pjandro/OmniRoute
1
0
Fork 0
mirror of https://github.com/diegosouzapw/OmniRoute.git synced 2026-08-05 14:52:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

merge: reconcile release/v3.8.49 into fix(usage): preserve account identity history

Browse Source 
Resolves conflicts from the retarget (main -> release): unrelated files
(ci workflows, quality baseline, provider registry, executors, combo
validation, error sanitizer, pack-artifact policy, docs) take the
release version wholesale since this branch's own commit never touched
them. The two owned files (usageHistory.ts import ordering,
analytics/route.ts UsageRows typing) are merged to keep both sides'
changes.
This commit is contained in:
Diego Rodrigues de Sa e Souza
2026-07-19 12:27:15 -03:00
parent 025c053499 a856e3dd20
commit 9f10f6bb56
1228 changed files with 76379 additions and 8370 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
.env.example
View File

@@ -88,6 +88,14 @@ PORT=20128
# Used by: src/sse/utils/backpressure.ts — disabled when unset/0.
# OMNI_MAX_CONCURRENT_CONNECTIONS=0
# Optional OmniRoute-to-OmniRoute peer chaining guard. Give every instance a
# unique ID and allowlist only the other OmniRoute base URLs it may call.
# Requests to allowlisted peers carry X-OmniRoute-Peer-Trace; repeated instances
# and exhausted hop budgets are rejected with HTTP 508 before provider routing.
# OMNIROUTE_INSTANCE_ID=gateway-a
# OMNIROUTE_PEER_URLS=http://gateway-b:20128/v1
# OMNIROUTE_PEER_MAX_HOPS=4
# Port for the real-time WebSocket live monitoring server.
# Used by: src/server/ws/liveServer.ts, src/app/api/v1/ws/route.ts
# Default: 20132
@@ -222,7 +230,7 @@ CONTAINER_HOST=docker
# - orbstack: OrbStack (high-perf Linux VM + docker shim on macOS)
# - podman: Podman (rootless, daemonless)
# - docker: Docker (default fallback)
SKILLS_SANDBOX_RUNTIME=auto
# (defined under SKILLS & SANDBOXING section below)
# ═══════════════════════════════════════════════════════════════════════════════
# 4. SECURITY & AUTHENTICATION
@@ -649,6 +657,15 @@ NEXT_PUBLIC_ENABLE_SOCKS5_PROXY=true
# Legacy alias for OMNIROUTE_API_KEY.
# ROUTER_API_KEY=
# Enable the offline/local Issue Agent recorded-triage endpoint.
# Used by: src/app/api/issue-agent/runs/route.ts. Default: disabled.
# OMNIROUTE_ISSUE_AGENT_ENABLED=false
# Timeout (ms) for a single Issue Agent recorded-triage run. Clamped to an internal
# maximum; falls back to the built-in default when unset or invalid.
# Used by: src/lib/issueAgent/execution.ts.
# OMNIROUTE_ISSUE_AGENT_TIMEOUT_MS=
# CLI remote-mode context/profile for `omniroute` commands (overrides the active
# context in the local contexts store). Equivalent to the `--context <name>` flag.
# Used by: bin/cli/program.mjs, bin/cli/api.mjs (remote mode).
@@ -1169,6 +1186,13 @@ CURSOR_USER_AGENT="Cursor/3.4"
# PIN_DROP_BACKOFF_LEVEL=2
# PIN_DROP_GRACE_MS=20000
# Whether OmniRoute may emit SSE `:` comment lines (e.g. the `: keepalive` heartbeat).
# Some strict OpenAI-compatible clients parse every SSE line as JSON and crash on `:`
# comments. Set to `off` to suppress comment-shaped heartbeats (they become a no-op);
# `data:` heartbeats are unaffected. Default: enabled.
# Used by: open-sse/utils/sseHeartbeat.ts.
# OMNIROUTE_SSE_COMMENTS=off
# ── Stream idle detection ──
# STREAM_IDLE_TIMEOUT_MS=600000 # Max silence between SSE chunks (default: 600000)
# # Extended-thinking models rarely pause >90s.
@@ -1425,6 +1449,12 @@ APP_LOG_TO_FILE=true
# NANOBANANA_POLL_TIMEOUT_MS=120000 # Max wait for job completion (default: 120s)
# NANOBANANA_POLL_INTERVAL_MS=2500 # Poll frequency (default: 2.5s)
# ── Microsoft Designer Web (Image Generation) ──
# Polling config for the microsoft-designer-web submit-then-poll image job.
# Used by: open-sse/handlers/imageGeneration/providers/designerWeb.ts
# DESIGNER_WEB_POLL_TIMEOUT_MS=60000 # Max wait for job completion (default: 60s)
# DESIGNER_WEB_POLL_INTERVAL_MS=2000 # Poll frequency (default: 2s)
# ── AWS Bedrock (Kiro / Audio) ──
# Region used to construct AWS Bedrock endpoints. Used by:
# src/lib/providers/validation.ts and open-sse/handlers/audioSpeech.ts.
@@ -1570,9 +1600,13 @@ APP_LOG_TO_FILE=true
# 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: 120000 (2 min)
# 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=120000
# RATE_LIMIT_MAX_WAIT_MS=15000
# Rate limit queue admission cap: reject with 429 queue_full once this many requests
# are already queued (0 = disabled/unbounded, the default). Used by: open-sse/services/rateLimitManager.ts
# RATE_LIMIT_MAX_QUEUE_DEPTH=0
# Force the auto-enable rate limit safety net on/off regardless of the persisted
# Dashboard setting. Used by: open-sse/services/rateLimitManager.ts.
@@ -1621,6 +1655,12 @@ APP_LOG_TO_FILE=true
# Used by: src/lib/tokenHealthCheck.ts. Default: 3000.
# HEALTHCHECK_STAGGER_MS=3000
# Randomized jitter range (ms) added on top of HEALTHCHECK_STAGGER_MS between
# provider token healthchecks, to prevent bursting (Issue #1220).
# Used by: src/lib/tokenHealthCheck.ts. Defaults: min=500, max=5000.
# HEALTHCHECK_JITTER_MIN_MS=500
# HEALTHCHECK_JITTER_MAX_MS=5000
# ═══════════════════════════════════════════════════════════════════════════════
# 22. DEBUGGING
# ═══════════════════════════════════════════════════════════════════════════════
@@ -1759,6 +1799,13 @@ 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
# 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.
# SKIP_ANTIGRAVITY_DNS=true
# Skip writing to the hosts file when adding/removing DNS entries (e.g. sandboxed
# or read-only test environments). Used by: src/mitm/dns/dnsConfig.ts.
# OMNIROUTE_SKIP_DNS_WRITE=1
# ── Test/CI-only guards (never needed in production) ──
# Set automatically by tests/_setup/isolateDataDir.ts and the CI workflows: the

36
.github/workflows/ci.yml vendored
View File

@@ -39,7 +39,7 @@ jobs:
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
- id: classify
@@ -82,7 +82,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -171,7 +171,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -280,7 +280,7 @@ jobs:
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -388,7 +388,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -424,7 +424,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -452,7 +452,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -515,7 +515,7 @@ jobs:
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
- name: Fetch base branch
@@ -554,7 +554,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -602,7 +602,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -649,7 +649,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -710,7 +710,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -757,7 +757,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -802,7 +802,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -871,7 +871,7 @@ jobs:
# (if-no-files-found: warn) — Sonar consumes the same file.
- name: Upload coverage to Codecov (informational)
if: always()
uses: codecov/codecov-action@04b047e8bb82a0c002c8312c1c880fbc6a999d45 # v5
uses: codecov/codecov-action@0fb7174895f61a3b6b78fc075e0cd60383518dac # v5
with:
files: coverage/lcov.info
token: ${{ secrets.CODECOV_TOKEN }}
@@ -1045,7 +1045,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -1115,7 +1115,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -1138,7 +1138,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm

4
.github/workflows/codeql.yml vendored
View File

@@ -22,10 +22,10 @@ jobs:
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- uses: github/codeql-action/init@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4.37.0
- uses: github/codeql-action/init@7188fc363630916deb702c7fdcf4e481b751f97a # v4.37.1
with:
languages: javascript-typescript
queries: security-extended
- uses: github/codeql-action/analyze@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4.37.0
- uses: github/codeql-action/analyze@7188fc363630916deb702c7fdcf4e481b751f97a # v4.37.1
with:
category: "/language:javascript-typescript"

4
.github/workflows/dast-smoke.yml vendored
View File

@@ -21,12 +21,14 @@ jobs:
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
with:
node-version: "24"
cache: npm
- run: npm ci
- name: Build CLI bundle
env:
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
run: npm run build:cli
- name: Start OmniRoute
env:

2
.github/workflows/electron-release.yml vendored
View File

@@ -88,7 +88,7 @@ jobs:
with:
persist-credentials: false
- name: Setup Node
uses: actions/setup-node@v6
uses: actions/setup-node@v7
with:
node-version: 24
cache: npm

2
.github/workflows/mutation-redundancy.yml vendored
View File

@@ -44,7 +44,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm

4
.github/workflows/nightly-compat.yml vendored
View File

@@ -66,7 +66,7 @@ jobs:
with:
ref: ${{ needs.resolve-branch.outputs.target }}
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "26"
cache: npm
@@ -93,7 +93,7 @@ jobs:
with:
ref: ${{ needs.resolve-branch.outputs.target }}
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ matrix.node }}
cache: npm

12
.github/workflows/nightly-llm-security.yml vendored
View File

@@ -15,11 +15,13 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with: { node-version: "24", cache: npm }
- run: npm ci
- name: Build CLI bundle
env: { JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation }
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
run: npm run build:cli
- name: Start OmniRoute (block mode)
env:
@@ -65,14 +67,16 @@ jobs:
with:
persist-credentials: false
if: steps.gate.outputs.run == 'true'
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
if: steps.gate.outputs.run == 'true'
with: { node-version: "24", cache: npm }
- run: npm ci
if: steps.gate.outputs.run == 'true'
- name: Build CLI bundle
if: steps.gate.outputs.run == 'true'
env: { JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation }
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
run: npm run build:cli
- name: Start OmniRoute
if: steps.gate.outputs.run == 'true'

4
.github/workflows/nightly-mutation.yml vendored
View File

@@ -107,7 +107,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
@@ -151,7 +151,7 @@ jobs:
- uses: actions/checkout@v6
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "24"
- name: Download all mutation reports

2
.github/workflows/nightly-property.yml vendored
View File

@@ -13,7 +13,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm

4
.github/workflows/nightly-release-green.yml vendored
View File

@@ -116,7 +116,7 @@ jobs:
git checkout "$TARGET"
git log -1 --oneline
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
@@ -228,7 +228,7 @@ jobs:
fetch-depth: 0
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm

9
.github/workflows/nightly-resilience.yml vendored
View File

@@ -15,7 +15,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
@@ -29,7 +29,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
@@ -43,7 +43,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
@@ -51,6 +51,7 @@ jobs:
- name: Build CLI bundle
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
run: npm run build:cli
- name: Start OmniRoute (background)
env:
@@ -94,7 +95,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm

6
.github/workflows/nightly-schemathesis.yml vendored
View File

@@ -16,11 +16,13 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with: { node-version: "24", cache: npm }
- run: npm ci
- name: Build CLI bundle
env: { JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation }
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
run: npm run build:cli
- name: Start OmniRoute (background)
env:

4
.github/workflows/npm-publish.yml vendored
View File

@@ -71,7 +71,7 @@ jobs:
fetch-depth: 0
- name: Setup Node.js
uses: actions/setup-node@v6
uses: actions/setup-node@v7
with:
node-version: ${{ env.NPM_PUBLISH_NODE_VERSION }}
registry-url: https://registry.npmjs.org
@@ -265,7 +265,7 @@ jobs:
# Full history needed for auto-bump: git diff against previous release tag
- name: Setup Node.js
uses: actions/setup-node@v6
uses: actions/setup-node@v7
with:
node-version: ${{ env.NPM_PUBLISH_NODE_VERSION }}
registry-url: https://registry.npmjs.org

4
.github/workflows/opencode-plugin-ci.yml vendored
View File

@@ -35,7 +35,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ matrix.node }}
cache: npm
@@ -52,7 +52,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "22"
cache: npm

4
.github/workflows/opencode-provider-ci.yml vendored
View File

@@ -35,7 +35,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ matrix.node }}
cache: npm
@@ -51,7 +51,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: "20"
cache: npm

14
.github/workflows/quality.yml vendored
View File

@@ -36,7 +36,7 @@ jobs:
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
- id: classify
@@ -68,7 +68,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -99,7 +99,7 @@ jobs:
with:
fetch-depth: 0
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -225,7 +225,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -265,7 +265,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -299,7 +299,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v6
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -343,7 +343,7 @@ jobs:
with:
fetch-depth: 0
persist-credentials: false
- uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm

2
.github/workflows/wiki-sync.yml vendored
View File

@@ -40,7 +40,7 @@ jobs:
uses: actions/checkout@v7
- name: Setup Node
uses: actions/setup-node@v6
uses: actions/setup-node@v7
with:
node-version: "24"

5
.gitignore vendored
View File

@@ -233,7 +233,7 @@ omniroute.md
# mise configuration
mise.toml
_artifacts/
_artifacts/ # release-green artifacts
.claude-flow/
# ESLint file cache (npm run lint --cache / complexity ratchets)
@@ -241,7 +241,7 @@ _artifacts/
.eslintcache-complexity
# CI/local quality artifacts (eslint-results.json, etc.)
# CI/local quality artifacts (eslint-results.json, quality-ratchet.md, etc.)
.artifacts/
# Homologation E2E suite (npm run homolog) — real-environment credentials + report output
@@ -249,3 +249,4 @@ _artifacts/
tests/homolog/.auth/
tests/homolog/ui/.auth/
homolog-report/
docker-compose.yml.bak

4
AGENTS.md
View File

@@ -3,12 +3,12 @@
## Project
Unified AI proxy/router — route any LLM through one endpoint. Multi-provider support
with **250 provider entries** (OpenAI, Anthropic, Gemini, DeepSeek, Groq, xAI, Mistral, Fireworks,
with **268 provider entries** (OpenAI, Anthropic, Gemini, DeepSeek, Groq, xAI, Mistral, Fireworks,
Cohere, NVIDIA, Cerebras, Pollinations, Puter, Cloudflare AI, HuggingFace, DeepInfra,
SambaNova, Meta Llama API, Moonshot AI, AI21 Labs, Databricks, Snowflake, and many more)
with **MCP Server** (94 tools), **A2A v0.3 Protocol**, and **Electron desktop app**.
> **Live counts (v3.8.47)**: providers 250 · MCP tools 94 · MCP scopes 30 · A2A skills 6 ·
> **Live counts (v3.8.49)**: providers 268 · MCP tools 104 · MCP scopes 30 · A2A skills 6 ·
> open-sse services 134 · routing strategies 17 · auto-combo scoring factors 12 ·
> DB modules 95 · DB migrations 110 · base tables 17 · search providers 11 ·
> i18n locales 42. **Refresh with `npm run check:docs-all`.**

