: "Gemini: Gemini 2.5 Pro (AI Studio)",
-    descriptionText: "Google AI Studio direct Gemini 2.5 Pro route",
-  },
-];
-
-const OMNIROUTE_CUSTOM_MODELS = new Set([
-  ...OMNIROUTE_BUILTIN_GROUPS.map((g) => g.id),
-  ...Object.keys(MODEL_ROUTING_MAP),
-]);
-
-function shouldInterceptToOmniRoute(model, url) {
-  if (!model) return false;
-
-  // Never intercept non-streaming unary RPCs (Antigravity expects raw JSON/Protobuf, not SSE)
-  const isStreaming =
-    url.includes("streamGenerateContent") ||
-    url.includes("StreamGenerateChat") ||
-    url.includes("alt=sse");
-  if (!isStreaming) return false;
-
-  // Never intercept native Google/Gemini models (used by Antigravity core, subagents, websearch, grounding)
-  if (model.startsWith("gemini-") || model.startsWith("models/gemini-")) {
-    return false;
-  }
-
-  // Never intercept native Google CloudCode PA hosted models
-  if (
-    model === "claude-sonnet-4-6" ||
-    model === "claude-opus-4-6" ||
-    model === "gpt-oss-120b-medium"
-  ) {
-    return false;
-  }
-
-  // Intercept any OmniRoute auto group, provider model, or mapped alias
-  const clean = model.replace(/^models\//, "").trim();
-  if (
-    clean.startsWith("auto/") ||
-    clean.toLowerCase().includes("omniroute") ||
-    clean.includes("/") ||
-    OMNIROUTE_CUSTOM_MODELS.has(model) ||
-    OMNIROUTE_CUSTOM_MODELS.has(clean) ||
-    Boolean(MODEL_ROUTING_MAP[model]) ||
-    Boolean(MODEL_ROUTING_MAP[clean])
-  ) {
-    return true;
-  }
-
-  return false;
-}
-
-const internalApp = http.createServer(async (req, res) => {
-  const host = (req.headers.host || "cloudcode-pa.googleapis.com").split(":")[0];
-  const url = req.url || "/";
-
-  // Collect request body
-  const chunks = [];
-  for await (const chunk of req) {
-    chunks.push(chunk);
-  }
-  const bodyBuffer = Buffer.concat(chunks);
-
-  let bodyJson = null;
-  if (bodyBuffer.length > 0) {
-    try {
-      bodyJson = JSON.parse(bodyBuffer.toString("utf-8"));
-    } catch {}
-  }
-
-  const model = extractModel(bodyJson, url);
-  const shouldIntercept = shouldInterceptToOmniRoute(model, url);
-
-  if (shouldIntercept) {
-    const resolvedModel = resolveTargetModel(model);
-    console.log(
-      `[Bridge] 🔀 INTERCEPTING -> OmniRoute: "${model || "default"}" => "${resolvedModel}" (${url})`
-    );
-
-    let outgoingBuffer = bodyBuffer;
-    if (bodyJson) {
-      const cloned = JSON.parse(JSON.stringify(bodyJson));
-      cloned.model = resolvedModel;
-      if (cloned.request && typeof cloned.request === "object") {
-        cloned.request.model = resolvedModel;
-      }
-      outgoingBuffer = Buffer.from(JSON.stringify(cloned), "utf-8");
-    }
-
-    // Forward to OmniRoute /v1/antigravity
-    try {
-      const forwardHeaders = {
-        "Content-Type": "application/json",
-        "Content-Length": Buffer.byteLength(outgoingBuffer),
-        Authorization: `Bearer ${ROUTER_API_KEY}`,
-        "x-omniroute-source": "agent-bridge",
-        "x-omniroute-agent": "antigravity",
-        "x-omniroute-skip-usage": "true", // Skip usage tracking for default models
-      };
-
-      const upstreamReq = http.request(
-        ROUTER_URL,
-        {
-          method: "POST",
-          headers: forwardHeaders,
-          agent: httpAgent,
-        },
-        (upstreamRes) => {
-          res.writeHead(upstreamRes.statusCode || 200, upstreamRes.headers);
-          upstreamRes.pipe(res);
-        }
-      );
-      upstreamReq.setNoDelay(true);
-
-      upstreamReq.on("error", (err) => {
-        console.error(`[Bridge] ❌ Error forwarding to OmniRoute: ${err.message}`);
-        if (!res.headersSent) {
-          res.writeHead(502, { "Content-Type": "application/json" });
-          res.end(JSON.stringify({ error: { message: `OmniRoute bridge error: ${err.message}` } }));
-        }
-      });
-
-      upstreamReq.write(outgoingBuffer);
-      upstreamReq.end();
-      return;
-    } catch (err) {
-      console.error(`[Bridge] ❌ Failed to invoke OmniRoute: ${err.message}`);
-    }
-  }
-
-  // Otherwise: Passthrough directly to Google upstream
-  console.log(`[Bridge] ⏩ PASSTHROUGH -> Google: ${model || "non-model"} (${url})`);
-
-  const upstreamHeaders = { ...req.headers };
-  delete upstreamHeaders["host"]; // Let https.request set the correct Host
-  upstreamHeaders["host"] = host;
-
-  if (url.includes("fetchAvailableModels")) {
-    delete upstreamHeaders["accept-encoding"];
-  }
-
-  const googleReq = https.request(
-    {
-      hostname: host,
-      port: 443,
-      path: url,
-      method: req.method,
-      headers: upstreamHeaders,
-      agent: httpsAgent,
-    },
-    (googleRes) => {
-      if (url.includes("fetchAvailableModels")) {
-        const respChunks = [];
-        googleRes.on("data", (chunk) => respChunks.push(chunk));
-        googleRes.on("end", () => {
-          const respBuffer = Buffer.concat(respChunks);
-          let finalBuffer = respBuffer;
-          try {
-            const data = JSON.parse(respBuffer.toString("utf-8"));
-            if (data && data.models) {
-              // Inject OmniRoute built-in auto groups and models