320
CHANGELOG.md
View File

@@ -6,6 +6,326 @@
## [3.8.49] — TBD
_Living section — regenerated 2026-07-19 from all 306 cycle commits (bump 2c62333b0 → tip). Bullets carry the merged PR and its author; direct pushes listed separately. Finalized at the v3.8.49 release._
### ✨ New Features
- **feat:** generalize ensureThinkingBudget to all providers + preserve server-side tool invocations on antigravity ([#6979](https://github.com/diegosouzapw/OmniRoute/pull/6979)) — thanks @rafaumeu
- **feat(6922):** effort-tier aliases for glm-5.2 & mimo-v2.5 on opencode-go ([#6987](https://github.com/diegosouzapw/OmniRoute/pull/6987)) — thanks @rafaumeu
- **feat(providers):** curated OpenRouter embeddings catalog + specialty merge in live discovery (#6976) ([#6994](https://github.com/diegosouzapw/OmniRoute/pull/6994))
- **feat(quota):** opt-in auto-ping to keep Codex quota windows warm (#6977) ([#6995](https://github.com/diegosouzapw/OmniRoute/pull/6995))
- **feat(providers):** add Agnes AI native provider support ([#7035](https://github.com/diegosouzapw/OmniRoute/pull/7035)) — thanks @HouMinXi
- **feat(sse):** allow disabling `:` comment heartbeats via OMNIROUTE_SSE_COMMENTS=off ([#7036](https://github.com/diegosouzapw/OmniRoute/pull/7036)) — thanks @xier2012
- **feat(perf):** add performance.mark/measure to SSE pipeline + request-size metric ([#7045](https://github.com/diegosouzapw/OmniRoute/pull/7045)) — thanks @oyi77
- **feat(providers):** add Dahl free inference provider ([#7062](https://github.com/diegosouzapw/OmniRoute/pull/7062)) — thanks @growab
- **feat(ci):** boot-smoke the packed npm tarball (check:pack-boot, #7065 class killer) ([#7086](https://github.com/diegosouzapw/OmniRoute/pull/7086))
- **feat(ci):** hotfix fast-lane + tests-only E2E skip (WS3.1) ([#7088](https://github.com/diegosouzapw/OmniRoute/pull/7088))
- **feat(ci):** continuous release-green — on-push quick gate + 3x/day full sweep (WS5.1) ([#7089](https://github.com/diegosouzapw/OmniRoute/pull/7089))
- **feat(ci):** duration-balanced E2E shards via LPT bin-packing (WS4.1) ([#7090](https://github.com/diegosouzapw/OmniRoute/pull/7090))
- **feat(ci):** TypeScript 7 native shadow for typecheck:core (WS4.2, advisory) ([#7091](https://github.com/diegosouzapw/OmniRoute/pull/7091))
- **feat(release):** npm staged publishing + pre-publish boot-smoke (WS1.3) ([#7092](https://github.com/diegosouzapw/OmniRoute/pull/7092))
- **feat(release):** post-publish verifier — clean-container install + boot (WS1.4) ([#7109](https://github.com/diegosouzapw/OmniRoute/pull/7109))
- **feat(ci):** Mergify merge queue + manual-train fallback runbook (WS3.4/WS3.2) ([#7112](https://github.com/diegosouzapw/OmniRoute/pull/7112))
- **feat(ci):** Windows leg for Electron prepare smoke (WS1.5) ([#7113](https://github.com/diegosouzapw/OmniRoute/pull/7113))
- **feat(ci):** Codecov patch coverage (informational) + fix missing lcov reporter (WS5.6) ([#7114](https://github.com/diegosouzapw/OmniRoute/pull/7114))
- **feat(sidecar):** support conditional provider manifest refresh ([#7130](https://github.com/diegosouzapw/OmniRoute/pull/7130)) — thanks @KooshaPari
- **feat(homolog):** real-environment E2E homologation suite (npm run homolog) ([#7133](https://github.com/diegosouzapw/OmniRoute/pull/7133))
- **feat(usage):** add Codex reset credit picker ([#7154](https://github.com/diegosouzapw/OmniRoute/pull/7154)) — thanks @JxnLexn
- **feat(ci):** Trunk Flaky Tests uploads for vitest + Playwright E2E (WS5.2/5.3) ([#7175](https://github.com/diegosouzapw/OmniRoute/pull/7175))
- **feat(ci):** Trunk Flaky Tests upload on the fast-path vitest job (per-PR volume) ([#7205](https://github.com/diegosouzapw/OmniRoute/pull/7205))
- **feat(kiro):** register GPT-5.6 Sol/Terra/Luna model family ([#7209](https://github.com/diegosouzapw/OmniRoute/pull/7209))
- **feat(dashboard):** show Codex plan label in provider and quota views ([#7210](https://github.com/diegosouzapw/OmniRoute/pull/7210))
- **feat(dashboard):** add reorder connections by availability button ([#7211](https://github.com/diegosouzapw/OmniRoute/pull/7211))
- **feat(dashboard):** add 180D and 365D usage/cost analytics periods (#7213) ([#7213](https://github.com/diegosouzapw/OmniRoute/pull/7213))
- **feat(api):** add Vary: Accept-Encoding to token-authenticated /v1* responses (#6737) ([#7217](https://github.com/diegosouzapw/OmniRoute/pull/7217))
- **feat(api):** expose GET /api/usage/model-latency-stats (#6873) ([#7218](https://github.com/diegosouzapw/OmniRoute/pull/7218))
- **feat(dashboard):** add compression-mode selector to Context & Cache combos page (#6760) ([#7219](https://github.com/diegosouzapw/OmniRoute/pull/7219))
- **feat(sse):** route GitHub Copilot Claude models through native /v1/messages ([#7223](https://github.com/diegosouzapw/OmniRoute/pull/7223))
- **feat(mitm):** add Antigravity reasoning-effort overrides ([#7228](https://github.com/diegosouzapw/OmniRoute/pull/7228))
- **feat:** replace free-text model inputs with hidePaid-aware Selects (#6540) ([#7229](https://github.com/diegosouzapw/OmniRoute/pull/7229))
- **feat:** editable ComfyUI base-URL field + per-connection override for image/video/music generation (#6928) ([#7232](https://github.com/diegosouzapw/OmniRoute/pull/7232))
- **feat(sse):** add optional-enum null-omission idiom for codex strict-mode tools (#7023) ([#7233](https://github.com/diegosouzapw/OmniRoute/pull/7233))
- **feat(sse):** preserve tools/tool_choice for tool-bearing requests through fusion combos (#6771) ([#7235](https://github.com/diegosouzapw/OmniRoute/pull/7235))
- **feat(api):** accept x-goog-api-key header for client-facing auth (#7034) ([#7236](https://github.com/diegosouzapw/OmniRoute/pull/7236))
- **feat(sse):** add native xAI Grok Imagine video generation provider ([#7238](https://github.com/diegosouzapw/OmniRoute/pull/7238))
- **feat:** add Type filter and easiest-first sort to Free Provider Rankings (#6915) ([#7240](https://github.com/diegosouzapw/OmniRoute/pull/7240))
- **feat(cli):** add Grok Build CLI tool setup (~/.grok/config.toml) ([#7241](https://github.com/diegosouzapw/OmniRoute/pull/7241))
- **feat(provider):** add Chenzk API OpenAI-compatible gateway ([#7246](https://github.com/diegosouzapw/OmniRoute/pull/7246))
- **feat(providers):** let custom connections opt into prompt-cache capability (#6880) ([#7257](https://github.com/diegosouzapw/OmniRoute/pull/7257))
- **feat(db):** include xp_audit_log in automatic retention/prune (#6801) ([#7260](https://github.com/diegosouzapw/OmniRoute/pull/7260))
- **feat(api):** structured X-Routing-Fallback-Reason header for relay routing (#6872) ([#7262](https://github.com/diegosouzapw/OmniRoute/pull/7262))
- **feat(compression):** support RTK TOML schema v1 filters ([#7281](https://github.com/diegosouzapw/OmniRoute/pull/7281)) — thanks @JxnLexn
- **feat:** add principal-scoped CCR MCP lifecycle ([#7282](https://github.com/diegosouzapw/OmniRoute/pull/7282)) — thanks @JxnLexn
- **feat(morph):** refresh curated models ([#7314](https://github.com/diegosouzapw/OmniRoute/pull/7314)) — thanks @backryun
- **feat(issue-agent):** surface RecordedTriageTimeoutError as 504 ([#7315](https://github.com/diegosouzapw/OmniRoute/pull/7315)) — thanks @KooshaPari
- **feat(incident-response):** structured incident response templates ([#7334](https://github.com/diegosouzapw/OmniRoute/pull/7334)) — thanks @KooshaPari
- **feat(providers):** add xAI OAuth PKCE provider ([#7399](https://github.com/diegosouzapw/OmniRoute/pull/7399)) — thanks @fenix007
- **feat(models):** advertise Claude reasoning-effort variants in /v1/models ([#7497](https://github.com/diegosouzapw/OmniRoute/pull/7497)) — thanks @thepigdestroyer
- **feat(kimi):** sync Code, Web, and Moonshot providers ([#7531](https://github.com/diegosouzapw/OmniRoute/pull/7531)) — thanks @backryun
- **feat(resilience):** guard OmniRoute peer routing loops ([#7555](https://github.com/diegosouzapw/OmniRoute/pull/7555)) — thanks @isiahw1
- **feat:** add Mixedbread AI as embeddings provider (#6660) ([#7595](https://github.com/diegosouzapw/OmniRoute/pull/7595))
- **feat(providers):** add Rev AI speech-to-text provider (#6655) ([#7596](https://github.com/diegosouzapw/OmniRoute/pull/7596))
- **feat:** add Freepik (Magnific Mystic) image generation provider (#6654) ([#7597](https://github.com/diegosouzapw/OmniRoute/pull/7597))
- **feat(sse):** add DeepInfra as a video-generation provider (#6653) ([#7598](https://github.com/diegosouzapw/OmniRoute/pull/7598))
- **feat(providers):** add Felo chat-aggregator provider (#6666) ([#7599](https://github.com/diegosouzapw/OmniRoute/pull/7599))
- **feat(sse):** add Notion AI Web (Unofficial/Experimental) provider (#6758) ([#7600](https://github.com/diegosouzapw/OmniRoute/pull/7600))
- **feat:** add FreeTheAi as OpenAI-compatible gateway provider (#6670) ([#7602](https://github.com/diegosouzapw/OmniRoute/pull/7602))
- **feat:** add Gladia as an async speech-to-text provider (#6657) ([#7603](https://github.com/diegosouzapw/OmniRoute/pull/7603))
- **feat:** add EdgeTTS audio-tts provider (#6668) ([#7605](https://github.com/diegosouzapw/OmniRoute/pull/7605))
- **feat(video):** add Novita AI as video-generation provider (#6658) ([#7606](https://github.com/diegosouzapw/OmniRoute/pull/7606))
- **feat:** add Segmind image+video provider (#6656) ([#7608](https://github.com/diegosouzapw/OmniRoute/pull/7608))
- **feat:** add Microsoft Designer as image provider (#6672) ([#7609](https://github.com/diegosouzapw/OmniRoute/pull/7609))
- **feat:** per-model default reasoning_effort + no-think none on OpenAI path (#6879) ([#7631](https://github.com/diegosouzapw/OmniRoute/pull/7631))
- **feat(sse):** per-model upstream header-response timeout override (#6354) ([#7632](https://github.com/diegosouzapw/OmniRoute/pull/7632))
- **feat(dashboard):** in-product guidance for prompt compression engines (#7530) ([#7634](https://github.com/diegosouzapw/OmniRoute/pull/7634))
- **feat(usage):** add TTFT/E2E-latency/tokens-per-second to model latency stats (#6875) ([#7635](https://github.com/diegosouzapw/OmniRoute/pull/7635))
- **feat:** import providers from CSV/JSON file (#6836) ([#7636](https://github.com/diegosouzapw/OmniRoute/pull/7636))
- **feat:** confirm before removing a single connection (#7361) ([#7640](https://github.com/diegosouzapw/OmniRoute/pull/7640))
- **feat(sse):** honor excluded models in no-auth auto-combo candidate pool (#7622) ([#7646](https://github.com/diegosouzapw/OmniRoute/pull/7646))
- **feat(providers):** add g4f.space no-key gateway (groq/gemini/pollinations/ollama/nvidia) (#6650) ([#7647](https://github.com/diegosouzapw/OmniRoute/pull/7647))
- **feat:** rate-limit queue admission control (maxQueueDepth + 15s default) (#6593) ([#7649](https://github.com/diegosouzapw/OmniRoute/pull/7649))
- **feat(sse):** generalize session affinity TTL to all providers (#7274) ([#7650](https://github.com/diegosouzapw/OmniRoute/pull/7650))
- **feat:** OpenRouter quota tracking (key/credits + free-window counter) (#6842) ([#7651](https://github.com/diegosouzapw/OmniRoute/pull/7651))
- **feat(sse):** quota tracking for AgentRouter, v0 (Vercel), FreeModel (#6850, #6845, #7075) ([#7653](https://github.com/diegosouzapw/OmniRoute/pull/7653))
- **feat(providers):** Speechmatics STT, gTTS, VibeProxy preset (#6659, #6667, #6874) ([#7655](https://github.com/diegosouzapw/OmniRoute/pull/7655))
- **feat(api):** route Google AI Studio Imagen through /v1/images/generations ([#7656](https://github.com/diegosouzapw/OmniRoute/pull/7656)) — thanks @danscMax
### ⚡ Performance
- **perf(db):** project columns + composite index in getProviderConnections ([#6918](https://github.com/diegosouzapw/OmniRoute/pull/6918)) — thanks @oyi77
- **perf(db):** add jitter to stagger due-on-restart connections ([#6919](https://github.com/diegosouzapw/OmniRoute/pull/6919)) — thanks @oyi77
- **perf(startup):** warm model catalog cache at module init ([#6920](https://github.com/diegosouzapw/OmniRoute/pull/6920)) — thanks @oyi77
- **perf(db):** add temp_store=MEMORY pragma to SQLite init ([#6921](https://github.com/diegosouzapw/OmniRoute/pull/6921)) — thanks @oyi77
- **perf(db):** cap modelLockouts eviction at 1000 entries ([#6923](https://github.com/diegosouzapw/OmniRoute/pull/6923)) — thanks @oyi77
- **perf:** wrap ComboCard, HeroSection in React.memo ([#7070](https://github.com/diegosouzapw/OmniRoute/pull/7070)) — thanks @oyi77
### 🐛 Bug Fixes
- **fix:** add re-entrancy guard to token health check sweep ([#6917](https://github.com/diegosouzapw/OmniRoute/pull/6917)) — thanks @oyi77
- **fix(grok):** strip reasoningEffort for grok cli models ([#6938](https://github.com/diegosouzapw/OmniRoute/pull/6938)) — thanks @CitrusIce
- **fix(6954,6953):** preserve system role + strip empty-signature thinking blocks ([#6982](https://github.com/diegosouzapw/OmniRoute/pull/6982)) — thanks @rafaumeu
- **fix(6980):** classify Cloudflare AI neuron exhaustion as quota_exhausted ([#6983](https://github.com/diegosouzapw/OmniRoute/pull/6983)) — thanks @rafaumeu
- **fix(dashboard):** hide disabled provider connections from combo builder ([#6984](https://github.com/diegosouzapw/OmniRoute/pull/6984))
- **fix(providers):** cap grok-cli tools at 200 for cli-chat-proxy ([#6986](https://github.com/diegosouzapw/OmniRoute/pull/6986))
- **fix(6848):** auto-cleanup for telemetry tables causing OOM ([#6988](https://github.com/diegosouzapw/OmniRoute/pull/6988)) — thanks @rafaumeu
- **fix(models):** preserve direct-model combo metadata ([#6993](https://github.com/diegosouzapw/OmniRoute/pull/6993)) — thanks @JxnLexn
- **fix:** DDG circuit breaker (#6999) + null content validation (#7000) ([#7001](https://github.com/diegosouzapw/OmniRoute/pull/7001)) — thanks @rafaumeu
- **fix(models):** preserve chat-capable image model rows ([#7004](https://github.com/diegosouzapw/OmniRoute/pull/7004)) — thanks @xz-dev
- **fix(codex):** preserve GPT-5.6 reasoning contract ([#7012](https://github.com/diegosouzapw/OmniRoute/pull/7012)) — thanks @xz-dev
- **fix(base-red):** align least-used combo tests with executionKey usage keying ([#7015](https://github.com/diegosouzapw/OmniRoute/pull/7015))
- **fix:** infer bare models from active synced catalogs ([#7028](https://github.com/diegosouzapw/OmniRoute/pull/7028)) — thanks @guanbear
- **fix(auggie):** update model registry to match v0.32.0 CLI model IDs ([#7032](https://github.com/diegosouzapw/OmniRoute/pull/7032)) — thanks @oyi77
- **fix(sse):** register ollama-cloud in USAGE_FETCHER_PROVIDERS (#7026) ([#7041](https://github.com/diegosouzapw/OmniRoute/pull/7041)) — thanks @alltomatos
- **fix(quality):** read cognitiveComplexity= machine line in validate-release-green (#7009) ([#7042](https://github.com/diegosouzapw/OmniRoute/pull/7042)) — thanks @alltomatos
- **fix(providers):** sanitize Claude native output_config.effort (#7044) ([#7050](https://github.com/diegosouzapw/OmniRoute/pull/7050)) — thanks @xier2012
- **fix(combo):** treat maxInputTokens as an input-only cap in the context filter (#7039) ([#7052](https://github.com/diegosouzapw/OmniRoute/pull/7052)) — thanks @xier2012
- **fix(antigravity):** collect native part.functionCall into tool calls (#7037) ([#7053](https://github.com/diegosouzapw/OmniRoute/pull/7053)) — thanks @xier2012
- **fix(responses):** map mid-conversation system turns to developer role (#6954) ([#7056](https://github.com/diegosouzapw/OmniRoute/pull/7056)) — thanks @xier2012
- **fix(combo):** least-used sorts by per-account executionKey (#7015) ([#7059](https://github.com/diegosouzapw/OmniRoute/pull/7059)) — thanks @xier2012
- **fix(providers):** AgentRouter model import applies Claude Code wire image to /v1/models (#7016) ([#7060](https://github.com/diegosouzapw/OmniRoute/pull/7060)) — thanks @xier2012
- **fix(translator):** preserve thinking.budget_tokens: 0 in Claude->Gemini (#6813) ([#7061](https://github.com/diegosouzapw/OmniRoute/pull/7061)) — thanks @xier2012
- **fix(cloudflare-relay):** avoid invalid regex syntax in generated worker ([#7063](https://github.com/diegosouzapw/OmniRoute/pull/7063)) — thanks @SeaXen
- **fix(dashboard):** strip browser-extension attrs before hydration ([#7073](https://github.com/diegosouzapw/OmniRoute/pull/7073)) — thanks @MrFadiAi
- **fix(relay):** bound Bifrost stream lifetime ([#7093](https://github.com/diegosouzapw/OmniRoute/pull/7093)) — thanks @KooshaPari
- **fix(sse):** recognize xiaomi-tokenplan mimo as a thinking-mode model ([#7098](https://github.com/diegosouzapw/OmniRoute/pull/7098))
- **fix(codex):** strip regex lookaround from tool schema patterns ([#7100](https://github.com/diegosouzapw/OmniRoute/pull/7100))
- **fix(openai):** strip reasoning_effort when GPT-5.x models carry function tools ([#7101](https://github.com/diegosouzapw/OmniRoute/pull/7101))
- **fix(compression):** Headroom SmartCrusher skips developer-role messages (port from 9router#2132) ([#7102](https://github.com/diegosouzapw/OmniRoute/pull/7102))
- **fix(providers):** surface a warning on 404 model_not_found in OpenAI-compatible Check (port from 9router#2032) ([#7103](https://github.com/diegosouzapw/OmniRoute/pull/7103))
- **fix(executors):** forward X-Session-ID/X-Title agent metadata headers ([#7104](https://github.com/diegosouzapw/OmniRoute/pull/7104))
- **fix(cli):** verify better-sqlite3 native binary is actually loadable ([#7105](https://github.com/diegosouzapw/OmniRoute/pull/7105))
- **fix(sse):** sanitize non-ok Antigravity streaming error body (port from 9router#2461) ([#7106](https://github.com/diegosouzapw/OmniRoute/pull/7106))
- **fix(providers):** add MiniMax image-generation provider ([#7108](https://github.com/diegosouzapw/OmniRoute/pull/7108))
- **fix(sse):** handle space-separated arg name/value in Composer tool calls (port from 9router#1811) ([#7116](https://github.com/diegosouzapw/OmniRoute/pull/7116))
- **fix(cli):** remove MITM DNS spoof entries before killing server process ([#7117](https://github.com/diegosouzapw/OmniRoute/pull/7117))
- **fix(dashboard):** include never-tested connections in combo builder active-provider list (port from 9router#2057) ([#7118](https://github.com/diegosouzapw/OmniRoute/pull/7118))
- **fix(api):** check Vercel SSO-protection PATCH response on relay deploy ([#7119](https://github.com/diegosouzapw/OmniRoute/pull/7119))
- **fix(combos):** reject oversized fusion panels before fan-out (port from 9router#1905) ([#7120](https://github.com/diegosouzapw/OmniRoute/pull/7120))
- **fix(combo):** detect empty content_block in streaming SSE peek ([#7121](https://github.com/diegosouzapw/OmniRoute/pull/7121))
- **fix(oauth):** resolve Kiro AWS SSO cache client credentials by clientId match (port from 9router#1253) ([#7122](https://github.com/diegosouzapw/OmniRoute/pull/7122))
- **fix(tests):** vitest UI suite back to green (69 fails triaged — WS6.1) ([#7127](https://github.com/diegosouzapw/OmniRoute/pull/7127))
- **fix(auto):** use p95 fallback in speed factors ([#7128](https://github.com/diegosouzapw/OmniRoute/pull/7128)) — thanks @KooshaPari
- **fix(models):** update Anthropic model contextLength to 1M ([#7129](https://github.com/diegosouzapw/OmniRoute/pull/7129)) — thanks @HouMinXi
- **fix(ci):** raise dast-smoke timeout 12->25min (build alone eats up to 11min) ([#7139](https://github.com/diegosouzapw/OmniRoute/pull/7139))
- **fix(compression):** lazy-load typescript in RTK codeStripper so prod-lean deploys don't break (#7096) ([#7164](https://github.com/diegosouzapw/OmniRoute/pull/7164)) — thanks @alltomatos
- **fix(providers):** accept m365.cloud.microsoft for copilot-m365-web token (#7078) ([#7166](https://github.com/diegosouzapw/OmniRoute/pull/7166)) — thanks @xier2012
- **fix(executors):** disable parallel tools for Codex Responses Lite ([#7171](https://github.com/diegosouzapw/OmniRoute/pull/7171)) — thanks @fenix007
- **fix(tests+providers):** env-dependent tests exposed by GH-hosted runners (#6634 selfref shallow checkout + yuanbao live-network 401) ([#7174](https://github.com/diegosouzapw/OmniRoute/pull/7174))
- **fix(combo):** reject known context overflow without exhausting providers ([#7177](https://github.com/diegosouzapw/OmniRoute/pull/7177)) — thanks @JxnLexn
- **fix:** add static.cloudflareinsights.com to CSP script-src ([#7178](https://github.com/diegosouzapw/OmniRoute/pull/7178)) — thanks @oyi77
- **fix:** extend turbopack ignoreIssue suppression to compression module (#7051) ([#7180](https://github.com/diegosouzapw/OmniRoute/pull/7180))
- **fix:** recognize Ollama Cloud session usage-limit 429 as quota-exhausted (#7071) ([#7181](https://github.com/diegosouzapw/OmniRoute/pull/7181))
- **fix:** preserve relayAuth for pool-referenced relay proxies (#5716) ([#7182](https://github.com/diegosouzapw/OmniRoute/pull/7182))
- **fix:** wire adaptive context-budget dial into settings schema and DB (#7005) ([#7183](https://github.com/diegosouzapw/OmniRoute/pull/7183))
- **fix(providers):** DuckDuckGo VQD 429 misclassified as 503 (#6996) ([#7185](https://github.com/diegosouzapw/OmniRoute/pull/7185))
- **fix(db):** cap OOM probe-failure cycle in getDbInstance() (#6835) ([#7186](https://github.com/diegosouzapw/OmniRoute/pull/7186))
- **fix:** stop opencode-go quota lookup defaulting to Z.AI endpoint (#7022) ([#7187](https://github.com/diegosouzapw/OmniRoute/pull/7187))
- **fix(providers):** refresh OpenCode (oc) free-tier model catalog (#6998) ([#7188](https://github.com/diegosouzapw/OmniRoute/pull/7188))
- **fix:** include proxyId when testing a saved registry proxy (#7080) ([#7189](https://github.com/diegosouzapw/OmniRoute/pull/7189))
- **fix:** sanitize non-Latin1 chars in combo diagnostic headers (#6612) ([#7190](https://github.com/diegosouzapw/OmniRoute/pull/7190))
- **fix:** raise main server keepAliveTimeout/headersTimeout above Node's 5s default (#7003) ([#7191](https://github.com/diegosouzapw/OmniRoute/pull/7191))
- **fix:** route zai-web (and other registry-entry web-cookie providers) connection-test cookie probe through the configured proxy (#7058) ([#7192](https://github.com/diegosouzapw/OmniRoute/pull/7192))
- **fix(providers):** reject chat requests for cloud-agent-only jules provider (#6699) ([#7193](https://github.com/diegosouzapw/OmniRoute/pull/7193))
- **fix:** restore mobile grid-cols-1 fallback on quota page card grid (#7072) ([#7194](https://github.com/diegosouzapw/OmniRoute/pull/7194))
- **fix:** wire modelAliases fetch into HermesAgentToolCard (#7151) ([#7195](https://github.com/diegosouzapw/OmniRoute/pull/7195))
- **fix:** surface real claude-web error body for non-SSE 400s (#7134) ([#7196](https://github.com/diegosouzapw/OmniRoute/pull/7196))
- **fix(dashboard):** agent bridge dns toggle uses POST, not PUT (#7157) ([#7197](https://github.com/diegosouzapw/OmniRoute/pull/7197))
- **fix:** stop duplicating text in Gemini Web streamed responses (#7163) ([#7198](https://github.com/diegosouzapw/OmniRoute/pull/7198))
- **fix:** filter hidden custom models out of legacy combo model picker (#7156) ([#7199](https://github.com/diegosouzapw/OmniRoute/pull/7199))
- **fix(dashboard):** implement missing handleToggleSource on Free Pool tab (#7161) ([#7200](https://github.com/diegosouzapw/OmniRoute/pull/7200))
- **fix:** honor combo-level proxy assignments from the registry (#7149) ([#7201](https://github.com/diegosouzapw/OmniRoute/pull/7201))
- **fix(ci):** run quality gates on Mergify merge-queue draft PRs (anchor check never ran, queue always dequeued) ([#7202](https://github.com/diegosouzapw/OmniRoute/pull/7202))
- **fix:** add dashboard-scoped typecheck gate covering src/app/(dashboard) TSX (#7033) ([#7203](https://github.com/diegosouzapw/OmniRoute/pull/7203))
- **fix(guardrails/chat):** stop Vision Bridge hijacking credentialed models to opencode-zen ([#7204](https://github.com/diegosouzapw/OmniRoute/pull/7204)) — thanks @artickc
- **fix(translator):** preserve Gemini thought parts as reasoning_content on the OpenAI bridge ([#7206](https://github.com/diegosouzapw/OmniRoute/pull/7206))
- **fix(translator):** register openai response projection for gemini clients ([#7207](https://github.com/diegosouzapw/OmniRoute/pull/7207))
- **fix(cli):** fast-path --version to skip full CLI bootstrap ([#7208](https://github.com/diegosouzapw/OmniRoute/pull/7208))
- **fix:** honor PROVIDER_LIMITS_SYNC_SPACING_MS for local/API-key connections (#6916) ([#7214](https://github.com/diegosouzapw/OmniRoute/pull/7214))
- **fix(api):** bulk-add API keys no longer overwrite existing connections ([#7234](https://github.com/diegosouzapw/OmniRoute/pull/7234))
- **fix(sse):** route the public OpenAI GPT-5.6 family through the Responses API ([#7242](https://github.com/diegosouzapw/OmniRoute/pull/7242))
- **fix(providers):** honor configured proxy on Grok Build egress ([#7244](https://github.com/diegosouzapw/OmniRoute/pull/7244))
- **fix(nvidia):** expand NIM chat model catalog ([#7247](https://github.com/diegosouzapw/OmniRoute/pull/7247))
- **fix(sse):** reconstruct Claude-format content in synthetic bypass responses ([#7248](https://github.com/diegosouzapw/OmniRoute/pull/7248))
- **fix(build):** isolate Windows HOME/AppData during next build ([#7249](https://github.com/diegosouzapw/OmniRoute/pull/7249))
- **fix(cli):** omniroute dashboard respects PORT env when --port is omitted (#7049) ([#7252](https://github.com/diegosouzapw/OmniRoute/pull/7252))
- **fix(sse):** project non-streaming JSON back to the Gemini/Antigravity envelope ([#7255](https://github.com/diegosouzapw/OmniRoute/pull/7255))
- **fix(combo):** fall back on Responses SSE failures ([#7256](https://github.com/diegosouzapw/OmniRoute/pull/7256)) — thanks @rushsinging
- **fix(routing):** resolve nested combo-ref panel members in fusion strategy (#6764) ([#7259](https://github.com/diegosouzapw/OmniRoute/pull/7259))
- **fix(usage):** reset logs and show provider names in analytics ([#7264](https://github.com/diegosouzapw/OmniRoute/pull/7264)) — thanks @SeaXen
- **fix(sse):** silence noisy proxy-failure log on caller-initiated abort ([#7266](https://github.com/diegosouzapw/OmniRoute/pull/7266))
- **fix(codex):** normalize nested Responses output content ([#7269](https://github.com/diegosouzapw/OmniRoute/pull/7269)) — thanks @JxnLexn
- **fix(combo):** derive session stickiness key from Responses API .input, not just .messages (#7270) ([#7277](https://github.com/diegosouzapw/OmniRoute/pull/7277)) — thanks @alltomatos
- **fix(antigravity):** wrap Pro fallback chain in try/catch for timeout resilience ([#7290](https://github.com/diegosouzapw/OmniRoute/pull/7290)) — thanks @HouMinXi
- **fix(logs):** show saved provider names in request/provider log views ([#7294](https://github.com/diegosouzapw/OmniRoute/pull/7294)) — thanks @SeaXen
- **fix(stream):** reconcile encrypted Codex reasoning visibility without mutating upstream item ([#7304](https://github.com/diegosouzapw/OmniRoute/pull/7304))
- **fix(build):** packed tarball boot crash — server-ws timeout import escaped the package (#7065 class) ([#7308](https://github.com/diegosouzapw/OmniRoute/pull/7308))
- **fix(skills):** register cli-skill-collector in the agent-skills catalog (Integration 2/2 base-red) ([#7310](https://github.com/diegosouzapw/OmniRoute/pull/7310))
- **fix(db):** tolerate unavailable virtual table modules in stats ([#7313](https://github.com/diegosouzapw/OmniRoute/pull/7313)) — thanks @megamen32
- **fix(router-eval):** retained-optimization gate cleanup ([#7318](https://github.com/diegosouzapw/OmniRoute/pull/7318)) — thanks @KooshaPari
- **fix(ci):** Coverage job timeout 10->20min (lcov reporter pushed it past the old cap) ([#7342](https://github.com/diegosouzapw/OmniRoute/pull/7342))
- **fix(electron):** normalize hashed standalone externals ([#7353](https://github.com/diegosouzapw/OmniRoute/pull/7353)) — thanks @tianrking
- **fix(db):** stop a 'latest' path segment from disabling backups and migrations ([#7359](https://github.com/diegosouzapw/OmniRoute/pull/7359)) — thanks @danscMax
- **fix(branding):** regenerate raster favicons — white mark was shipped without its gradient tile ([#7390](https://github.com/diegosouzapw/OmniRoute/pull/7390)) — thanks @vzts
- **fix(test):** skip real DNS writes in MITM dynamic-import test ([#7398](https://github.com/diegosouzapw/OmniRoute/pull/7398)) — thanks @HouMinXi
- **fix(antigravity):** streaming passthrough for non-streaming clients ([#7408](https://github.com/diegosouzapw/OmniRoute/pull/7408)) — thanks @HouMinXi
- **fix(build):** align engines.node with SUPPORTED_NODE_RANGE (#7446) ([#7490](https://github.com/diegosouzapw/OmniRoute/pull/7490)) — thanks @alltomatos
- **fix(api):** await params in Agent Bridge DNS route (Next.js 16) (#7271) ([#7492](https://github.com/diegosouzapw/OmniRoute/pull/7492)) — thanks @alltomatos
- **fix(dashboard):** show Obsidian context source card ([#7500](https://github.com/diegosouzapw/OmniRoute/pull/7500)) — thanks @DKotsyuba
- **fix(ci):** fetch full base history in pr-test-policy (shallow graft broke merge-base) ([#7501](https://github.com/diegosouzapw/OmniRoute/pull/7501))