-              const baseTemplate =
-                data.models["claude-sonnet-4-6"] ||
-                data.models["gpt-oss-120b-medium"] ||
-                Object.values(data.models)[0] ||
-                {};
-
-              const injectedIds = [];
-              for (const group of OMNIROUTE_BUILTIN_GROUPS) {
-                data.models[group.id] = {
-                  ...baseTemplate,
-                  id: group.id,
-                  name: group.id,
-                  displayName: group.displayName,
-                  descriptionText: group.descriptionText,
-                };
-                injectedIds.push(group.id);
-              }
-
-              // Prepend OmniRoute groups to agentModelSorts recommended group
-              if (
-                Array.isArray(data.agentModelSorts) &&
-                data.agentModelSorts[0]?.groups?.[0]?.modelIds
-              ) {
-                const existing = data.agentModelSorts[0].groups[0].modelIds;
-                data.agentModelSorts[0].groups[0].modelIds = [
-                  ...injectedIds,
-                  ...existing.filter((id) => !injectedIds.includes(id)),
-                ];
-              }
-              finalBuffer = Buffer.from(JSON.stringify(data), "utf-8");
-              console.log(
-                `[Bridge] 🌟 Injected custom models into fetchAvailableModels (${finalBuffer.length} bytes)`
-              );
-            }
-          } catch (err) {
-            console.error(`[Bridge] ⚠️ Error modifying fetchAvailableModels: ${err.message}`);
-          }
-
-          const headers = { ...googleRes.headers };
-          delete headers["content-length"];
-          delete headers["content-encoding"];
-          headers["content-length"] = String(finalBuffer.length);
-          res.writeHead(googleRes.statusCode || 200, headers);
-          res.end(finalBuffer);
-        });
-        return;
-      }
-
-      res.writeHead(googleRes.statusCode || 200, googleRes.headers);
-      googleRes.pipe(res);
-    }
-  );
-  googleReq.setNoDelay(true);
-
-  googleReq.on("error", (err) => {
-    console.error(`[Bridge] ❌ Google upstream error: ${err.message}`);
-    if (!res.headersSent) {
-      res.writeHead(502, { "Content-Type": "application/json" });
-      res.end(JSON.stringify({ error: { message: `Google upstream error: ${err.message}` } }));
-    }
-  });
-
-  if (bodyBuffer.length > 0) {
-    googleReq.write(bodyBuffer);
-  }
-  googleReq.end();
-});
-
-internalApp.keepAliveTimeout = 65000;
-internalApp.headersTimeout = 66000;
-
-// Proxy server listening on HTTP port
-const proxyServer = http.createServer((req, res) => {
-  // Plain HTTP request (non-CONNECT)
-  res.writeHead(200, { "Content-Type": "text/plain" });
-  res.end("OmniRoute Antigravity Bridge Proxy Active\n");
-});
-
-proxyServer.keepAliveTimeout = 65000;
-proxyServer.headersTimeout = 66000;
-
-proxyServer.on("connect", (req, clientSocket, head) => {
-  clientSocket.setNoDelay(true);
-  const [targetHost, targetPortStr] = (req.url || "").split(":");
-  const targetPort = parseInt(targetPortStr || "443", 10);
-
-  if (TARGET_HOSTS.has(targetHost)) {
-    // Target host: Terminate TLS locally and route via internalApp
-    clientSocket.write("HTTP/1.1 200 Connection Established\r\n\r\n");
-
-    const ssl = getSslOptions();
-    const tlsSocket = new tls.TLSSocket(clientSocket, {
-      isServer: true,
-      key: ssl.key,
-      cert: ssl.cert,
-    });
-    tlsSocket.setNoDelay(true);
-
-    tlsSocket.on("error", (err) => {
-      // Client closed or TLS error
-      clientSocket.destroy();
-    });
-
-    internalApp.emit("connection", tlsSocket);
-  } else {
-    // Non-target host: Transparent raw TCP tunnel
-    const upstreamSocket = net.connect(targetPort, targetHost, () => {
-      upstreamSocket.setNoDelay(true);
-      clientSocket.write("HTTP/1.1 200 Connection Established\r\n\r\n");
-      if (head && head.length > 0) {
-        upstreamSocket.write(head);
-      }
-      upstreamSocket.pipe(clientSocket);
-      clientSocket.pipe(upstreamSocket);
-    });
-
-    const cleanup = () => {
-      clientSocket.destroy();
-      upstreamSocket.destroy();
-    };
-
-    upstreamSocket.on("error", cleanup);
-    clientSocket.on("error", cleanup);
-  }
-});
-
-export {
-  resolveTargetModel,
-  MODEL_ROUTING_MAP,
-  shouldInterceptToOmniRoute,
-  extractModel,
-  OMNIROUTE_BUILTIN_GROUPS,
-  proxyServer,
-  internalApp,
-};
-
-const isMain = process.argv[1] && path.resolve(process.argv[1]) === fileURLToPath(import.meta.url);
-
-if (isMain) {
-  proxyServer.listen(PORT, "127.0.0.1", () => {
-    console.log(`🚀 OmniRoute Antigravity Bridge listening on 127.0.0.1:${PORT}`);
-    console.log(`   Routing non-Gemini 3.8 model traffic -> ${ROUTER_URL}`);
-    console.log(`   Preserving Gemini 3.8 native traffic -> Google`);
-  });
-}
--- a/bin/cli/commands/chat.mjs
+++ b/bin/cli/commands/chat.mjs
@@ -79,8 +79,7 @@ export async function runChatCommand(promptArg, opts, cmd) {
  const data = await response.json();
  const text = extractText(data, opts.responsesApi);