- **fix(sse):** preserve chat quota across mixed windows ([#7504](https://github.com/diegosouzapw/OmniRoute/pull/7504)) — thanks @webmasterarbez
- **fix(oauth):** surface sanitized device-code error instead of a generic 500 ([#7511](https://github.com/diegosouzapw/OmniRoute/pull/7511)) — thanks @danscMax
- **fix(oauth):** repair qwen + codebuddy-cn device-code endpoints ([#7517](https://github.com/diegosouzapw/OmniRoute/pull/7517)) — thanks @danscMax
- **fix(mitm):** strip trailing assistant prefill to prevent upstream Anthropic 400 errors ([#7520](https://github.com/diegosouzapw/OmniRoute/pull/7520)) — thanks @chirag127
- **fix(codex):** Test probe uses a ChatGPT-account-supported model (#7521) ([#7524](https://github.com/diegosouzapw/OmniRoute/pull/7524))
- **fix(codex):** validate refresh_token on import before persisting (#7522) ([#7525](https://github.com/diegosouzapw/OmniRoute/pull/7525))
- **fix(codex):** non-stream chat 502 'Response body is already used' (single-reader peek) ([#7526](https://github.com/diegosouzapw/OmniRoute/pull/7526))
- **fix(oauth):** surface tunnel hint when Codex OAuth runs on a remote host (#7523) ([#7527](https://github.com/diegosouzapw/OmniRoute/pull/7527))
- **fix(sse):** preserve custom tool output images ([#7540](https://github.com/diegosouzapw/OmniRoute/pull/7540)) — thanks @loulanyue
- **fix(combo):** failover when upstream SSE is truncated mid-lifecycle ([#7545](https://github.com/diegosouzapw/OmniRoute/pull/7545)) — thanks @Chewji9875
- **fix(dashboard):** prefer public endpoint URLs ([#7547](https://github.com/diegosouzapw/OmniRoute/pull/7547)) — thanks @nguyenha935
- **fix(cli):** refresh runtime detection accurately ([#7552](https://github.com/diegosouzapw/OmniRoute/pull/7552)) — thanks @nguyenha935
- **fix(ui):** improve React Flow dark theme ([#7553](https://github.com/diegosouzapw/OmniRoute/pull/7553)) — thanks @nguyenha935
- **fix(i18n):** treat **MISSING** sync placeholders as absent in EN fallback (#7258) ([#7556](https://github.com/diegosouzapw/OmniRoute/pull/7556))
- **fix(cli):** Windows cert check/uninstall key off the real CA identity, not a hardcoded legacy host (#7275) ([#7557](https://github.com/diegosouzapw/OmniRoute/pull/7557))
- **fix(sse):** feed compression pipeline the authoritative vision capability (#7237) ([#7560](https://github.com/diegosouzapw/OmniRoute/pull/7560))
- **fix(dashboard):** providers model-name filter matches live/synced catalog (#7250) ([#7561](https://github.com/diegosouzapw/OmniRoute/pull/7561))
- **fix(db):** pre-init sql.js WASM ahead of any getDbInstance() consumer (#7288) ([#7562](https://github.com/diegosouzapw/OmniRoute/pull/7562))
- **fix(dashboard):** resolve costs page 500 from out-of-scope t() in TopListCard (#7272) ([#7564](https://github.com/diegosouzapw/OmniRoute/pull/7564))
- **fix(dashboard):** surface rate-limit warning on 429 chat-probe (#7284) ([#7565](https://github.com/diegosouzapw/OmniRoute/pull/7565))
- **fix(sse):** lazy-load playwright in claudeTurnstileSolver (#7265) ([#7566](https://github.com/diegosouzapw/OmniRoute/pull/7566))
- **fix(sse):** combo failover for OpenAI streams truncated without finish_reason (#7285) ([#7568](https://github.com/diegosouzapw/OmniRoute/pull/7568))
- **fix(cli):** reuse win32-aware locateCommand in tool-detector (#7279) ([#7569](https://github.com/diegosouzapw/OmniRoute/pull/7569))
- **fix(codex):** #7536 check content-type before touching response.body in peek ([#7570](https://github.com/diegosouzapw/OmniRoute/pull/7570))
- **fix(sse):** stop dropping tool_search and leaking OpenAI-only params in Responses->Chat translation ([#7571](https://github.com/diegosouzapw/OmniRoute/pull/7571))
- **fix(api):** resolve provider display name and dedup byModel on normalized key (#7534, #7535) ([#7573](https://github.com/diegosouzapw/OmniRoute/pull/7573))
- **fix(mitm):** route Claude Code standalone MITM traffic ([#7574](https://github.com/diegosouzapw/OmniRoute/pull/7574)) — thanks @dongwook-chan
- **fix(sse):** stop per-byte enumeration of binary image bytes in log redaction (#7297) ([#7576](https://github.com/diegosouzapw/OmniRoute/pull/7576))
- **fix(sse):** split effort/reasoning suffix off pinned cursor model ids (#7289) ([#7577](https://github.com/diegosouzapw/OmniRoute/pull/7577))
- **fix(chatgpt-web):** recognize update_content.messages[] celsius WS frames (#7357) ([#7578](https://github.com/diegosouzapw/OmniRoute/pull/7578))
- **fix(sse):** 401 model-not-supported lockout + sticky quota-exhausted release (#7268, #7387) ([#7580](https://github.com/diegosouzapw/OmniRoute/pull/7580))
- **fix(antigravity):** allow cloudcode envelope through messages guard ([#7582](https://github.com/diegosouzapw/OmniRoute/pull/7582)) — thanks @dongwook-chan
- **fix(sse):** sanitize empty-signature thinking blocks + hoist strict-provider system messages ([#7583](https://github.com/diegosouzapw/OmniRoute/pull/7583))
- **fix(sse):** honor per-model targetFormat override for zai/glm-coding-apikey (#7364) ([#7584](https://github.com/diegosouzapw/OmniRoute/pull/7584))
- **fix(sse):** clamp glm-4.6v max_tokens to the 32768 ceiling (#7364) ([#7585](https://github.com/diegosouzapw/OmniRoute/pull/7585))
- **fix(cli):** log Codex Responses WebSocket history/usage per logical turn, not per connection ([#7588](https://github.com/diegosouzapw/OmniRoute/pull/7588))
- **fix(providers):** derive static model catalogs for search providers from searchTypes ([#7589](https://github.com/diegosouzapw/OmniRoute/pull/7589))
- **fix(stream-readiness):** bump timeout for heavy Claude-format reasoning replicas ([#7612](https://github.com/diegosouzapw/OmniRoute/pull/7612)) — thanks @herjarsa
- **fix(translator):** synthesize tool call chunks from response.completed batched output ([#7613](https://github.com/diegosouzapw/OmniRoute/pull/7613)) — thanks @ekinnee
- **fix(embeddings):** add lmstudio to embedding provider registry ([#7614](https://github.com/diegosouzapw/OmniRoute/pull/7614)) — thanks @ekinnee
- **fix(combo):** auto-clear stale session pins and emit recovery hints on combo exhaustion ([#7625](https://github.com/diegosouzapw/OmniRoute/pull/7625)) — thanks @herjarsa
- **fix(providers):** unify connection and routing flows ([#7629](https://github.com/diegosouzapw/OmniRoute/pull/7629)) — thanks @nguyenha935
- **fix(db):** dedupe bulk-imported proxies by full credential tuple (#7594) ([#7644](https://github.com/diegosouzapw/OmniRoute/pull/7644)) — thanks @alltomatos
- **fix(api):** allow text-to-image on dual-modality models + revive HuggingFace image host ([#7648](https://github.com/diegosouzapw/OmniRoute/pull/7648)) — thanks @danscMax
- **fix(stryker):** add Microsoft Designer test to tap.testFiles ([#7659](https://github.com/diegosouzapw/OmniRoute/pull/7659))
- **fix(dashboard):** cut UI import chain from connection persist module (CI shard base-red) ([#7677](https://github.com/diegosouzapw/OmniRoute/pull/7677))
### 📚 Docs
- **docs(quality):** codify retry policy per runner + release-level drift rule (WS5.4/WS5.5) ([#7107](https://github.com/diegosouzapw/OmniRoute/pull/7107))
- **docs(troubleshooting):** document Avast/AVG README.md false positive (#5946) ([#7295](https://github.com/diegosouzapw/OmniRoute/pull/7295))
- **docs(perf):** add per-endpoint p50/p95/p99 latency + cost budget reference ([#7336](https://github.com/diegosouzapw/OmniRoute/pull/7336)) — thanks @KooshaPari
- **docs:** refresh revoked Discord invite + WhatsApp Brasil link ([#7604](https://github.com/diegosouzapw/OmniRoute/pull/7604))
- **docs(readme):** animated SVG for the 4-tier auto-fallback cascade ([#7615](https://github.com/diegosouzapw/OmniRoute/pull/7615))
- **docs:** sync provider count to 259 (unblocks docs-counts strict gate) ([#7616](https://github.com/diegosouzapw/OmniRoute/pull/7616))
- **docs(readme):** animate pool + combo ASCII blocks as SMIL SVG diagrams ([#7626](https://github.com/diegosouzapw/OmniRoute/pull/7626))
- **docs(readme):** animate CLI command list + compression flow as SMIL SVGs ([#7637](https://github.com/diegosouzapw/OmniRoute/pull/7637))
- **docs(readme):** replace free-tier budget mockup with animated SMIL card ([#7665](https://github.com/diegosouzapw/OmniRoute/pull/7665))
- **docs(readme):** standardize all README tables to full content width ([#7666](https://github.com/diegosouzapw/OmniRoute/pull/7666))
### 🧪 Tests & Quality
- **test(build):** derive pack-artifact closures for all npm-shipped entrypoints (#7065 class) ([#7081](https://github.com/diegosouzapw/OmniRoute/pull/7081))
- **test(dashboard):** dedicated regression guard for #6815 density guarantee ([#7291](https://github.com/diegosouzapw/OmniRoute/pull/7291))
- **test(ci):** make #6634 selfref guard hermetic — read file from disk, no git ref ([#7327](https://github.com/diegosouzapw/OmniRoute/pull/7327))
- **test(ci):** mock route bridge surfaces error message, not raw stack ([#7354](https://github.com/diegosouzapw/OmniRoute/pull/7354))
- **test(ci):** static body in codex e2e mock route bridge (CodeQL #737) ([#7558](https://github.com/diegosouzapw/OmniRoute/pull/7558))
- **test(ci):** exact-line assert in grok-build config test (CodeQL #740/#741) ([#7628](https://github.com/diegosouzapw/OmniRoute/pull/7628))
### 🔧 Chores / CI
- **chore(release):** gate the sync-back push on release-green --quick (WS0.3) ([#7083](https://github.com/diegosouzapw/OmniRoute/pull/7083))
- **chore(ci):** gate hygiene — secrets baseline 0, semgrep drop, hadolint (WS6/D3 + WS1.7) ([#7099](https://github.com/diegosouzapw/OmniRoute/pull/7099))
- **chore(ops):** runner-box janitor + operations runbook (WS3.3) ([#7115](https://github.com/diegosouzapw/OmniRoute/pull/7115))
- **chore(ci):** promote test:vitest:ui to blocking (suite green after #7127) ([#7147](https://github.com/diegosouzapw/OmniRoute/pull/7147))
- **chore(ci):** stop dependabot proposing typescript majors — peer-blocked by typescript-eslint ([#7306](https://github.com/diegosouzapw/OmniRoute/pull/7306))
- **chore(release):** script the 0a.0b PR re-home with a verified read-back ([#7312](https://github.com/diegosouzapw/OmniRoute/pull/7312))
- **chore(quality):** tighten the coverage ratchet to the CI's real numbers ([#7326](https://github.com/diegosouzapw/OmniRoute/pull/7326))
- **chore(ci):** make the Electron Windows leg advisory with bash stderr capture (first-run failure diagnosis) ([#7340](https://github.com/diegosouzapw/OmniRoute/pull/7340))
- **chore(deps):** bump actions/setup-node from 6 to 7 ([#7348](https://github.com/diegosouzapw/OmniRoute/pull/7348))
- **chore(deps):** bump codecov/codecov-action ([#7350](https://github.com/diegosouzapw/OmniRoute/pull/7350))
- **ci(release-green):** add a main-green arm to detect when main goes red ([#7355](https://github.com/diegosouzapw/OmniRoute/pull/7355))
- **chore(deps):** bump github/codeql-action/analyze from 4.37.0 to 4.37.1 ([#7641](https://github.com/diegosouzapw/OmniRoute/pull/7641))
- **chore(deps):** bump github/codeql-action/init from 4.37.0 to 4.37.1 ([#7642](https://github.com/diegosouzapw/OmniRoute/pull/7642))
- **chore(quality):** register #6672 test in stryker tap.testFiles (base-red unblock) ([#7652](https://github.com/diegosouzapw/OmniRoute/pull/7652))
- **chore(release):** merge-train box-speed suite + --fast mode ([#7670](https://github.com/diegosouzapw/OmniRoute/pull/7670))
### 🔀 Other
- [needs-vps] fix(electron): materialize Turbopack hashed-module symlinks during packaging (#6724, #6594) ([#6794](https://github.com/diegosouzapw/OmniRoute/pull/6794)) — thanks @huohua-dev
- [codex] Keep mode-pack weights consistent in auto fallback ranking ([#7008](https://github.com/diegosouzapw/OmniRoute/pull/7008)) — thanks @KooshaPari
- Explain effective auto-combo scoring weights ([#7087](https://github.com/diegosouzapw/OmniRoute/pull/7087)) — thanks @KooshaPari
- [needs-vps] fix(dashboard): add vision-capability toggle for custom OpenAI-compatible models ([#7124](https://github.com/diegosouzapw/OmniRoute/pull/7124))
- [needs-vps] fix(dashboard): align onboarding tier content ([#7125](https://github.com/diegosouzapw/OmniRoute/pull/7125)) — thanks @Wibias
- Use OpenAI chunks for early chat keepalives ([#7136](https://github.com/diegosouzapw/OmniRoute/pull/7136)) — thanks @KooshaPari
- Fix Codex Responses compression analytics ([#7273](https://github.com/diegosouzapw/OmniRoute/pull/7273)) — thanks @JxnLexn
- Add cache-aligned Live Zone compression ([#7280](https://github.com/diegosouzapw/OmniRoute/pull/7280)) — thanks @JxnLexn
- Fix routed target request parameters ([#7323](https://github.com/diegosouzapw/OmniRoute/pull/7323)) — thanks @JxnLexn
- deps: bump electron from 43.1.0 to 43.1.1 in /electron ([#7349](https://github.com/diegosouzapw/OmniRoute/pull/7349))
- deps: bump the development group with 8 updates ([#7351](https://github.com/diegosouzapw/OmniRoute/pull/7351))
- deps: bump the production group across 1 directory with 12 updates ([#7352](https://github.com/diegosouzapw/OmniRoute/pull/7352))
- Add per-connection Provider Quota visibility ([#7360](https://github.com/diegosouzapw/OmniRoute/pull/7360)) — thanks @JxnLexn
- Stream model health probes for slow providers ([#7377](https://github.com/diegosouzapw/OmniRoute/pull/7377)) — thanks @JxnLexn
- Refresh NVIDIA free metadata and detect catalog drift ([#7378](https://github.com/diegosouzapw/OmniRoute/pull/7378)) — thanks @JxnLexn
- Reject invalid output token budgets ([#7379](https://github.com/diegosouzapw/OmniRoute/pull/7379)) — thanks @JxnLexn
- Honor provider proxies for The Old LLM Vercel blocks ([#7380](https://github.com/diegosouzapw/OmniRoute/pull/7380)) — thanks @JxnLexn
- Restore proxy navigation and sidebar accordion state ([#7381](https://github.com/diegosouzapw/OmniRoute/pull/7381)) — thanks @JxnLexn
- Expose proxy controls for no-auth providers ([#7419](https://github.com/diegosouzapw/OmniRoute/pull/7419)) — thanks @JxnLexn
- Add reasoning-based model and effort routing ([#7607](https://github.com/diegosouzapw/OmniRoute/pull/7607)) — thanks @JxnLexn
### 🩹 Direct release-branch fixes (no PR — authorized base-red sweep, 2026-07-18)
- **fix(base-red):** full-suite realignment after the 102-PR merge campaign: two real production fixes (legacy `refresh_token` column healed before its index is created; `shouldSkipCloudSyncInitialization` no longer swaps its `(env, argv)` arguments) plus 13 test files, goldens, provider counts, and env docs realigned to the live-validated behavior of the merged PRs.
---
## [3.8.48] — 2026-07-13

2
CLAUDE.md
View File

@@ -35,7 +35,7 @@ For full test matrix, see `CONTRIBUTING.md` → "Running Tests". For deep archit
## Project at a Glance
**OmniRoute** — unified AI proxy/router. One endpoint, 250 LLM providers, auto-fallback.
**OmniRoute** — unified AI proxy/router. One endpoint, 268 LLM providers, auto-fallback.
| Layer | Location | Purpose |
| ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |

639
README.md
View File

@@ -6,18 +6,23 @@
# 🚀 OmniRoute — The Free AI Gateway
### Never stop coding. Connect every AI tool to **250 providers** — **90+ free** — through one endpoint.
<img src="./docs/diagrams/readme-hero.svg" width="100%" alt="OmniRoute — Never stop coding. Every AI tool → 268 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 268 AI providers · 90+ free tiers · ~1.6B free tokens/mo · 18 routing strategies · $0 to start."/>
**Plug Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini. Auto-fallback.**
<br/>
</div>
**RTK + Caveman compression saves 15–95% tokens. Never hit limits.**
<div align="center">
<br/>
# 💰 ~1.6B Free Tokens / Month
**~1.6B documented free tokens/month** — up to **~2.1B in your first month** with signup credits — aggregated across the free tiers, plus a long tail of permanently-free, no-cap providers, and the compression above stretches every one further. ([how we count →](docs/reference/FREE_TIERS.md#tldr--how-much-free-inference-does-omniroute-actually-aggregate))
</div>
<br/>
> Stacking free tiers by hand is painful — dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute aggregates the **documented** free tiers of **40+ provider pools / 500+ models** into one honest number and shows it live on the dashboard (`/dashboard/free-tiers`).
<img src="./docs/diagrams/free-tier-budget.svg" width="100%" alt="OmniRoute free-tier budget card: ~1.6B free tokens per month steady, up to ~2.1B in the first month with signup credits, from the documented free tiers of 40+ provider pools / 500+ models behind one endpoint. Honest pool-deduped math — each shared pool counted once (counting every rate limit 24/7 would read ~10B; not published), 15 providers ToS-flagged so you decide. Budget bar of the 21 countable free pools with per-model grid (Mistral Large 3 1B, GPT-4o mini 150M, LongCat 150M, Gemini 2.5 Flash 60M … Auto 25K), ~616M one-time first-month signup credits (vertex 300M, agentrouter 200M, predibase 25M, together 25M, glm-cn 20M, doubao 15M, ai21 10M, deepseek 5M, hyperbolic 5M), plus permanently-free no-token-cap providers (SiliconFlow, Z.AI GLM-Flash, Kilo, OpenCode Zen, baidu …) and a $10 OpenRouter top-up unlocking +24M/mo — surfaced separately so they never inflate the headline. Live used/remaining on /dashboard/free-tiers."/>
> 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)**.
<div align="center">
<h3>
@@ -29,26 +34,17 @@
<a href="https://trendshift.io/repositories/23589" target="_blank"><img src="https://trendshift.io/api/badge/repositories/23589" alt="diegosouzapw%2FOmniRoute | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
[![Star History Rank](https://api.star-history.com/badge?repo=diegosouzapw/OmniRoute&theme=dark)](https://www.star-history.com/diegosouzapw/omniroute)
</br>
[![250 AI Providers](https://img.shields.io/badge/250-AI_Providers-6C5CE7?style=for-the-badge)](#-250-ai-providers--90-free)
[![90+ Free](https://img.shields.io/badge/90%2B-Free_Tiers-00B894?style=for-the-badge)](#-250-ai-providers--90-free)
[![1.6B Free Tokens/mo](https://img.shields.io/badge/1.6B-Free_Tokens%2Fmo-00B894?style=for-the-badge)](docs/reference/FREE_TIERS.md)
[![Token Savings](https://img.shields.io/badge/up_to_95%25-Token_Savings-E17055?style=for-the-badge)](#%EF%B8%8F-save-1595-tokens--automatically)
[![18 Strategies](https://img.shields.io/badge/18-Routing_Strategies-0984E3?style=for-the-badge)](#-combos--the-flagship)
[![$0 to start](https://img.shields.io/badge/%240-To_Start-FDCB6E?style=for-the-badge&logoColor=black)](#-quick-start)
<br/>
### 💬 Join the community
[![Discord](https://img.shields.io/badge/Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/EkzRkpzKYt)
[![Discord](https://img.shields.io/badge/Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/U47eFqAXCn)
[![Telegram](https://img.shields.io/badge/Telegram-26A5E4?style=for-the-badge&logo=telegram&logoColor=white)](https://t.me/omnirouteOficial)
[![WhatsApp Global](https://img.shields.io/badge/WhatsApp_Global-25D366?style=for-the-badge&logo=whatsapp&logoColor=white)](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
[![WhatsApp Brasil](https://img.shields.io/badge/WhatsApp_Brasil-25D366?style=for-the-badge&logo=whatsapp&logoColor=white)](https://chat.whatsapp.com/BTGJXIyjeNIIgExvTMGGhI)
[![WhatsApp Brasil](https://img.shields.io/badge/WhatsApp_Brasil-25D366?style=for-the-badge&logo=whatsapp&logoColor=white)](https://chat.whatsapp.com/LTSpdFhXTxjH4R6CCNiKWz)
[![Website](https://img.shields.io/badge/Website-omniroute.online-blue?logo=google-chrome&logoColor=white)](https://omniroute.online)
**Questions, provider tips, roadmap & support → [Discord](https://discord.gg/EkzRkpzKYt) · [Telegram](https://t.me/omnirouteOficial) · WhatsApp [🌍 Global](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t) / [🇧🇷 Brasil](https://chat.whatsapp.com/BTGJXIyjeNIIgExvTMGGhI)**
**Questions, provider tips, roadmap & support → [Discord](https://discord.gg/U47eFqAXCn) · [Telegram](https://t.me/omnirouteOficial) · WhatsApp [🌍 Global](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t) / [🇧🇷 Brasil](https://chat.whatsapp.com/LTSpdFhXTxjH4R6CCNiKWz)**
<br/>
@@ -61,14 +57,14 @@
![Docker Pulls](https://img.shields.io/docker/pulls/diegosouzapw/omniroute?label=docker%20pulls&logo=docker&color=2496ED)
![Electron Downloads](https://img.shields.io/github/downloads/diegosouzapw/omniroute/total?style=flat&label=electron%20downloads&logo=electron&color=47848F)
[**🚀 Quick Start**](#-quick-start) • [**🎯 Combos**](#-combos--the-flagship) • [**🌐 Providers**](#-250-ai-providers--90-free) • [**🔌 CLI & MCP**](#-full-cli--a2a--mcp) • [**🗜️ Compression**](#%EF%B8%8F-save-1595-tokens--automatically) • [**🌍 Website**](https://omniroute.online)
[**🚀 Quick Start**](#-quick-start) • [**🎯 Combos**](#-combos--the-flagship) • [**🌐 Providers**](#-268-ai-providers--90-free) • [**🔌 CLI & MCP**](#-full-cli--a2a--mcp) • [**🗜️ Compression**](#%EF%B8%8F-save-1595-tokens--automatically) • [**🌍 Website**](https://omniroute.online)
[💥 The Promise](#-the-promise) • [🤔 Why](#-why-omniroute) • [🏆 What Sets Apart](#-what-sets-omniroute-apart) • [🤖 Compatible CLIs](#-compatible-clis--coding-agents) • [🖥️ Where It Runs](#%EF%B8%8F-where-omniroute-runs--anywhere) • [🔒 Private](#-private--local-first) • [🎬 In Action](#-omniroute-in-action) • [📚 Explore More](#-explore-more) • [📧 Support](#-support--community)
[💥 The Promise](#-the-promise) • [🤔 Why](#-why-omniroute) • [🏆 What Sets Apart](#-what-sets-omniroute-apart) • [🤖 Compatible CLIs](#-compatible-clis--coding-agents) • [🖥️ Where It Runs](#%EF%B8%8F-where-omniroute-runs--anywhere) • [🔒 Private](#-private--local-first) • [🎬 In Action](#-omniroute-in-action) • [📸 Screenshots](#-dashboard-screenshots) • [📧 Support](#-support--community)
</div>
<div align="center">
<b>🌐 In 42+ languages</b>
<b>🌐 In 43 languages</b>
<table>
<tr>
<td align="center"><a href="README.md">🇺🇸</a></td>
@@ -122,47 +118,13 @@
</table>
</div>
<br/>
<div align="center">
# 💰 ~1.6B 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 aggregates the **documented** free tiers of **40+ provider pools / 500+ models** into one honest number and shows it live on the dashboard (`/dashboard/free-tiers`).
- **~1.6B free tokens / month** (steady) — and **up to ~2.1B in your first month** with signup credits.
- **Pool-deduped, honest** — we count each shared free pool **once**, so the headline isn't inflated by rate-limit ceilings the way multi-billion competitor claims are. (Counting every rate limit 24/7 would read ~10B; we don't publish that.)
- **Plus the un-countable** — permanently-free, no-token-cap providers (SiliconFlow, Z.AI GLM-Flash, Kilo, OpenCode Zen…) and a **$10 OpenRouter top-up** that unlocks **+24M/mo**, both surfaced separately so they never inflate the headline.
- **Per-model breakdown**, **live used / remaining** for the current month, and a transparent **terms flag** per provider.
![Free-Tier Budget card (preview mockup)](docs/screenshots/free-tier-budget-card.svg)
> Preview mockup — a real screenshot lands once the `/dashboard/free-tiers` page is validated. Full methodology (pool dedupe, credit tiers, provider terms): **[docs/reference/FREE_TIERS.md](docs/reference/FREE_TIERS.md)**.
<br/>
<div align="center">
# 💥 The Promise
</div>
> One endpoint. **250 providers.** Never stop building — and let OmniRoute pick the cheapest one that works.
<table>
<tr>
<td width="33%" valign="top"><b>🚫 Never hit limits</b><br/><sub>Auto-fallback across 250 providers in milliseconds. Quota out? Next provider takes over — zero downtime.</sub></td>
<td width="33%" valign="top"><b>💸 Save up to 95% tokens</b><br/><sub>RTK + Caveman stacked compression cuts 15–95% of eligible tokens (~89% avg on tool-heavy sessions).</sub></td>
<td width="33%" valign="top"><b>🆓 $0 to start</b><br/><sub>90+ providers with a free tier, 11 free <i>forever</i> (Kiro, Qoder, Pollinations, LongCat…). No card needed.</sub></td>
</tr>
<tr>
<td width="33%" valign="top"><b>🔌 Every tool works</b><br/><sub>24+ coding agents — Claude Code, Codex, Cursor, Cline, Copilot, Antigravity — through one config.</sub></td>
<td width="33%" valign="top"><b>🧩 One endpoint</b><br/><sub>OpenAI ↔ Claude ↔ Gemini ↔ Responses API translation. Point any tool at <code>/v1</code> and it just works.</sub></td>
<td width="33%" valign="top"><b>🛡️ Production-grade</b><br/><sub>Circuit breakers, TLS stealth, MCP (94 tools), A2A, memory, guardrails, evals. 21,000+ tests.</sub></td>
</tr>
</table>
<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint. 268 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 268 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 40+ free forever — no card needed) · Every tool works (26 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 104 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
<br/>
<br/>
@@ -173,37 +135,11 @@
</div>
> Stop juggling 10 dashboards, dead API keys, and surprise bills.
| ❌ The daily pain | ✅ How OmniRoute fixes it |
| ------------------------------------------------------ | ----------------------------------------------------------------------------- |
| 📉 Subscription quota expires unused every month | **Maximize subscriptions** — track quota, use every token before reset |
| 🛑 Rate limits stop you mid-coding | **4-tier auto-fallback** — Subscription → API → Cheap → Free, in milliseconds |
| 🔥 Tool outputs (`git diff`, `grep`, logs) burn tokens | **RTK + Caveman compression** — save 15–95% eligible tokens per request |
| 💸 Expensive APIs ($20–50/mo per provider) | **Cost-optimized routing** — auto-route to the cheapest viable model |
| 🧰 Each AI tool wants its own setup | **One endpoint, every tool, one dashboard** |
| 🌍 AI blocked in your country | **3-level proxy** + TLS fingerprint stealth — use AI from anywhere |
<img src="./docs/diagrams/why-pain-fix.svg" width="100%" alt="Why OmniRoute — stop juggling 10 dashboards, dead API keys and surprise bills. Ten daily pains vs fixes: quota expiring unused → maximize subscriptions; rate limits mid-coding → 4-tier auto-fallback (Subscription → API → Cheap → Free); tool outputs burning tokens → RTK + Caveman compression (15–95%); expensive APIs → cost-optimized routing; every tool its own setup → one endpoint, one dashboard; AI blocked → 3-level proxy + TLS stealth; dead keys → 3-layer resilience (circuit breakers, key cooldown, model lockout); team sharing one subscription → key pools with fair-share quotas; prompts through someone's cloud → local-first with AES-256-GCM encrypted keys; no spend visibility → live analytics (usage, quota, savings, p95 latency)."/>
<div align="center">
```
┌──────────────────────────────────────────────────────────┐
│ Your IDE / CLI (Claude Code, Cursor, Cline…) │
└─────────────────────────┬──────────────────────────────────┘
│ http://localhost:20128/v1
▼
┌──────────────────────────────────────────────────────────┐
│ OmniRoute — Smart Router │
│ RTK + Caveman compression · 18 routing strategies │
│ Circuit breakers · TLS stealth · MCP · A2A · Guardrails │
└─────────────────────────┬──────────────────────────────────┘
┌─────────────┬────┴────────┬─────────────┐
▼ Tier 1 ▼ Tier 2 ▼ Tier 3 ▼ Tier 4
SUBSCRIPTION API KEY CHEAP FREE
Claude Code, DeepSeek, GLM $0.5, Kiro, Qoder,
Codex, Copilot Groq, xAI MiniMax $0.2 Pollinations
quota out? ───▶ budget hit? ─▶ budget hit? ─▶ always on
```
<img src="./docs/diagrams/tier-cascade.svg" width="100%" alt="OmniRoute request flow: your IDE or CLI (Claude Code, Cursor, Cline…) calls one local endpoint (http://localhost:20128/v1); the OmniRoute Smart Router (RTK + Caveman compression, 18 routing strategies, circuit breakers, TLS stealth, MCP, A2A, guardrails) auto-falls back across 4 provider tiers — Tier 1 Subscription (Claude Code, Codex, Copilot), quota out? Tier 2 API Key (DeepSeek, Groq, xAI), budget hit? Tier 3 Cheap (GLM $0.5, MiniMax $0.2), budget hit? Tier 4 Free (Kiro, Qoder, Pollinations) — always on."/>
</div>
@@ -221,14 +157,14 @@
No combo to create. Set your model to `auto` (or a variant) and OmniRoute builds a virtual combo from your connected providers, scored live:
| Model ID | What it optimizes for |
| -------------- | -------------------------------------------------------------- |
| `auto` | 🎯 Balanced default (LKGP — sticks to your last good provider) |
| `auto/coding` | 🧑‍💻 Quality-first weights for code generation |
| `auto/fast` | ⚡ Lowest latency first |
| `auto/cheap` | 💰 Cheapest per token first |
| `auto/offline` | 🔋 Most quota / rate-limit headroom first |
| `auto/smart` | 🔭 Quality-first + 10% exploration to discover better models |
| Model ID | What it optimizes for                                                                                                                                                                  |
| -------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `auto` | 🎯 Balanced default (LKGP — sticks to your last good provider) |
| `auto/coding` | 🧑‍💻 Quality-first weights for code generation |
| `auto/fast` | ⚡ Lowest latency first |
| `auto/cheap` | 💰 Cheapest per token first |
| `auto/offline` | 🔋 Most quota / rate-limit headroom first |
| `auto/smart` | 🔭 Quality-first + 10% exploration to discover better models |
##
@@ -236,26 +172,28 @@ No combo to create. Set your model to `auto` (or a variant) and OmniRoute builds
All **18** strategies — mix & match per combo step:
| # | Strategy | What it does |
| --- | ------------------- | ---------------------------------------------------------------- |
| 1 | `priority` | First-target ordered list — drain each before the next 🥇 |
| 2 | `fill-first` | Fill each target's quota fully before moving on |
| 3 | `weighted` | Weighted random by per-target weight |
| 4 | `round-robin` | Cycle through targets in order |
| 5 | `p2c` | Power-of-two-choices random load balancing |
| 6 | `least-used` | Pick the target with the lowest current load |
| 7 | `random` | Uniform random pick (deduplicated) |
| 8 | `strict-random` | Random without de-duplicating repeats 🎲 |
| 9 | `cost-optimized` | Minimize $ per request from live catalog pricing 💸 |
| 10 | `headroom` | Pick the target with the most remaining quota |
| 11 | `reset-window` | Prefer the target whose quota window resets soonest |
| 12 | `reset-aware` | Rank by quota reset time — short windows first 📊 |
| 13 | `context-relay` | Hand off context across targets for long conversations 🧠 |
| 14 | `context-optimized` | Pick the best fit for the current context size |
| 15 | `lkgp` | Last-Known-Good Path — sticky to the last successful target |
| 16 | `auto` | 12-factor live scoring across every connection 🤖 |
| 17 | `fusion` | Fan out to a panel of models + a judge synthesizes one answer 🧬 |
| 18 | `pipeline` | Chain steps — each target's output feeds the next one 🔗 |
| # | Strategy | What it does                                                                                                                                                             |
| --- | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| 1 | `priority` | First-target ordered list — drain each before the next 🥇 |
| 2 | `fill-first` | Fill each target's quota fully before moving on |
| 3 | `weighted` | Weighted random by per-target weight |
| 4 | `round-robin` | Cycle through targets in order |
| 5 | `p2c` | Power-of-two-choices random load balancing |
| 6 | `least-used` | Pick the target with the lowest current load |
| 7 | `random` | Uniform random pick (deduplicated) |
| 8 | `strict-random` | Random without de-duplicating repeats 🎲 |
| 9 | `cost-optimized` | Minimize $ per request from live catalog pricing 💸 |
| 10 | `headroom` | Pick the target with the most remaining quota |
| 11 | `reset-window` | Prefer the target whose quota window resets soonest |
| 12 | `reset-aware` | Rank by quota reset time — short windows first 📊 |
| 13 | `context-relay` | Hand off context across targets for long conversations 🧠 |
| 14 | `context-optimized` | Pick the best fit for the current context size |
| 15 | `lkgp` | Last-Known-Good Path — sticky to the last successful target |
| 16 | `auto` | 12-factor live scoring across every connection 🤖 |
| 17 | `fusion` | Fan out to a panel of models + a judge synthesizes one answer 🧬 |
| 18 | `pipeline` | Chain steps — each target's output feeds the next one 🔗 |
<img src="./docs/diagrams/strategies-grid.svg" width="100%" alt="All 18 combo routing strategies animated, one tile per strategy showing the flow it executes: priority (drain the 1st, then the next), fill-first (fill a target's quota, then move on), weighted (weighted random), round-robin (cycle in order), p2c (pick 2, take the lighter), least-used (lowest load wins), random (uniform, deduped), strict-random (repeats allowed), cost-optimized (cheapest $ per request), headroom (most remaining quota), reset-window (resets soonest → use it), reset-aware (rank by reset, short first), context-relay (hand off long context), context-optimized (fit the context size), lkgp (sticky to last success), auto (live 12-factor scoring), fusion (panel + judge → one answer), pipeline (each output feeds the next)."/>
<sub>The Auto-Combo engine scores every candidate on **12 factors** (health, quota, cost, latency, success rate, freshness…) — see [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md).</sub>