-  // Commander stores `--no-history` as `history === false`, never as `noHistory`.
-  if (opts.history !== false && opts.noHistory !== true) {
+  if (!opts.noHistory) {
    appendHistory({ prompt, model: opts.model, latencyMs, usage: data.usage, response: text });
  }

--- a/bin/cli/commands/contexts.mjs
+++ b/bin/cli/commands/contexts.mjs
@@ -248,9 +248,7 @@ export function registerContexts(program) {
    .option("--no-secrets", "Omit API keys from export")
    .action(async (opts, cmd) => {
      const cfg = loadContexts();
-      // Commander stores `--no-secrets` as `secrets === false`, never as `noSecrets`.
-      const redact = opts.secrets === false || opts.noSecrets === true;
-      const out = redact ? redactContextSecrets(cfg) : JSON.parse(JSON.stringify(cfg));
+      const out = opts.noSecrets ? redactContextSecrets(cfg) : JSON.parse(JSON.stringify(cfg));
      const json = JSON.stringify(out, null, 2);
      if (opts.out) {
        const { writeFileSync } = await import("node:fs");
--- a/bin/cli/commands/doctor.mjs
+++ b/bin/cli/commands/doctor.mjs
@@ -10,7 +10,6 @@ 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";
-import { getCrashLogPath } from "../runtime/processSupervisor.mjs";

 const STATIC_SALT = "omniroute-field-encryption-v1";
 const KEY_LENGTH = 32;
@@ -381,33 +380,6 @@ function checkMemory() {
  });
 }

-// #13538: surfaces the supervisor's give-up crash record (persisted by
-// ServerSupervisor.persistCrashLog(), bin/cli/runtime/processSupervisor.mjs)
-// so a user whose `--tray` worker died silently (detached, stdio:"ignore")
-// has something concrete `doctor` can point at without needing `--log`.
-function checkCrashLog() {
-  const crashLogPath = getCrashLogPath();
-  if (!fs.existsSync(crashLogPath)) {
-    return ok("Crash log", "No supervisor crash record found", { crashLogPath });
-  }
-
-  try {
-    const stat = fs.statSync(crashLogPath);
-    const contents = fs.readFileSync(crashLogPath, "utf8");
-    const lastEntry = contents.split("\n").filter(Boolean).slice(-6).join("\n");
-    return warn(
-      "Crash log",
-      `Supervisor recorded a give-up crash at ${crashLogPath} (last modified ${stat.mtime.toISOString()})`,
-      { crashLogPath, modifiedAt: stat.mtime.toISOString(), tail: lastEntry }
-    );
-  } catch (error) {
-    return warn("Crash log", `Crash record exists at ${crashLogPath} but could not be read`, {
-      crashLogPath,
-      error: error instanceof Error ? error.message : String(error),
-    });
-  }
-}
-
 async function fetchWithTimeout(url, options = {}) {
  const controller = new AbortController();
  const timeout = setTimeout(() => controller.abort(), CHECK_TIMEOUT_MS);
@@ -607,7 +579,6 @@ export async function collectDoctorChecks(context = {}, options = {}) {
  checks.push(await checkNodeRuntime(rootDir));
  checks.push(await checkNativeBinary(rootDir));
  checks.push(checkMemory());
-  checks.push(checkCrashLog());

  if (!options.skipLiveness) {
    checks.push(await checkServerLiveness(options));
--- a/bin/cli/commands/env.mjs
+++ b/bin/cli/commands/env.mjs
@@ -13,7 +13,6 @@ const OMNIROUTE_ENV_VARS = [
  "OMNIROUTE_API_KEY",
  "OMNIROUTE_BASE_URL",
  "OMNIROUTE_HTTP_TIMEOUT_MS",
-  "OMNIROUTE_READY_TIMEOUT_MS",
 ];

 const ENV_DEFAULTS = {
--- a/bin/cli/commands/keys.mjs
+++ b/bin/cli/commands/keys.mjs
@@ -352,24 +352,10 @@ export async function runKeysRegenerateCommand(id, opts = {}) {
    return 1;
  }
  try {
-    const encodedId = encodeURIComponent(id);
-    let res = await apiFetch(`/api/v1/registered-keys/${encodedId}/regenerate`, {
+    const res = await apiFetch(`/api/v1/registered-keys/${encodeURIComponent(id)}/regenerate`, {
      method: "POST",
      retry: false,
-      acceptNotOk: true,
    });
-    // `keys` predates the split between registered keys and the dashboard's
-    // ordinary API keys. IDs shown by `keys list`/the dashboard belong to
-    // `/api/keys`, while deployment/registered-key IDs belong to
-    // `/api/v1/registered-keys`. Try the ordinary-key route when the ID is not
-    // present in the registered-key store so the command works with either ID.
-    if (isRouteUnavailableStatus(res.status)) {
-      res = await apiFetch(`/api/keys/${encodedId}/regenerate`, {
-        method: "POST",
-        retry: false,
-        acceptNotOk: true,
-      });
-    }
    if (!res.ok) {
      console.error(t("common.error", { message: `HTTP ${res.status}` }));
      return 1;
@@ -424,17 +410,9 @@ export async function runKeysRevealCommand(id, opts = {}) {
    return 1;
  }
  try {
-    const encodedId = encodeURIComponent(id);
-    let res = await apiFetch(`/api/v1/registered-keys/${encodedId}/reveal`, {
+    const res = await apiFetch(`/api/v1/registered-keys/${encodeURIComponent(id)}/reveal`, {
      retry: false,
-      acceptNotOk: true,
    });
-    if (isRouteUnavailableStatus(res.status)) {
-      res = await apiFetch(`/api/keys/${encodedId}/reveal`, {
-        retry: false,
-        acceptNotOk: true,
-      });
-    }
    if (!res.ok) {
      console.error(t("common.error", { message: `HTTP ${res.status}` }));
      return 1;
--- a/bin/cli/commands/mcp.mjs
+++ b/bin/cli/commands/mcp.mjs
@@ -9,8 +9,6 @@ function truncate(v, len = 60) {
  return s.length > len ? s.slice(0, len - 1) + "…" : s;
 }