@@ -265,21 +203,14 @@ All **18** strategies — mix & match per combo step:
> Running several keys against the **same upstream account** (one Codex Pro plan, one Kimi key, one GLM Coding seat)? A burst on one key can burn the whole 5-hour / hourly quota and lock everyone else out. **Quota-Share** distributes a provider's time-based quota **fairly** across the keys in a pool — and it's _work-conserving_, so an idle member's slice is lent out instead of wasted.
| Knob | What it controls |
| ------------------------ | ------------------------------------------------------------------------------- |
| ⚖️ **Allocation weight** | each key's slice of the pool — e.g. `50 / 30 / 20` |
| 📐 **Dimensions** | track `%` · requests · tokens · `$`, per **5h / 7d / per-model** window |
| 🚦 **Policy** | `hard` (block over share) · `soft` (deprioritize) · `burst` (use idle headroom) |
| 🧱 **Cap** | absolute ceiling per key, independent of mode |
| Knob | What it controls                                                                                                                                                              |
| ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| ⚖️ **Allocation weight** | each key's slice of the pool — e.g. `50 / 30 / 20` |
| 📐 **Dimensions** | track `%` · requests · tokens · `$`, per **5h / 7d / per-model** window |
| 🚦 **Policy** | `hard` (block over share) · `soft` (deprioritize) · `burst` (use idle headroom) |
| 🧱 **Cap** | absolute ceiling per key, independent of mode |
```
Pool "team-codex" · 1 Codex Pro account · 3 keys · 5-hour window
├─ alice weight 50 ██████████░░░░░░░░░░ ≤ 50% of the shared 5h quota
├─ bob weight 30 ██████░░░░░░░░░░░░░░ ≤ 30%
└─ ci-bot weight 20 ████░░░░░░░░░░░░░░░░ ≤ 20%
Generous mode (<50% pool used) → idle shares are lent out
Strict mode (≥50% pool used) → each key held to its fair share
```
<img src="./docs/diagrams/pool-fair-share.svg" width="100%" alt="OmniRoute key pool 'team-codex': one Codex Pro account shared by 3 keys over a 5-hour window. alice weight 50 (up to 50% of the shared 5h quota), bob weight 30, ci-bot weight 20. In generous mode (under 50% pool used) idle shares are lent out; once the pool crosses 50% strict mode holds each key to its fair share."/>
<sub>Enforced in the hot path **before** the request leaves OmniRoute, with per-(key, model) caps + session stickiness for prompt-cache integrity (now with a per-combo / global disable toggle). 📖 [Quota Sharing Engine](docs/routing/QUOTA_SHARE.md)</sub>
@@ -287,20 +218,7 @@ Strict mode (≥50% pool used) → each key held to its fair share
### 🧱 Resilience is built in (3 independent layers)
| Layer | Scope | What it does |
| -------------------------- | ----------------- | -------------------------------------------------------------------------- |
| 🔌 **Circuit breaker** | whole provider | Stops hammering a provider that's failing upstream; auto-probes to recover |
| 💤 **Connection cooldown** | one account / key | Skips a rate-limited key while other keys keep serving |
| 🎯 **Model lockout** | provider + model | Quarantines just one quota-limited model, not the whole connection |
```
Combo: "always-on" Strategy: priority
1. cc/claude-opus-4-7 ← subscription (use it fully)
2. cx/gpt-5.5 ← second subscription
3. glm/glm-5.1 ← cheap backup ($0.5/1M)
4. kr/claude-sonnet-4.5 ← FREE, unlimited (never fails)
Result: 4 layers of fallback = zero downtime
```
<img src="./docs/diagrams/resilience-layers.svg" width="100%" alt="OmniRoute resilience — 3 independent self-healing layers, the right layer for the right failure. Layer 1 provider circuit breaker (whole provider): trips only on 408/5xx, thresholds OAuth 3× / API-key 5× / local 2×, resets 60s/30s/15s into a HALF-OPEN probe, lazy recovery; while OPEN the combo reroutes to the next provider. Layer 2 connection cooldown (one key/account): base 5s OAuth / 3s API-key, exponential ×2 backoff with anti-thundering-herd guard, 429 honors Retry-After, success clears all error state; one cooling key is skipped while sibling keys keep serving. Layer 3 model lockout (one model): per-model 429, local 404 or mode denials lock just that model — never the whole connection. Terminal states (banned, expired, credits exhausted) are for the operator, not cooldowns."/>
<sub>📖 [Auto-Combo Engine](docs/routing/AUTO-COMBO.md) · [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md)</sub>
@@ -314,18 +232,18 @@ Result: 4 layers of fallback = zero downtime
| Feature | OmniRoute | Other routers |
| -------------------------------------- | ------------------------------------------------------------------- | ------------- |
| 🌐 Providers | **250** | 20–100 |
| 🆓 Free providers | **90+ (11 free forever)** | 1–5 |
| 🌐 Providers | **268** | 20–100 |
| 🆓 Free providers | **90+ (40+ free forever)** | 1–5 |
| 🔀 Routing strategies | **18** (priority, weighted, cost-optimized, context-relay, fusion…) | 1–3 |
| 🗜️ Token compression | **RTK + Caveman stacked (15–95%)** | None / 20–40% |
| 🧰 Built-in MCP server | **94 tools, 3 transports, 30 scopes** | Rare |
| 🧰 Built-in MCP server | **104 tools, 3 transports, 30 scopes** | Rare |
| 🤝 A2A agent protocol | **6 skills, JSON-RPC 2.0** | None |
| 🧠 Memory (FTS5 + vector) | **Yes** | Rare |
| 🛡️ Guardrails (PII, injection, vision) | **Yes** | Rare |
| ☁️ Cloud agents | **Codex, Cursor, Devin, Jules** | None |
| 🥷 TLS fingerprint stealth | **JA3/JA4 via wreq-js** | None |
| 🖥️ Multi-platform | **Web · Desktop · Termux · PWA** | Web only |
| 🌍 i18n | **42 locales** | 0–4 |
| 🌍 i18n | **43 locales** | 0–4 |
<sub>📊 Detailed comparison vs LiteLLM, OpenRouter & Portkey → [`docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`](docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md)</sub>
@@ -337,23 +255,23 @@ Result: 4 layers of fallback = zero downtime
</div>
> Recent highlights from **v3.8.20 → v3.8.47**. Full history in [`CHANGELOG.md`](CHANGELOG.md).
> Recent highlights from **v3.8.20 → v3.8.49**. Full history in [`CHANGELOG.md`](CHANGELOG.md).
- **🗜️ Compression hardening** — a default-on **inflation guard** (discard the stacked result and send the verbatim original whenever compression would _grow_ the prompt), completed **Caveman rule packs** for German / French / Japanese (dedup + ultra) plus a new **Chinese (文言 / wényán) input pack** with zh-vs-ja auto-detection, and **RTK filters for Gradle & .NET (`dotnet`)** build output. → [Compression](docs/compression/COMPRESSION_ENGINES.md)
- **💸 Honest flat-rate cost** — subscription / coding-plan providers (ChatGPT Web, grok-web, the Minimax / Kimi / GLM / Alibaba Coding plans, Xiaomi MiMo…) now read **$0** in cost analytics instead of an inflated per-token estimate, while budget / quota / routing keep estimating unchanged. → [API Reference](docs/reference/API_REFERENCE.md)
- **⚖️ Quota-Share routing** — a dedicated combo strategy that spreads load across accounts by _available quota_: Deficit-Round-Robin scheduling, per-connection `max_concurrent` with cooldown-wait queueing, multi-window usage buckets (5h / 7d / per-model), per-(key, model) caps, session stickiness for prompt-cache integrity (now with a per-combo / global disable toggle), and proactive saturation from upstream token-usage headers. → [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md)
- **🤖 One-command CLI/agent setup** — a dedicated `setup-*` command configures each coding tool to route through OmniRoute (Claude Code, Codex, Cline, Continue, Cursor, Roo Code, Kilo Code, Crush, Goose, Qwen Code, Aider, OpenCode); `omniroute launch` / `omniroute launch-codex` are zero-config launchers. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
- **🛰️ Remote mode** — drive a remote OmniRoute from any machine with scoped access tokens (`omniroute connect` / `omniroute contexts` / `omniroute tokens`), plus an `omniroute login antigravity` helper that runs Google "native/desktop" OAuth on your own machine and pastes a credential blob into a remote/VPS install (where the loopback redirect is unreachable). → [Remote Mode](docs/guides/REMOTE-MODE.md)
- **🧭 Smarter auto-routing** — OpenRouter-style `auto/<category>:<tier>` combos (e.g. `auto/coding:fast`, `auto/reasoning:pro`), a **Fusion** strategy (fan out to a panel of models in parallel, then synthesize via a judge), **task-aware routing** (best-fit connection per task type), per-request `X-Route-Model` override, live Arena-ELO + models.dev model intelligence, per-step account allowlists, provider-wildcard combo steps, nested combo-ref execution, sticky weighted selection, `web_search`-aware routing (now with **per-model web-search/web-fetch interception rules**), native **xAI Grok `/v1/responses`** routing, and **per-request Auto-Combo controls** (`X-OmniRoute-Mode` mode-preset override + `X-OmniRoute-Budget` hard USD cost ceiling, scoped to a single request). Embeddings-only and rerank-only models (JinaAI, OpenRouter custom, reranker models…) no longer disappear from the combo builder's model picker. → [Auto-Combo](docs/routing/AUTO-COMBO.md)
- **🗜️ Pluggable compression** — an async pipeline of **10 composable engines** with Compression Studios, an LLMLingua-2 ONNX engine and a heuristic/SLM two-tier **Ultra**, RTK, delegated Anthropic Context Editing, **Output Styles** (output-axis steering: terse-prose / less-code / terse-CJK), an **adaptive context-budget dial** (escalate only as far as needed to fit the context window), per-request `x-omniroute-compression` control, an opt-in offline eval harness, one-click **Headroom** proxy lifecycle management from the dashboard (Docker sidecar supported), a synthetic **compression playground** (Play lanes + A/B Compare with USD-capped fidelity verdicts), an opt-in **per-step fidelity gate** that rejects a lossy engine before it degrades the prompt, a **best-of-N candidate encoder** (GCF vs TOON — keep whichever is shorter, with an A/B bytes/token table in the studio), the vendored **GCF codec updated to spec v3.2** (nested flattening — deeply-nested payloads go from ~3% to ~32% compression vs JSON), a new **omniglyph** engine (context-as-image, ~10× fewer tokens on the converted block), **CCR ranged/grep/stats retrieval** (pull an exact byte/line slice or summary of a stored block instead of re-expanding it), a unified panel with named profiles + an active-profile selector, an opt-in **per-engine pipeline circuit-breaker**, an opt-in **LLM-tier engine** (a model pass for higher-ratio semantic compression), a **read-lifecycle engine** that collapses superseded file reads, **usage-observed prefix freeze**, a graduated **CCR retrieval-feedback ramp**, a `preserveSystemPrompt` mode enum, and a **drag-reorder pipeline editor** in the studio. → [Compression](docs/compression/COMPRESSION_ENGINES.md)
- **🕵️ Transparent MITM decrypt (TPROXY)** — capture & translate traffic from CLIs that ignore proxy env vars, with a per-SNI certificate authority and a trust-store installer. → [MITM/TPROXY](docs/security/MITM-TPROXY-DECRYPT.md)
- **💸 Cost telemetry everywhere** — `X-OmniRoute-*` cost/usage headers on every endpoint (including media), a non-token cost engine, a cache-HIT `X-OmniRoute-Cost-Saved` header, and per-key USD spend quotas. → [API Reference](docs/reference/API_REFERENCE.md)
- **🧠 Memory you control** — opt-in int8 vector quantization (Qdrant + sqlite-vec), opt-in **typed memory decay** (aged low-value memories fade on a per-type schedule), memory off by default, and a per-request `x-omniroute-no-memory` header. → [Memory](docs/frameworks/MEMORY.md)
- **🛡️ Security** — a prompt-injection guard across every LLM route (backed by a red-team suite), plus a free DuckDuckGo last-resort web search. → [Guardrails](docs/security/GUARDRAILS.md)
- **🖼️ New endpoints** — `/v1/ocr` (Mistral OCR) and `/v1/audio/translations` (Whisper-style audio translation) round out the media API surface. → [API Reference](docs/reference/API_REFERENCE.md)
- **🌍 Deployment & ops** — reverse-proxy `basePath` deployment (`OMNIROUTE_BASE_PATH`, e.g. serving OmniRoute under `/omniroute/`), browser-language auto-detect on first visit, per-API-key device/connection tracking (IP+UA fingerprint, masked, in-memory only), root-less MITM cert trust for user-namespaced containers (`OMNIROUTE_NO_SUDO`), server-side configured-only / available-only filters on the Free Provider Rankings page, and **Traditional Chinese (zh-TW)** localization for the frontend + CLI. → [Environment](docs/reference/ENVIRONMENT.md)
- **🤝 More providers & agents** — Cursor Cloud Agent (a 4th cloud agent), CodeBuddy CN (`copilot.tencent.com`), a Google Flow video-generation provider, new gateways **DGrid** and **Pioneer AI** (Fastino Labs), inbound **xAI Grok** translators plus **Grok Build (xAI)** with an OAuth import-token flow, GPT-4 / GPT-4o-mini on the GitHub Copilot provider, multi-model **Factory Droid**, **ZenMux Free** (session-cookie free tier), **Alibaba DashScope** text-to-video (`wan2.7-t2v`), a refreshed 250-provider catalog (OrcaRouter, Wafer AI, OpenAdapter, dit.ai, TokenRouter, …), Vertex AI media generation (speech/transcription/music/video), a first-class **Ollama** local-provider card, the **SenseNova** free Token Plan (chat + text-to-image), one-click account import from CLIProxyAPI (`~/.cli-proxy-api/`), **Claude Sonnet 5** wired end-to-end, a new provider wave (**Kenari**, **SumoPod**, **X5Lab**, **Charm Hyper**, **Nube.sh**, **b.ai**, **Qiniu**, **ModelScope**, **Augment/Auggie CLI**, **ClinePass**, NVIDIA NIM image generation), Codex account import from a raw ChatGPT access token, the **Requesty** gateway (BYOK, ~200 free req/day), **Yuanbao (web)** as a cookie-session provider (DeepSeek V3/R1 + Hunyuan), the **Zed** hosted LLM aggregator (OAuth), **Claude 5 Sonnet** on the Claude Web provider, Kiro **adaptive-thinking reasoning** surfaced as `reasoning_content`, **bulk API-key add for Cloudflare Workers AI**, and **OpenVecta** (AI inference gateway). → [Providers](docs/reference/PROVIDER_REFERENCE.md)
- **⚡ Local performance & infra** — a one-click local Redis launcher (`omniroute redis up`, plus a dashboard Redis panel), one-click **Cloudflare Workers** and **Deno Deploy** relay deployers wired into the proxy pool, a relay-backend selector (`OMNIROUTE_RELAY_BACKEND=ts|bifrost|auto`) so `/v1/relay` stays the stable surface while choosing the fastest backend internally, **Bifrost** (Go AI-gateway) and **Mux** (agent-orchestration daemon) promoted to first-class embedded/supervised services alongside 9Router/CLIProxyAPI, **Webshare** added as a paid fourth source in the free-proxy provider framework, and **shorthand proxy formats + protocol header mode** for bulk proxy import. → [Embedded Services](docs/frameworks/EMBEDDED-SERVICES.md)
- **🗜️ Compression hardening** — default-on inflation guard, Caveman packs for DE / FR / JA + Chinese (wényán), RTK filters for Gradle & .NET. → [Compression](docs/compression/COMPRESSION_ENGINES.md)
- **💸 Honest flat-rate cost** — subscription / coding-plan providers read **$0** in cost analytics; budget, quota & routing keep estimating. → [API Reference](docs/reference/API_REFERENCE.md)
- **⚖️ Quota-Share routing** — split load across accounts by _available quota_: DRR scheduling, per-connection concurrency, multi-window buckets, session stickiness. → [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md)
- **🤖 One-command CLI/agent setup** — `setup-*` configures 12+ coding tools; `omniroute launch` / `launch-codex` are zero-config. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
- **🛰️ Remote mode** — drive a remote OmniRoute with scoped tokens (`connect` / `contexts` / `tokens`) + an `antigravity` OAuth helper for VPS installs. → [Remote Mode](docs/guides/REMOTE-MODE.md)
- **🧭 Smarter auto-routing** — `auto/<category>:<tier>` combos, **Fusion** (model panel + judge), task-aware routing, per-request model / mode / USD-budget overrides. → [Auto-Combo](docs/routing/AUTO-COMBO.md)
- **🗜️ Pluggable compression** — 10 composable engines + Compression Studios: LLMLingua-2, two-tier Ultra, omniglyph, per-step fidelity gate, GCF v3.2, drag-reorder editor. → [Compression](docs/compression/COMPRESSION_ENGINES.md)
- **🕵️ Transparent MITM decrypt (TPROXY)** — capture CLIs that ignore proxy env vars, with a per-SNI CA + trust-store installer. → [MITM/TPROXY](docs/security/MITM-TPROXY-DECRYPT.md)
- **💸 Cost telemetry everywhere** — `X-OmniRoute-*` cost/usage headers on every endpoint, cache-HIT savings header, per-key USD spend quotas. → [API Reference](docs/reference/API_REFERENCE.md)
- **🧠 Memory you control** — off by default, opt-in int8 vector quantization + typed decay, per-request `x-omniroute-no-memory`. → [Memory](docs/frameworks/MEMORY.md)
- **🛡️ Security** — prompt-injection guard on every LLM route (red-team suite) + free DuckDuckGo last-resort web search. → [Guardrails](docs/security/GUARDRAILS.md)
- **🖼️ New endpoints** — `/v1/ocr` (Mistral OCR) and `/v1/audio/translations` (Whisper-style) round out the media surface. → [API Reference](docs/reference/API_REFERENCE.md)
- **🌍 Deployment & ops** — reverse-proxy `basePath`, browser-language auto-detect, per-key device tracking, root-less MITM trust, zh-TW localization. → [Environment](docs/reference/ENVIRONMENT.md)
- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI), Ollama first-class card, Claude Sonnet 5, Zed, Requesty, SenseNova, Yuanbao… and a refreshed 250-provider catalog. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
- **⚡ Local performance & infra** — one-click local Redis, Cloudflare Workers / Deno Deploy relay deployers, Bifrost & Mux as supervised embedded services. → [Embedded Services](docs/frameworks/EMBEDDED-SERVICES.md)
<br/>
@@ -366,28 +284,44 @@ Result: 4 layers of fallback = zero downtime
<div align="center">
<table>
<tr>
<td align="center" width="120"><a href="https://github.com/anthropics/claude-code"><img src="./public/providers/claude.svg" width="52" alt="Claude Code"/><br/><b>Claude Code</b></a></td>
<td align="center" width="120"><a href="https://github.com/openai/codex"><img src="./public/providers/codex.svg" width="52" alt="Codex CLI"/><br/><b>Codex CLI</b></a></td>
<td align="center" width="120"><img src="./public/providers/cursor.png" width="52" alt="Cursor"/><br/><b>Cursor</b></td>
<td align="center" width="120"><img src="./public/providers/copilot.png" width="52" alt="Copilot"/><br/><b>Copilot</b></td>
<td align="center" width="120"><img src="./public/providers/continue.png" width="52" alt="Continue"/><br/><b>Continue</b></td>
<td align="center" width="76"><a href="https://github.com/anthropics/claude-code"><img src="./public/providers/claude.svg" width="40" alt="Claude Code"/><br/><sub><b>Claude Code</b></sub><br/><sub>                           </sub></a></td>
<td align="center" width="76"><a href="https://github.com/openai/codex"><img src="./public/providers/codex.svg" width="40" alt="Codex CLI"/><br/><sub><b>Codex CLI</b></sub><br/><sub>                           </sub></a></td>
<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/cline.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cline.svg" width="40" alt="Cline"/></picture><br/><sub><b>Cline</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><a href="https://github.com/Kilo-Org/kilocode"><img src="./public/providers/kilocode.svg" width="40" alt="Kilo Code"/><br/><sub><b>Kilo Code</b></sub><br/><sub>                           </sub></a></td>
<td align="center" width="76"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/roocode.png#gh-dark-mode-only" width="40" alt="Roo Code"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/roocode.svg#gh-light-mode-only" width="40" alt="Roo Code"/><br/><sub><b>Roo Code</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><img src="./public/providers/continue.svg" width="40" alt="Continue"/><br/><sub><b>Continue</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><img src="./public/providers/qwen.svg" width="40" alt="Qwen Code"/><br/><sub><b>Qwen Code</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><img src="./public/providers/cli-generic.svg" width="40" alt="Aider"/><br/><sub><b>Aider</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><img src="./public/providers/cli-generic.svg" width="40" alt="ForgeCode"/><br/><sub><b>ForgeCode</b></sub><br/><sub>                           </sub></td>
</tr>
<tr>
<td align="center" width="120"><a href="https://github.com/anomalyco/opencode"><img src="./public/providers/opencode.svg" width="52" alt="OpenCode"/><br/><b>OpenCode</b></a></td>
<td align="center" width="120"><a href="https://github.com/Kilo-Org/kilocode"><img src="./public/providers/kilocode.svg" width="52" alt="Kilo Code"/><br/><b>Kilo Code</b></a></td>
<td align="center" width="120"><img src="./public/providers/droid.svg" width="52" alt="Droid"/><br/><b>Droid</b></td>
<td align="center" width="120"><img src="./public/providers/openclaw.png" width="52" alt="OpenClaw"/><br/><b>OpenClaw</b></td>
<td align="center" width="120"><img src="./public/providers/kiro.svg" width="52" alt="Kiro"/><br/><b>Kiro</b></td>
<td align="center" width="120"><img src="./public/providers/command-code.svg" width="52" alt="Command Code"/><br/><b>Command</b></td>
<td align="center" width="76"><img src="./public/providers/cli-generic.svg" width="40" alt="jcode"/><br/><sub><b>jcode</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><img src="./public/providers/deepseek.svg" width="40" alt="DeepSeek TUI"/><br/><sub><b>DeepSeek TUI</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><img src="./public/providers/cli-generic.svg" width="40" alt="CodeWhale"/><br/><sub><b>CodeWhale</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><a href="https://github.com/anomalyco/opencode"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/opencode.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/opencode.svg" width="40" alt="OpenCode"/></picture><br/><sub><b>OpenCode</b></sub><br/><sub>                           </sub></a></td>
<td align="center" width="76"><img src="./public/providers/droid.svg" width="40" alt="Factory Droid"/><br/><sub><b>Factory Droid</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><img src="./public/providers/copilot.svg" width="40" alt="GitHub Copilot CLI"/><br/><sub><b>Copilot CLI</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><img src="./public/providers/cursor.svg" width="40" alt="Cursor CLI"/><br/><sub><b>Cursor CLI</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><img src="./public/providers/cli-generic.svg" width="40" alt="Smelt"/><br/><sub><b>Smelt</b></sub><br/><sub>                           </sub></td>
</tr>
<tr>
<td align="center" width="76"><img src="./public/providers/cli-generic.svg" width="40" alt="Pi (pi-coding-agent)"/><br/><sub><b>Pi</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><img src="./public/providers/grok.svg" width="40" alt="Grok Build (xAI)"/><br/><sub><b>Grok Build</b></sub><br/><sub>                           </sub></td>
<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/nousresearch.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/nousresearch.svg" width="40" alt="Hermes Agent (Nous Research)"/></picture><br/><sub><b>Hermes Agent</b></sub><br/><sub>                           </sub></td>
<td align="center" width="76"><img src="./public/providers/openclaw.svg" width="40" alt="OpenClaw"/><br/><sub><b>OpenClaw</b></sub><br/><sub>                           </sub></td>
<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"><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> · Cline · Antigravity · Windsurf · AMP · Hermes · Qwen CLI · Roo · Continue · <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 24+ tools → [`docs/reference/CLI-TOOLS.md`](docs/reference/CLI-TOOLS.md) · 🧩 OpenCode plugin → [`@omniroute/opencode-provider`](https://www.npmjs.com/package/@omniroute/opencode-provider)</sub>
<sub>📖 Per-tool setup for all 26 tools (20 CLI Code's + 6 CLI Agents) → [`docs/reference/CLI-TOOLS.md`](docs/reference/CLI-TOOLS.md) · 🧩 OpenCode plugin → [`@omniroute/opencode-provider`](https://www.npmjs.com/package/@omniroute/opencode-provider)</sub>
</div>
@@ -395,11 +329,11 @@ Result: 4 layers of fallback = zero downtime
<div align="center">
# 🌐 250 AI Providers — 90+ Free
# 🌐 268 AI Providers — 90+ Free
</div>
> The most complete catalog of any open-source router: **250 providers**, **90+ with a free tier**, **11 free forever**.
> The most complete catalog of any open-source router: **268 providers**, **90+ with a free tier**, **40+ free forever**.
<div align="center">
@@ -407,28 +341,26 @@ Result: 4 layers of fallback = zero downtime
<table>
<tr>
<td align="center" width="92"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/openai.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/openai.svg" width="40" alt="OpenAI"/></picture><br/><sub>OpenAI</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/claude-color.svg" width="40" alt="Anthropic"/><br/><sub>Anthropic</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/gemini-color.svg" width="40" alt="Gemini"/><br/><sub>Gemini</sub></td>
<td align="center" width="92"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/grok.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/grok.svg" width="40" alt="xAI Grok"/></picture><br/><sub>xAI Grok</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/deepseek-color.svg" width="40" alt="DeepSeek"/><br/><sub>DeepSeek</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/mistral-color.svg" width="40" alt="Mistral"/><br/><sub>Mistral</sub></td>
<td align="center" width="98"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/openai.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/openai.svg" width="40" alt="OpenAI"/></picture><br/><sub>OpenAI</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/claude-color.svg" width="40" alt="Anthropic"/><br/><sub>Anthropic</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/gemini-color.svg" width="40" alt="Gemini"/><br/><sub>Gemini</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/grok.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/grok.svg" width="40" alt="xAI Grok"/></picture><br/><sub>xAI Grok</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/deepseek-color.svg" width="40" alt="DeepSeek"/><br/><sub>DeepSeek</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/mistral-color.svg" width="40" alt="Mistral"/><br/><sub>Mistral</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/qwen-color.svg" width="40" alt="Qwen"/><br/><sub>Qwen</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/meta-color.svg" width="40" alt="Meta Llama"/><br/><sub>Meta Llama</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/groq.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/groq.svg" width="40" alt="Groq"/></picture><br/><sub>Groq</sub><br/><sub>                           </sub></td>
</tr>
<tr>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/qwen-color.svg" width="40" alt="Qwen"/><br/><sub>Qwen</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/meta-color.svg" width="40" alt="Meta Llama"/><br/><sub>Meta Llama</sub></td>
<td align="center" width="92"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/groq.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/groq.svg" width="40" alt="Groq"/></picture><br/><sub>Groq</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/nvidia-color.svg" width="40" alt="NVIDIA"/><br/><sub>NVIDIA</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/minimax-color.svg" width="40" alt="MiniMax"/><br/><sub>MiniMax</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cohere-color.svg" width="40" alt="Cohere"/><br/><sub>Cohere</sub></td>
</tr>
<tr>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/perplexity-color.svg" width="40" alt="Perplexity"/><br/><sub>Perplexity</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/huggingface-color.svg" width="40" alt="Hugging Face"/><br/><sub>HuggingFace</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/together-color.svg" width="40" alt="Together"/><br/><sub>Together</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/fireworks-color.svg" width="40" alt="Fireworks"/><br/><sub>Fireworks</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cloudflare-color.svg" width="40" alt="Cloudflare"/><br/><sub>Cloudflare</sub></td>
<td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/baidu-color.svg" width="40" alt="Baidu"/><br/><sub>Baidu</sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/nvidia-color.svg" width="40" alt="NVIDIA"/><br/><sub>NVIDIA</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/minimax-color.svg" width="40" alt="MiniMax"/><br/><sub>MiniMax</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cohere-color.svg" width="40" alt="Cohere"/><br/><sub>Cohere</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/perplexity-color.svg" width="40" alt="Perplexity"/><br/><sub>Perplexity</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/huggingface-color.svg" width="40" alt="Hugging Face"/><br/><sub>HuggingFace</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/together-color.svg" width="40" alt="Together"/><br/><sub>Together</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/fireworks-color.svg" width="40" alt="Fireworks"/><br/><sub>Fireworks</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cloudflare-color.svg" width="40" alt="Cloudflare"/><br/><sub>Cloudflare</sub><br/><sub>                           </sub></td>
<td align="center" width="98"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/baidu-color.svg" width="40" alt="Baidu"/><br/><sub>Baidu</sub><br/><sub>                           </sub></td>
</tr>
</table>
@@ -440,15 +372,13 @@ Result: 4 layers of fallback = zero downtime
<table>
<tr>
<td align="center" width="150"><img src="./public/providers/agentrouter.png" width="44" alt="AgentRouter"/><br/><b>AgentRouter</b><br/><sub>GPT-5, Claude, Gemini<br/>$100 free credits</sub></td>
<td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/qoder-color.svg" width="44" alt="Qoder AI"/><br/><b>Qoder AI</b><br/><sub>Kimi-K2, DeepSeek-R1<br/>Unlimited FREE</sub></td>
<td align="center" width="150"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/pollinations.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/pollinations.svg" width="44" alt="Pollinations"/></picture><br/><b>Pollinations</b><br/><sub>GPT-5, Claude, Llama 4<br/>No key needed</sub></td>
<td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/longcat-color.svg" width="44" alt="LongCat"/><br/><b>LongCat</b><br/><sub>LongCat-2.0<br/>10M tokens one-time (KYC) 🔑</sub></td>
</tr>
<tr>
<td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cloudflare-color.svg" width="44" alt="Cloudflare AI"/><br/><b>Cloudflare AI</b><br/><sub>50+ models<br/>10K neurons/day</sub></td>
<td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/nvidia-color.svg" width="44" alt="NVIDIA NIM"/><br/><b>NVIDIA NIM</b><br/><sub>129 models<br/>~40 RPM free</sub></td>
<td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cerebras-color.svg" width="44" alt="Cerebras"/><br/><b>Cerebras</b><br/><sub>Qwen3 235B<br/>1M tokens/day</sub></td>
<td align="center" width="127"><img src="./public/providers/agentrouter.png" width="44" alt="AgentRouter"/><br/><b>AgentRouter</b><br/><sub>GPT-5, Claude, Gemini<br/>$100 free credits</sub><br/><sub>                                     </sub></td>
<td align="center" width="127"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/qoder-color.svg" width="44" alt="Qoder AI"/><br/><b>Qoder AI</b><br/><sub>Kimi-K2, DeepSeek-R1<br/>Unlimited FREE</sub><br/><sub>                                     </sub></td>
<td align="center" width="127"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/pollinations.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/pollinations.svg" width="44" alt="Pollinations"/></picture><br/><b>Pollinations</b><br/><sub>GPT-5, Claude, Llama 4<br/>No key needed</sub><br/><sub>                                     </sub></td>
<td align="center" width="127"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/longcat-color.svg" width="44" alt="LongCat"/><br/><b>LongCat</b><br/><sub>LongCat-2.0<br/>10M tokens one-time (KYC) 🔑</sub><br/><sub>                                     </sub></td>
<td align="center" width="127"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cloudflare-color.svg" width="44" alt="Cloudflare AI"/><br/><b>Cloudflare AI</b><br/><sub>50+ models<br/>10K neurons/day</sub><br/><sub>                                     </sub></td>
<td align="center" width="127"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/nvidia-color.svg" width="44" alt="NVIDIA NIM"/><br/><b>NVIDIA NIM</b><br/><sub>129 models<br/>~40 RPM free</sub><br/><sub>                                     </sub></td>
<td align="center" width="127"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cerebras-color.svg" width="44" alt="Cerebras"/><br/><b>Cerebras</b><br/><sub>Qwen3 235B<br/>1M tokens/day</sub><br/><sub>                                     </sub></td>
</tr>
</table>
@@ -486,13 +416,7 @@ Result: 4 layers of fallback = zero downtime
</div>
> Your keys, your machine, your data. OmniRoute is a **local proxy** — it never phones home.
- 🏠 **Runs 100% on your hardware** — npm, Docker, desktop, or your phone. No OmniRoute cloud sits in the request path.
- 🔐 **Credentials encrypted at rest** — API keys & OAuth tokens sealed with **AES-256-GCM**.
- 🚫 **Zero telemetry by default** — your prompts go only to the providers _you_ choose, nowhere else.
- 🛡️ **Hardened gateway** — API-key scoping, IP filtering, rate limits, prompt-injection guard, loopback-only process routes.
- 📜 **MIT licensed & fully open-source** — audit every line, self-host forever.
<img src="./docs/diagrams/privacy-local.svg" width="100%" alt="Private and local-first — your keys, your machine, your data; OmniRoute is a local proxy that never phones home. Eleven guarantees: runs 100% on your hardware (0 cloud hops), zero telemetry by default, credentials encrypted at rest (AES-256-GCM), no account or sign-up, hardened gateway (API-key scoping, IP filtering, rate limits, prompt-injection guard), loopback-only process routes, upstream header scrubbing, strictly opt-in PII redaction, sanitized errors that never leak internals, a local audit trail in your own SQLite, and MIT-licensed fully open-source code."/>
<sub>📖 [Authorization](docs/architecture/AUTHZ_GUIDE.md) · [Guardrails](docs/security/GUARDRAILS.md) · [Compliance](docs/security/COMPLIANCE.md)</sub>
@@ -533,7 +457,7 @@ Tokens are scoped `read` / `write` / `admin`; process-spawning routes stay loopb
<div align="center">
`providers` · `oauth` · `keys` · `combo` · `nodes` · `models` · `cache` · `compression` · `cost` · `usage` · `quota` · `health` · `resilience` · `telemetry` · `logs` · `audit` · `mcp` · `a2a` · `cloud` · `memory` · `skills` · `eval` · `tunnel` · `backup` · `sync` · `webhooks` · `policy` · `pricing` · `translator` · `simulate` …
<img src="./docs/diagrams/cli-terminal.svg" width="100%" alt="Animated terminal demoing the OmniRoute CLI — omniroute providers list, omniroute combo list, omniroute health — cycling over the 80+ command surface: providers · oauth · keys · combo · nodes · models · cache · compression · cost · usage · quota · health · resilience · telemetry · logs · audit · mcp · a2a · cloud · memory · skills · eval · tunnel · backup · sync · webhooks · policy · pricing · translator · simulate …"/>
</div>
@@ -541,12 +465,12 @@ Tokens are scoped `read` / `write` / `admin`; process-spawning routes stay loopb
Expose OmniRoute over **MCP** or **A2A** and any capable agent gets the keys to the whole gateway — routing, providers, combos, cache, compression, memory — autonomously.
| Protocol | Endpoint | Use it for |
| ------------------ | ----------------------------------------------- | ------------------------------------------------------ |
| 🧰 **MCP (stdio)** | `omniroute --mcp` | Plug into Claude Desktop, Cursor, any MCP client |
| 🌊 **MCP (HTTP)** | `http://localhost:20128/api/mcp/stream` | Remote MCP — **94 tools**, 30 scopes, full audit trail |
| 📡 **MCP (SSE)** | `http://localhost:20128/api/mcp/sse` | Streaming MCP transport |
| 🤝 **A2A** | `http://localhost:20128/.well-known/agent.json` | Agent-to-agent, **JSON-RPC 2.0** + SSE, 6 skills |
| Protocol | Endpoint | Use it for |
| ------------------ | ----------------------------------------------- | ------------------------------------------------------- |
| 🧰 **MCP (stdio)** | `omniroute --mcp` | Plug into Claude Desktop, Cursor, any MCP client |
| 🌊 **MCP (HTTP)** | `http://localhost:20128/api/mcp/stream` | Remote MCP — **104 tools**, 30 scopes, full audit trail |
| 📡 **MCP (SSE)** | `http://localhost:20128/api/mcp/sse` | Streaming MCP transport |
| 🤝 **A2A** | `http://localhost:20128/.well-known/agent.json` | Agent-to-agent, **JSON-RPC 2.0** + SSE, 6 skills |
```bash
# Give Claude Code the full OmniRoute toolset over MCP:
@@ -569,29 +493,29 @@ claude mcp add-server omniroute --type http --url http://localhost:20128/api/mcp
Engines run in pipeline order; each is independently toggleable and configurable per combo:
| # | Engine | What it does |
| --- | ----------------- | ------------------------------------------------------------------- |