-const VALID_MCP_TRANSPORTS = ["stdio", "sse", "streamable-http"];
-
 const mcpToolSchema = [
  { key: "name", header: "Tool", width: 36 },
  {
@@ -45,25 +43,6 @@ export function registerMcp(program) {
      if (exitCode !== 0) process.exit(exitCode);
    });

-  mcp
-    .command("enable")
-    .description(t("mcp.enable.description"))
-    .option("--transport <transport>", t("mcp.enable.transport"))
-    .action(async (opts, cmd) => {
-      const globalOpts = cmd.parent.optsWithGlobals();
-      const exitCode = await runMcpEnableCommand({ ...opts, output: globalOpts.output });
-      if (exitCode !== 0) process.exit(exitCode);
-    });
-
-  mcp
-    .command("disable")
-    .description(t("mcp.disable.description"))
-    .action(async (opts, cmd) => {
-      const globalOpts = cmd.parent.optsWithGlobals();
-      const exitCode = await runMcpDisableCommand({ ...opts, output: globalOpts.output });
-      if (exitCode !== 0) process.exit(exitCode);
-    });
-
  // 5.1 — mcp call + mcp scopes
  mcp
    .command("call <tool> [argsJson]")
@@ -82,15 +61,10 @@ export function registerMcp(program) {
            ? JSON.parse(argsPositional)
            : {};

-      const exitCode = await runMcpCallCommand(
-        tool,
-        args,
-        {
-          ...opts,
-          stream: opts.stream,
-        },
-        globalOpts
-      );
+      const exitCode = await runMcpCallCommand(tool, args, {
+        ...opts,
+        stream: opts.stream,
+      }, globalOpts);

      if (exitCode !== 0) process.exit(exitCode);
    });
@@ -153,9 +127,7 @@ async function mcpJsonRpcCall(tool, args, { stream = false, globalOpts = {} } =

  if (!initRes.ok) {
    const text = await initRes.text().catch(() => "");
-    process.stderr.write(
-      `MCP initialize failed: HTTP ${initRes.status}${text ? ` — ${text}` : ""}\n`
-    );
+    process.stderr.write(`MCP initialize failed: HTTP ${initRes.status}${text ? ` — ${text}` : ""}\n`);
    return 1;
  }

@@ -255,7 +227,6 @@ export async function runMcpStatusCommand(opts = {}) {
    });
    if (!res.ok) {
      console.log(t("mcp.stopped"));
-      console.log(t("mcp.stoppedHint"));
      return 0;
    }

@@ -269,9 +240,6 @@ export async function runMcpStatusCommand(opts = {}) {
    const transport = status.transport || "stdio";
    const online = status.online ?? status.running;
    console.log(online ? t("mcp.running", { transport }) : t("mcp.stopped"));
-    if (!online && status.enabled === false) {
-      console.log(t("mcp.stoppedHint"));
-    }
    if (status.toolsCount !== undefined) console.log(`  Tools: ${status.toolsCount}`);
    if (status.scopes?.length) {
      console.log("  Scopes:");
@@ -302,76 +270,10 @@ export async function runMcpRestartCommand(opts = {}) {
      console.log(t("mcp.restarted"));
      return 0;
    }
-    const body = await res.json().catch(() => null);
-    const message = body?.error || `HTTP ${res.status}`;
-    console.error(t("common.error", { message }));
+    console.error(t("common.error", { message: `HTTP ${res.status}` }));
    return 1;
  } catch (err) {
    console.error(t("common.error", { message: err instanceof Error ? err.message : String(err) }));
    return 1;
  }
 }
-
-export async function runMcpEnableCommand(opts = {}) {
-  const serverUp = await isServerUp();
-  if (!serverUp) {
-    console.error(t("common.serverOffline"));
-    return 1;
-  }
-
-  if (opts.transport && !VALID_MCP_TRANSPORTS.includes(opts.transport)) {
-    console.error(
-      t("common.error", {
-        message: `Invalid transport '${opts.transport}'. Valid: ${VALID_MCP_TRANSPORTS.join(", ")}`,
-      })
-    );
-    return 1;
-  }
-
-  try {
-    const body = { mcpEnabled: true };
-    if (opts.transport) body.mcpTransport = opts.transport;
-
-    const res = await apiFetch("/api/settings", {
-      method: "PATCH",
-      body,
-      retry: false,
-      acceptNotOk: true,
-    });
-    if (!res.ok) {
-      console.error(t("common.error", { message: `HTTP ${res.status}` }));
-      return 1;
-    }
-    console.log(t("mcp.enabled"));
-    return 0;
-  } catch (err) {
-    console.error(t("common.error", { message: err instanceof Error ? err.message : String(err) }));
-    return 1;
-  }
-}
-
-export async function runMcpDisableCommand(opts = {}) {
-  const serverUp = await isServerUp();
-  if (!serverUp) {
-    console.error(t("common.serverOffline"));
-    return 1;
-  }
-
-  try {
-    const res = await apiFetch("/api/settings", {
-      method: "PATCH",
-      body: { mcpEnabled: false },
-      retry: false,
-      acceptNotOk: true,
-    });
-    if (!res.ok) {
-      console.error(t("common.error", { message: `HTTP ${res.status}` }));
-      return 1;
-    }
-    console.log(t("mcp.disabled"));
-    return 0;
-  } catch (err) {
-    console.error(t("common.error", { message: err instanceof Error ? err.message : String(err) }));
-    return 1;
-  }
-}
--- a/bin/cli/commands/oauth.mjs
+++ b/bin/cli/commands/oauth.mjs
@@ -54,34 +54,6 @@ async function openBrowser(url) {
  }
 }

-// Mirrors src/lib/oauth/providers.ts::isLoopbackHostname — used here to detect
-// when the redirect_uri the server resolved (and the authorize URL now
-// advertises) points at a loopback address the CLI never binds a listener on
-// (issue #12413). Returns false on an unparseable URI rather than throwing.
-function isLoopbackHost(uri) {
-  try {
-    return /^(localhost|127\.0\.0\.1|\[::1\]|::1)$/i.test(new URL(uri).hostname);
-  } catch {
-    return false;
-  }
-}
-
-function printLoopbackRedirectWarning(providerId, redirectUri) {
-  process.stdout.write(
-    `Note: the authorize URL below advertises ${redirectUri}, but this CLI does not\n` +
-      "listen on that port. Right after you approve, the browser is expected to\n" +
-      "show a connection error (e.g. \"This site can't be reached\" / \n" +
-      "ERR_CONNECTION_REFUSED) — that is normal, not a failure. Copy the full URL\n" +
-      "from the address bar anyway and paste it below.\n"
-  );
-  if (providerId === "antigravity") {
-    process.stdout.write(
-      "Tip: `omniroute login antigravity` captures the code automatically and\n" +
-        "avoids that error page entirely.\n"
-    );
-  }
-}
-
 function targetApiOptions(opts = {}) {
  return {
    baseUrl: opts.baseUrl,
@@ -138,10 +110,6 @@ async function runBrowserFlow(def, opts) {
  const { codeVerifier, state, redirectUri: returnedRedirectUri } = start;
  const finalRedirectUri = returnedRedirectUri || redirectUri;

-  if (finalRedirectUri && isLoopbackHost(finalRedirectUri)) {
-    printLoopbackRedirectWarning(def.id, finalRedirectUri);
-  }
-
  process.stdout.write(`\nOpen this URL to authorize:\n  ${url}\n\n`);
  if (opts.browser !== false) await openBrowser(url);
  process.stdout.write(
--- a/bin/cli/commands/restart.mjs
+++ b/bin/cli/commands/restart.mjs
@@ -6,8 +6,7 @@ export function registerRestart(program) {
  program
    .command("restart")
    .description(t("restart.description"))
-    // No Commander default: runServe() falls back to PORT, then 20128 (#7049).
-    .option("--port <port>", t("serve.port"))
+    .option("--port <port>", t("serve.port"), "20128")
    .action(async (opts) => {
      const exitCode = await runRestartCommand(opts);
      if (exitCode !== 0) process.exit(exitCode);
--- a/bin/cli/commands/serve.mjs
+++ b/bin/cli/commands/serve.mjs
@@ -4,13 +4,7 @@ import { join, dirname } from "node:path";
 import { fileURLToPath, pathToFileURL } from "node:url";
 import { platform, totalmem } from "node:os";
 import { t } from "../i18n.mjs";
-import {
-  writePidFile,
-  cleanupPidFile,
-  waitForServer,
-  findListeningPids,
-  resolveReadyTimeoutMs,
-} from "../utils/pid.mjs";
+import { writePidFile, cleanupPidFile, waitForServer } from "../utils/pid.mjs";
 import {
  ServerSupervisor,
  detectMitmCrash,
@@ -64,11 +58,6 @@ export function registerServe(program) {
    .option("--max-restarts <n>", t("serve.max_restarts"), parseInt, 2)
    .option("--tray", t("serve.tray") || "Start in the system tray (desktop only)")
    .option("--no-tray", t("serve.no_tray") || "Disable system tray icon")
-    .option(
-      "--ready-timeout <ms>",
-      t("serve.ready_timeout") ||
-        "Readiness probe timeout in ms (also OMNIROUTE_READY_TIMEOUT_MS, default 60000)"
-    )
    .option(
      "--tls-cert <path>",
      t("serve.tls_cert") ||
@@ -241,16 +230,6 @@ export async function runServe(opts = {}) {
    process.exit(1);
  }

-  // Refuse to start a second instance on a port something else already owns,
-  // BEFORE any pid file is written or any child is spawned. Otherwise the
-  // doomed child's EADDRINUSE arrives only after this process has rewritten
-  // the pid files of the healthy instance that actually owns the port.
-  const busyPids = await findListeningPids(dashboardPort);
-  if (busyPids.length > 0) {
-    reportPortInUse(dashboardPort, busyPids);
-    process.exit(1);
-  }
-
  console.log(`  \x1b[2m⏳ Starting server...\x1b[0m\n`);

  // #5172/#5160/#5152: default the V8 heap to ~35% of physical RAM (clamped
@@ -297,8 +276,7 @@ export async function runServe(opts = {}) {
    return runDaemon(serverJs, env, memoryLimit, dashboardPort, apiPort);
  }

-  // Commander stores `--no-recovery` as `recovery === false`, never as `noRecovery`.
-  if (opts.recovery === false || opts.noRecovery === true) {
+  if (opts.noRecovery) {
    return runWithoutRecovery(
      serverJs,
      env,
@@ -321,29 +299,10 @@ export async function runServe(opts = {}) {
    opts.maxRestarts ?? 2,
    startedAt,
    useTray,
-    {
-      trayReadyPort: opts.trayReadyPort,
-      trayReadyToken: opts.trayReadyToken,
-      readyTimeoutMs: resolveReadyTimeoutMs({ timeoutMs: opts.readyTimeout }),
-    }
+    { trayReadyPort: opts.trayReadyPort, trayReadyToken: opts.trayReadyToken }
  );
 }

-/**
- * Explain a port conflict in terms the operator can act on: who owns the port,
- * and the two ways out. Exported for unit tests.
- */
-export function reportPortInUse(port, pids = []) {
-  const owner = pids.length === 1 ? `PID ${pids[0]}` : `PIDs ${pids.join(", ")}`;
-  console.error(`\n\x1b[31m✖ Port ${port} is already in use by ${owner}.\x1b[0m`);
-  console.error(
-    `  Another OmniRoute is most likely already serving there, so open` +
-      ` ${urlScheme}://localhost:${port} before starting a second one.`
-  );
-  console.error(`  To replace it:    \x1b[36momniroute stop\x1b[0m, then start again`);
-  console.error(`  To run alongside: \x1b[36momniroute serve --port <other-port>\x1b[0m\n`);
-}
-
 function runDaemon(serverJs, env, memoryLimit, dashboardPort, apiPort) {
  // #5238: skip the explicit CLI --max-old-space-size when the user pinned the
  // heap via NODE_OPTIONS (a CLI arg would shadow/override their value).
@@ -454,7 +413,7 @@ async function runWithSupervisor(
  maxRestarts,
  startedAt,
  useTray = false,
-  { trayReadyPort, trayReadyToken, readyTimeoutMs = resolveReadyTimeoutMs() } = {}
+  { trayReadyPort, trayReadyToken } = {}
 ) {
  if (showLog) process.env.OMNIROUTE_SHOW_LOG = "1";
  writePidFile("supervisor", process.pid);
@@ -493,12 +452,7 @@ async function runWithSupervisor(
  });

  if (!showLog) {
-    let lastProbeOutcome = null;
-    waitForServer(dashboardPort, readyTimeoutMs, {
-      onOutcome: (outcome) => {
-        lastProbeOutcome = outcome;
-      },
-    }).then(async (up) => {
+    waitForServer(dashboardPort, 60000).then(async (up) => {
      if (up) {
        if (useTray) {
          const trayReady = await maybeStartTray(dashboardPort, apiPort, supervisor);
@@ -522,7 +476,7 @@ async function runWithSupervisor(
        }
        onReady(dashboardPort, apiPort, noOpen, startedAt);
      } else {
-        reportReadinessTimeout(dashboardPort, supervisor, lastProbeOutcome);
+        reportReadinessTimeout(dashboardPort, supervisor);
      }
    });
  }
@@ -534,31 +488,11 @@ async function runWithSupervisor(
 // stuck (issue reports show the server sometimes actually comes up later, or is
 // reachable directly while the CLI still looks hung). Surface a clear diagnostic
 // plus whatever stdout/stderr the child buffered instead of going silent.
-export function reportReadinessTimeout(dashboardPort, supervisor, lastProbeOutcome = null) {
-  const readyTimeoutMs = resolveReadyTimeoutMs();
-  const seconds = Math.round(readyTimeoutMs / 1000);
+export function reportReadinessTimeout(dashboardPort, supervisor) {
  console.error(
-    `\n\x1b[33m⚠ Server did not respond within ${seconds}s.\x1b[0m It may still be starting, or may` +
+    `\n\x1b[33m⚠ Server did not respond within 60s.\x1b[0m It may still be starting, or may` +
      ` have failed silently.`
  );
-  // The last probe classification separates a real boot failure (nothing ever
-  // bound the port, so the buffered output below is the reason) from a server
-  // that IS listening and merely did not answer the health route in time:
-  // very likely usable already, with only the readiness signal timed out.
-  if (lastProbeOutcome === "hanging" || lastProbeOutcome === "fast-reject") {
-    console.error(
-      `  Port ${dashboardPort} IS accepting connections, so the server is probably up and` +
-        ` still warming up. Check the dashboard before restarting it.`
-    );
-  } else if (lastProbeOutcome === "not-listening") {
-    console.error(
-      `  Nothing is listening on port ${dashboardPort}, so the server never bound it and the` +
-        ` output below is the reason.`
-    );
-  }
-  console.error(
-    `  Tip:  set OMNIROUTE_READY_TIMEOUT_MS=${readyTimeoutMs * 2} or --ready-timeout ${readyTimeoutMs * 2} for slower cold starts.`
-  );
  console.error(`  Try:  curl -I http://localhost:${dashboardPort}/api/monitoring/health`);
  console.error(`  Or:   rerun with \x1b[36m--log\x1b[0m to see live server output.\n`);

--- a/bin/cli/commands/setup-opencode.mjs
+++ b/bin/cli/commands/setup-opencode.mjs
@@ -35,24 +35,16 @@ export function resolveOpencodeTarget(opts = {}) {
      baseUrl = `http://localhost:${Number(opts.port ?? process.env.PORT ?? 20128) || 20128}`;
  }

-  // Precedence: explicit --api-key flag > OMNIROUTE_API_KEY env var > active
-  // context's management token. A context's accessToken/apiKey is a CLI
-  // management credential (oma_live_...) with no /v1/* inference scope — it
-  // must never silently outrank a real inference key the caller supplied
-  // either as a flag or via the ambient env var (mirrors the explicit >
-  // ambient-env > context precedence documented in bin/cli/api.mjs's
-  // buildHeaders()). Only fall back to the context token when neither an
-  // explicit flag nor the env var is set.
  let apiKey = opts.apiKey ?? opts["api-key"];
-  if (!apiKey) apiKey = process.env.OMNIROUTE_API_KEY || "";
  if (!apiKey) {
    try {
      const c = resolveActiveContext(opts.context ?? process.env.OMNIROUTE_CONTEXT);
-      apiKey = c?.accessToken || c?.apiKey || "";
+      apiKey = c?.accessToken || c?.apiKey;
    } catch {
      /* no context auth */
    }
  }
+  if (!apiKey) apiKey = process.env.OMNIROUTE_API_KEY || "";
  return { baseUrl: baseUrl.replace(/\/+$/, ""), apiKey };
 }

@@ -185,17 +177,8 @@ export function registerSetupOpencode(program) {
      "--allow-container-write",
      "Write even when the target is inside a container and not mounted from the host"
    )
-    .action(async (opts, cmd) => {
-      // Commander parses the ancestor program's own global --api-key option
-      // (bin/cli/program.mjs, bound to .env("OMNIROUTE_API_KEY")) against any
-      // occurrence of the flag in argv, so it wins the value even when the
-      // user typed --api-key AFTER `setup-opencode` — this local option's own
-      // `opts.apiKey` never sees it. cmd.optsWithGlobals() resolves to the
-      // correct value either way ("globals overwrite locals" is exactly the
-      // outcome we want here, since the global option is where the value
-      // always actually lands).
-      const resolvedOpts = { ...opts, apiKey: cmd.optsWithGlobals().apiKey ?? opts.apiKey };
-      const code = await runSetupOpencodeCommand(resolvedOpts);
+    .action(async (opts) => {
+      const code = await runSetupOpencodeCommand(opts);
      if (code !== 0) process.exit(code);
    });
 }
--- a/bin/cli/commands/update.mjs
+++ b/bin/cli/commands/update.mjs
@@ -187,9 +187,7 @@ export async function runUpdateCommand(opts = {}) {
  }

  if (dryRun) {
-    console.log(
-      "\n  [DRY RUN] Would run: npm install -g omniroute@latest --include=optional --legacy-peer-deps"
-    );
+    console.log("\n  [DRY RUN] Would run: npm install -g omniroute@latest --include=optional");
    if (!skipBackup) console.log("  [DRY RUN] Would create backup in ~/.omniroute/backups/");
    return 0;
  }
@@ -223,9 +221,7 @@ export async function runUpdateCommand(opts = {}) {
    const { execSync } = await import("child_process");
    // --include=optional keeps the optionalDependencies (better-sqlite3, keytar,
    // tls-client, llmlingua SLM stack) on update so an omit=optional config can't drop them.
-    execSync("npm install -g omniroute@latest --include=optional --legacy-peer-deps", {
-      stdio: "inherit",
-    });
+    execSync("npm install -g omniroute@latest --include=optional", { stdio: "inherit" });
    // Trust-but-verify: `npm install -g` exits 0 even when a shadowing local install
    // (e.g. ~/node_modules/omniroute ahead of the global prefix on PATH) means the
    // binary the user actually runs was not touched. Re-read the running binary's
--- a/bin/cli/locales/am.json
+++ b/bin/cli/locales/am.json
--- a/bin/cli/locales/ar.json
+++ b/bin/cli/locales/ar.json
--- a/bin/cli/locales/az.json
+++ b/bin/cli/locales/az.json
--- a/bin/cli/locales/bg.json
+++ b/bin/cli/locales/bg.json
--- a/bin/cli/locales/bn.json
+++ b/bin/cli/locales/bn.json
--- a/bin/cli/locales/cs.json
+++ b/bin/cli/locales/cs.json
--- a/bin/cli/locales/da.json
+++ b/bin/cli/locales/da.json
--- a/bin/cli/locales/de.json
+++ b/bin/cli/locales/de.json
--- a/bin/cli/locales/el.json
+++ b/bin/cli/locales/el.json
--- a/bin/cli/locales/en.json
+++ b/bin/cli/locales/en.json
@@ -256,7 +256,6 @@
    "max_restarts": "Max crash restarts within 30s before giving up (default: 2)",
    "tray": "Start in the system tray (desktop only, opt-in)",
    "no_tray": "Disable system tray icon",
-    "ready_timeout": "Readiness probe timeout in ms (also OMNIROUTE_READY_TIMEOUT_MS, default 60000)",
    "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)"
  },
@@ -348,16 +347,6 @@
    "running": "MCP server running ({transport})",
    "stopped": "MCP server stopped.",
    "restarted": "MCP server restarted.",
-    "stoppedHint": "Run `omniroute mcp enable` to turn it on.",
-    "enabled": "MCP server enabled.",
-    "disabled": "MCP server disabled.",
-    "enable": {
-      "description": "Enable the MCP server",
-      "transport": "Transport to use: stdio|sse|streamable-http"
-    },
-    "disable": {
-      "description": "Disable the MCP server"
-    },
    "call": {
      "description": "Invoke an MCP tool directly",
      "args": "JSON arguments object (inline)",
--- a/bin/cli/locales/es.json
+++ b/bin/cli/locales/es.json
--- a/bin/cli/locales/et.json
+++ b/bin/cli/locales/et.json
--- a/bin/cli/locales/fa.json
+++ b/bin/cli/locales/fa.json
--- a/bin/cli/locales/fi.json
+++ b/bin/cli/locales/fi.json
--- a/bin/cli/locales/fr.json
+++ b/bin/cli/locales/fr.json
--- a/bin/cli/locales/ga.json
+++ b/bin/cli/locales/ga.json
--- a/bin/cli/locales/gu.json
+++ b/bin/cli/locales/gu.json
--- a/bin/cli/locales/ha.json
+++ b/bin/cli/locales/ha.json
--- a/bin/cli/locales/he.json
+++ b/bin/cli/locales/he.json
--- a/bin/cli/locales/hi.json
+++ b/bin/cli/locales/hi.json
--- a/bin/cli/locales/hr.json
+++ b/bin/cli/locales/hr.json
--- a/bin/cli/locales/hu.json
+++ b/bin/cli/locales/hu.json
--- a/bin/cli/locales/hy.json
+++ b/bin/cli/locales/hy.json
--- a/bin/cli/locales/id.json
+++ b/bin/cli/locales/id.json
--- a/bin/cli/locales/ig.json
+++ b/bin/cli/locales/ig.json
--- a/bin/cli/locales/it.json
+++ b/bin/cli/locales/it.json
--- a/bin/cli/locales/ja.json
+++ b/bin/cli/locales/ja.json
--- a/bin/cli/locales/ka.json
+++ b/bin/cli/locales/ka.json
--- a/bin/cli/locales/km.json
+++ b/bin/cli/locales/km.json
--- a/bin/cli/locales/kn.json
+++ b/bin/cli/locales/kn.json
--- a/bin/cli/locales/ko.json
+++ b/bin/cli/locales/ko.json
--- a/bin/cli/locales/lt.json
+++ b/bin/cli/locales/lt.json
--- a/bin/cli/locales/lv.json
+++ b/bin/cli/locales/lv.json
--- a/bin/cli/locales/ml.json
+++ b/bin/cli/locales/ml.json
--- a/bin/cli/locales/mr.json
+++ b/bin/cli/locales/mr.json
--- a/bin/cli/locales/ms.json
+++ b/bin/cli/locales/ms.json
--- a/bin/cli/locales/mt.json
+++ b/bin/cli/locales/mt.json
--- a/bin/cli/locales/my.json
+++ b/bin/cli/locales/my.json
--- a/bin/cli/locales/ne.json
+++ b/bin/cli/locales/ne.json
--- a/bin/cli/locales/nl.json
+++ b/bin/cli/locales/nl.json
--- a/bin/cli/locales/no.json
+++ b/bin/cli/locales/no.json
--- a/bin/cli/locales/or.json
+++ b/bin/cli/locales/or.json
--- a/bin/cli/locales/pa.json
+++ b/bin/cli/locales/pa.json
--- a/bin/cli/locales/phi.json
+++ b/bin/cli/locales/phi.json
--- a/bin/cli/locales/pl.json
+++ b/bin/cli/locales/pl.json
--- a/bin/cli/locales/pt-BR.json
+++ b/bin/cli/locales/pt-BR.json
@@ -30,7 +30,7 @@
    "opencode": "Instala e configura o plugin @omniroute/opencode-plugin incluído para o OpenCode"
  },
  "doctor": {
-    "title": "Diagnóstico do OmniRoute",
+    "title": "OmniRoute Doctor",
    "dbOk": "Banco de dados: OK ({path})",
    "dbMissing": "Banco de dados: não inicializado — execute `omniroute setup`",
    "portOk": "Porta {port}: disponível",
@@ -256,7 +256,6 @@
    "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",
-    "ready_timeout": "Tempo limite da verificação de prontidão em ms (também OMNIROUTE_READY_TIMEOUT_MS, padrão 60000)",
    "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)"
  },
@@ -302,7 +301,7 @@
    "noServer": "Servidor não está em execução. Inicie com: omniroute serve",
    "title": "Saúde",
    "status": "Status: {status}",
-    "uptime": "Tempo de atividade: {uptime}",
+    "uptime": "Uptime: {uptime}",
    "requests": "Requisições (24h): {count}",
    "cost": "Custo (24h): ${cost}"
  },
@@ -345,19 +344,6 @@
  },
  "mcp": {
    "title": "Servidor MCP",
-    "running": "Servidor MCP em execução ({transport})",
-    "stopped": "Servidor MCP parado.",
-    "restarted": "Servidor MCP reiniciado.",
-    "stoppedHint": "Execute `omniroute mcp enable` para ativá-lo.",
-    "enabled": "Servidor MCP ativado.",
-    "disabled": "Servidor MCP desativado.",
-    "enable": {
-      "description": "Ativar o servidor MCP",
-      "transport": "Transporte a ser usado: stdio|sse|streamable-http"
-    },
-    "disable": {
-      "description": "Desativar o servidor MCP"
-    },
    "call": {
      "description": "Invocar uma ferramenta MCP diretamente",
      "args": "Objeto JSON de argumentos (inline)",
@@ -385,7 +371,10 @@
    },
    "audit": {
      "description": "Log de auditoria MCP (alias para audit --source mcp)"
-    }
+    },
+    "running": "Servidor MCP em execução ({transport})",
+    "stopped": "Servidor MCP parado.",
+    "restarted": "Servidor MCP reiniciado."
  },
  "a2a": {
    "skills": {
@@ -1104,7 +1093,7 @@
    }
  },
  "combo": {
-    "title": "Combinações",
+    "title": "Combos",
    "switched": "Combo ativo: {name}",
    "created": "Combo criado: {name}",
    "deleted": "Combo removido: {name}",
@@ -1279,7 +1268,7 @@
    "description": "REPL interativo multi-turn com LLM",
    "model": "Modelo a usar (padrão: auto)",
    "combo": "Nome do combo a usar",
-    "system": "Prompt do sistema",
+    "system": "System prompt",
    "resume": "Retomar sessão salva pelo nome"
  },
  "plugin": {
--- a/bin/cli/locales/pt.json
+++ b/bin/cli/locales/pt.json
--- a/bin/cli/locales/ro.json
+++ b/bin/cli/locales/ro.json
--- a/bin/cli/locales/ru.json
+++ b/bin/cli/locales/ru.json
--- a/bin/cli/locales/si.json
+++ b/bin/cli/locales/si.json
--- a/bin/cli/locales/sk.json
+++ b/bin/cli/locales/sk.json
--- a/bin/cli/locales/sl.json
+++ b/bin/cli/locales/sl.json
--- a/bin/cli/locales/sr.json
+++ b/bin/cli/locales/sr.json
--- a/Show More
+++ b/Show More