| 1 | **Session-Dedup** | Drops content repeated across turns (content-addressed, cross-turn) |
| 2 | **CCR** | Archives large blocks behind retrieve markers, fetched on demand |
| 3 | **RTK** | Smart tool-result filtering, dedup & truncation (command-aware) |
| # | Engine | What it does |
| --- | ----------------- | ----------------------------------------------------------------------------------------------------------------------- |
| 1 | **Session-Dedup** | Drops content repeated across turns (content-addressed, cross-turn) |
| 2 | **CCR** | Archives large blocks behind retrieve markers, fetched on demand |
| 3 | **RTK** | Smart tool-result filtering, dedup & truncation (command-aware) |
| 4 | **Headroom** | Lossless tabular compaction of homogeneous JSON arrays, flat or nested (~30%), via a vendored **GCF** codec (spec v3.2) |
| 5 | **Relevance** | Extractive sentence scoring against the last user query |
| 6 | **Caveman** | Rule-based prose compression (~65–75% on output) |
| 7 | **LLMLingua-2** | ML semantic pruning via MobileBERT ONNX — code-safe, async |
| 8 | **Lite** | Whitespace + image-URL trimming (latency-light baseline) |
| 9 | **Aggressive** | Summarization + progressive aging of old turns |
| 10 | **Ultra** | Heuristic token pruning with an optional small-model (SLM) tier |
| 5 | **Relevance** | Extractive sentence scoring against the last user query |
| 6 | **Caveman** | Rule-based prose compression (~65–75% on output) |
| 7 | **LLMLingua-2** | ML semantic pruning via MobileBERT ONNX — code-safe, async |
| 8 | **Lite** | Whitespace + image-URL trimming (latency-light baseline) |
| 9 | **Aggressive** | Summarization + progressive aging of old turns |
| 10 | **Ultra** | Heuristic token pruning with an optional small-model (SLM) tier |
Code blocks, URLs and structured data are **always preserved** byte-perfect. **One-click presets** combine the engines:
| Mode | Savings | Best for |
| ------------------------------ | ---------- | --------------------------- |
| 🪶 **Lite** | ~15% | Always-on safe default |
| 🪨 **Standard (Caveman)** | ~30% | Daily coding |
| ⚡ **Aggressive** | ~50% | Long tool-heavy sessions |
| 🔥 **Ultra** | ~75% | Maximum savings |
| 🧰 **RTK** | 60–90% | Shell/test/build/git output |
| 🔗 **Stacked (RTK → Caveman)** | **78–95%** | Mixed prompts + tool logs |
| Mode | Savings | Best for                                                                                                                                        |
| ------------------------------ | ---------- | ----------------------------------------------------------------------------------------------------------------------------------------------- |
| 🪶 **Lite** | ~15% | Always-on safe default |
| 🪨 **Standard (Caveman)** | ~30% | Daily coding |
| ⚡ **Aggressive** | ~50% | Long tool-heavy sessions |
| 🔥 **Ultra** | ~75% | Maximum savings |
| 🧰 **RTK** | 60–90% | Shell/test/build/git output |
| 🔗 **Stacked (RTK → Caveman)** | **78–95%** | Mixed prompts + tool logs |
**Real example — Standard mode:**
@@ -613,9 +537,7 @@ Code blocks, URLs and structured data are **always preserved** byte-perfect. **O
### 📖 How it works — pipeline, architecture & savings math
```
Client (10,000 tok) ──▶ OmniRoute Compression (10 engines) ──▶ Provider (~1,080 tok, up to 95% saved)
```
<img src="./docs/diagrams/compression-pipeline.svg" width="100%" alt="OmniRoute compression pipeline: a client request of 10,000 tokens passes through 10 stacked engines — Session-Dedup, CCR, RTK, Headroom, Relevance, Caveman, LLMLingua-2, Lite, Aggressive, Ultra — and reaches the provider at about 1,080 tokens, up to 95% saved. Code, URLs and JSON are always preserved byte-perfect."/>
Default stacked combo runs `RTK → Caveman`. When both act on the same tool/context payload, savings compound:
@@ -805,137 +727,10 @@ same process on one port, so there is no separate CLI-only package today.
<div align="center">
# 📚 Explore More
# 📸 Dashboard Screenshots
</div>
<details>
<summary><b>💰 Pricing at a glance & the $0 Free Stack (11 providers)</b></summary>
<br/>
| Tier | Example | Cost |
| --------------------------- | ---------------------------------------- | ---------- |
| 💳 **Subscription** | Claude Code Pro / Codex / Copilot | $10–200/mo |
| 🔑 **API Key (free tiers)** | NVIDIA NIM, Cerebras, Groq | **FREE** |
| 💰 **Cheap** | GLM-5 $0.5/1M · MiniMax M2.5 $0.3/1M | pennies |
| 🆓 **Free Forever** | Kiro, Qoder, Qwen, Pollinations, LongCat | **$0** |
**The $0 Free Stack — combine into one unbreakable combo:**
| Provider | Prefix | Free models | Quota |
| ----------------- | ----------- | ----------------------------------------------- | ------------------ |
| **Kiro** | `kr/` | Claude Sonnet 4.5, Haiku 4.5, Opus 4.6 | 50 credits/mo |
| **Qoder** | `if/` | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 | ♾️ Unlimited |
| **Qwen** | `qw/` | qwen3-coder-plus/flash/next | ♾️ Unlimited |
| **Pollinations** | `pol/` | GPT-5, Claude, Gemini, DeepSeek, Llama 4 | No key needed |
| **LongCat** | `lc/` | LongCat-2.0 | 10M one-time (KYC) |
| **Cloudflare AI** | `cf/` | 50+ models | 10K neurons/day |
| **NVIDIA NIM** | `nvidia/` | 129 models | ~40 RPM |
| **Cerebras** | `cerebras/` | Qwen3 235B, GPT-OSS 120B | 1M tok/day |
> 💡 The dashboard "cost" is a **savings tracker**, not a bill — OmniRoute never charges you. A "$290 total cost" using free models means **$290 saved**.
📖 Complete free directory → [`docs/reference/FREE_TIERS.md`](docs/reference/FREE_TIERS.md) — 25+ providers, quotas, base URLs.
</details>
<details>
<summary><b>🎯 Use Cases — ready-made combo playbooks</b></summary>
<br/>
**$0 forever:**
```
1. kr/claude-sonnet-4.5 (Kiro — ~50 credits/mo per acct)
2. if/kimi-k2-thinking (Qoder — unlimited)
3. pol/gpt-5 (Pollinations — no key)
4. lc/LongCat-2.0 (10M one-time backup, KYC)
Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
```
**24/7 no interruptions:** chain 2 subscriptions → cheap → free for 5 layers of fallback.
**Blocked region:** free providers + global/per-provider proxy → access AI from any country.
**Max savings:** subscription + cheap backup + `ultra` compression (~75%) → ~$150–300/mo saved for heavy users.
</details>
<details>
<summary><b>🌍 Bypass geo-blocks — 3-level proxy + stealth</b></summary>
<br/>
🇷🇺 🇨🇳 🇮🇷 🇨🇺 🇹🇷 In a blocked region? OmniRoute's **3-level proxy** (Global / Per-Provider / Per-Connection) proxies API requests, OAuth flows, connection tests, token refresh & model sync.
- **Protocols:** HTTP/HTTPS, SOCKS5, authenticated proxies
- **🆓 1proxy marketplace** — hundreds of free validated proxies, quality scores, auto-rotation
- **Anti-detection** — TLS fingerprint spoofing (`wreq-js`), CLI fingerprint matching, proxy IP preservation
📖 [`docs/ops/PROXY_GUIDE.md`](docs/ops/PROXY_GUIDE.md)
</details>
<details>
<summary><b>✨ Full feature list — 30+ capabilities (memory, evals, observability)</b></summary>
<br/>
**Routing:** 18 strategies · task-aware smart routing · thinking budget controls · wildcard routing · system prompt injection.
**Compatibility:** OpenAI ↔ Claude ↔ Gemini ↔ Responses API · auto OAuth refresh (PKCE, 8 providers) · multi-account round-robin · Batch + Files API · live OpenAPI 3.0.
**Protocols:** MCP (94 tools, 3 transports, 30 scopes) · A2A (JSON-RPC 2.0, SSE, 6 skills) · ACP · cloud agents (Codex, Cursor, Devin, Jules).
**Plugins:** custom plugin marketplace (system-configured registry URL with SSRF-guarded fetch) · install / enable / disable · Notion + Obsidian knowledge-base integrations (WebDAV file server, vault search, note CRUD).
**Embedded services:** one-click install & lifecycle management of local sidecar services (CLIProxy, NineRouter).
**Quality & Ops:** built-in **Evals** (golden-set: exact/contains/regex/custom) · guardrails (PII, injection, vision) · health dashboard · p50/p95/p99 telemetry · webhooks · compliance audit.
**AI Agent Skills:** drop-in markdown manifests — point any agent at a `skills/*/SKILL.md` manifest. 43 skills available.
📖 [MCP Server](open-sse/mcp-server/README.md) · [A2A Server](src/lib/a2a/README.md) · [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md) · [Features Gallery](docs/guides/FEATURES.md)
</details>
<details>
<summary><b>📖 Setup, env vars & FAQ</b></summary>
<br/>
| Env var | Default | Purpose |
| ----------------- | -------------- | -------------------------------- |
| `PORT` | `20128` | API + dashboard port |
| `REQUIRE_API_KEY` | `false` | Require API key for all requests |
| `DATA_DIR` | `~/.omniroute` | Database & config storage |
**Will I be charged by OmniRoute?** No — it's free, open-source software on your machine. You only pay paid providers directly. OmniRoute has no billing system.
**Are FREE providers really unlimited?** Mostly — Qoder, Pollinations, LongCat, and Cloudflare are free with no per-account credit cap. Kiro is free too but capped at ~50 credits/month per account. Stack multiple free providers in a combo and auto-fallback keeps you serving for $0.
**Will compression hurt quality?** No — it only compresses the **input**; code, URLs, JSON are always protected.
**Does it work where AI is blocked?** Yes — 3-level proxy + 1proxy marketplace reach all 250 providers.
📖 [User Guide](docs/guides/USER_GUIDE.md) · [API Reference](docs/reference/API_REFERENCE.md) · [Environment Config](docs/reference/ENVIRONMENT.md)
</details>
<details>
<summary><b>🐛 Troubleshooting</b></summary>
<br/>
| Problem | Quick fix |
| ----------------------------------------- | ------------------------------------------------------------- |
| "Language model did not provide messages" | Provider quota exhausted → use a combo fallback |
| Rate limiting (429) | Add fallback: `cc/claude → glm/glm-4.7 → if/kimi-k2-thinking` |
| OAuth token expired | Auto-refreshed; if stuck, delete + re-auth in Providers |
| `unsupported_country_region_territory` | Configure proxy in Settings → Proxy |
| Docker SQLite locks | Use `--stop-timeout 40` for clean WAL checkpoint |
| Node runtime errors | Use Node `>=22.0.0 <23` or `>=24.0.0 <27` |
🐛 **Reporting a bug?** Run `npm run system-info` and attach `system-info.txt`. 📖 [`docs/guides/TROUBLESHOOTING.md`](docs/guides/TROUBLESHOOTING.md)
</details>
<details>
<summary><b>📸 Dashboard screenshots</b></summary>
<br/>
| Page | Screenshot | Page | Screenshot |
| ---------- | ------------------------------------------------- | ---------- | --------------------------------------------- |
| Providers | ![Providers](docs/screenshots/01-providers.png) | Combos | ![Combos](docs/screenshots/02-combos.png) |
@@ -943,8 +738,6 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
| Translator | ![Translator](docs/screenshots/05-translator.png) | Settings | ![Settings](docs/screenshots/06-settings.png) |
| CLI Tools | ![CLI Tools](docs/screenshots/07-cli-tools.png) | Usage Logs | ![Usage](docs/screenshots/08-usage.png) |
</details>
<br/>
<div align="center">
@@ -969,7 +762,7 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
</div>
- **Runtime**: Node.js 22.x or 24.x LTS (24 LTS recommended) — `>=22.0.0 <23 || >=24.0.0 <27`
- **Runtime**: Node.js 22.x or 24.x LTS (24 LTS recommended) — `>=22.22.2 <23 || >=24.0.0 <27`
- **Language**: TypeScript 6.0 — **100% TypeScript** across `src/` and `open-sse/` (zero `any` in core modules since v2.0)
- **Framework**: Next.js 16 + React 19 + Tailwind CSS 4
- **Database**: better-sqlite3 (SQLite) + LowDB (JSON legacy) — domain state, proxy logs, MCP audit, routing decisions, memory, skills
@@ -977,7 +770,7 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
- **Protocols**: MCP (stdio/HTTP) + A2A v0.3 (JSON-RPC 2.0 + SSE)
- **Streaming**: Server-Sent Events (SSE) + WebSocket bridge (`/v1/ws`)
- **Auth**: OAuth 2.0 (PKCE) + JWT + API Keys + MCP Scoped Authorization
- **Testing**: Node.js test runner + Vitest (**21,000+ test cases** across 2,586 files — unit, integration, E2E, security, ecosystem)
- **Testing**: Node.js test runner + Vitest (**25,000+ test cases** across 3,300+ files — unit, integration, E2E, security, ecosystem)
- **Platforms**: Desktop (Electron), Android (Termux), PWA (any browser)
- **CI/CD**: GitHub Actions (auto npm publish + Docker Hub on release)
- **Website**: [omniroute.online](https://omniroute.online)
@@ -995,66 +788,66 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
### 📘 Getting Started
| Document | Description |
| -------------------------------------------------------------- | -------------------------------------------------------------------------------- |
| [User Guide](docs/guides/USER_GUIDE.md) | Providers, combos, CLI integration, deployment |
| [Setup Guide](docs/guides/SETUP_GUIDE.md) | Full install methods, CLI tool configs, protocol setup, timeout tuning |
| [CLI Tools Guide](docs/reference/CLI-TOOLS.md) | Per-tool setup for Claude Code, Codex, Cursor, Cline, OpenClaw, Kilo, Copilot |
| [Remote Mode](docs/guides/REMOTE-MODE.md) | Drive a remote OmniRoute (VPS) from your laptop CLI via scoped access tokens |
| [Claude Code Config](docs/guides/CLAUDE-CODE-CONFIGURATION.md) | Point Claude Code at OmniRoute (local/remote) with `launch` + per-model profiles |
| [Quick Start](README.md#-quick-start) | 3-step install → connect → configure |
| Document | Description                                                                                                                                                                          |
| -------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| [User Guide](docs/guides/USER_GUIDE.md) | Providers, combos, CLI integration, deployment |
| [Setup Guide](docs/guides/SETUP_GUIDE.md) | Full install methods, CLI tool configs, protocol setup, timeout tuning |
| [CLI Tools Guide](docs/reference/CLI-TOOLS.md) | Per-tool setup for Claude Code, Codex, Cursor, Cline, OpenClaw, Kilo, Copilot |
| [Remote Mode](docs/guides/REMOTE-MODE.md) | Drive a remote OmniRoute (VPS) from your laptop CLI via scoped access tokens |
| [Claude Code Config](docs/guides/CLAUDE-CODE-CONFIGURATION.md) | Point Claude Code at OmniRoute (local/remote) with `launch` + per-model profiles |
| [Quick Start](README.md#-quick-start) | 3-step install → connect → configure |
### 🔧 Operations & Deployment
| Document | Description |
| -------------------------------------------------------- | -------------------------------------------------------------- |
| [Docker Guide](docs/guides/DOCKER_GUIDE.md) | Docker run, Compose profiles, Caddy HTTPS, tunnels, image tags |
| [Podman Guide](contrib/podman/README.md) | Quadlet systemd integration, podman-compose, SELinux |
| [VM Deployment](docs/ops/VM_DEPLOYMENT_GUIDE.md) | Complete guide: VM + nginx + Cloudflare setup |
| [Fly.io Deployment](docs/ops/FLY_IO_DEPLOYMENT_GUIDE.md) | Deploy to Fly.io with persistent storage |
| [Termux Guide](docs/guides/TERMUX_GUIDE.md) | Run OmniRoute on Android via Termux |
| [PWA Guide](docs/guides/PWA_GUIDE.md) | Progressive Web App install, caching, architecture |
| [Uninstall Guide](docs/guides/UNINSTALL.md) | Clean removal for all install methods |
| [Environment Config](docs/reference/ENVIRONMENT.md) | Complete `.env` variables and references |
| Document | Description                                                                                                                                                                         |
| -------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [Docker Guide](docs/guides/DOCKER_GUIDE.md) | Docker run, Compose profiles, Caddy HTTPS, tunnels, image tags |
| [Podman Guide](contrib/podman/README.md) | Quadlet systemd integration, podman-compose, SELinux |
| [VM Deployment](docs/ops/VM_DEPLOYMENT_GUIDE.md) | Complete guide: VM + nginx + Cloudflare setup |
| [Fly.io Deployment](docs/ops/FLY_IO_DEPLOYMENT_GUIDE.md) | Deploy to Fly.io with persistent storage |
| [Termux Guide](docs/guides/TERMUX_GUIDE.md) | Run OmniRoute on Android via Termux |
| [PWA Guide](docs/guides/PWA_GUIDE.md) | Progressive Web App install, caching, architecture |
| [Uninstall Guide](docs/guides/UNINSTALL.md) | Clean removal for all install methods |
| [Environment Config](docs/reference/ENVIRONMENT.md) | Complete `.env` variables and references |
### 🧠 Features & Architecture
| Document | Description |
| ---------------------------------------------------------------------------- | ----------------------------------------------------------------------------- |
| [Architecture](docs/architecture/ARCHITECTURE.md) | System architecture, data flow, and internals |
| [Compression Guide](docs/compression/COMPRESSION_GUIDE.md) | 7-option pipeline: off / lite / standard / aggressive / ultra / RTK / stacked |
| [RTK Compression](docs/compression/RTK_COMPRESSION.md) | Command-output compression, filters, trust, verify, raw-output recovery |
| [Compression Engines](docs/compression/COMPRESSION_ENGINES.md) | Caveman, RTK, stacked pipelines, dashboard/API/MCP surfaces |
| [Compression Rules Format](docs/compression/COMPRESSION_RULES_FORMAT.md) | JSON rule-pack schemas for Caveman and RTK filters |
| [Compression Language Packs](docs/compression/COMPRESSION_LANGUAGE_PACKS.md) | Language detection and Caveman rule-pack authoring |
| [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md) | Circuit breakers, cooldowns, queue, anti-thundering herd, TLS spoofing |
| [Auto-Combo Engine](docs/routing/AUTO-COMBO.md) | 12-factor scoring, mode packs, self-healing |
| [Proxy Guide](docs/ops/PROXY_GUIDE.md) | 3-level proxy system, 1proxy marketplace, registry CRUD |
| [Free Tiers](docs/reference/FREE_TIERS.md) | 25+ free API providers consolidated directory |
| [Features Gallery](docs/guides/FEATURES.md) | Visual dashboard tour with screenshots |
| [Codebase Documentation](docs/architecture/CODEBASE_DOCUMENTATION.md) | Beginner-friendly codebase walkthrough |
| Document | Description                                                                                                                                                        |
| ---------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| [Architecture](docs/architecture/ARCHITECTURE.md) | System architecture, data flow, and internals |
| [Compression Guide](docs/compression/COMPRESSION_GUIDE.md) | 7-option pipeline: off / lite / standard / aggressive / ultra / RTK / stacked |
| [RTK Compression](docs/compression/RTK_COMPRESSION.md) | Command-output compression, filters, trust, verify, raw-output recovery |
| [Compression Engines](docs/compression/COMPRESSION_ENGINES.md) | Caveman, RTK, stacked pipelines, dashboard/API/MCP surfaces |
| [Compression Rules Format](docs/compression/COMPRESSION_RULES_FORMAT.md) | JSON rule-pack schemas for Caveman and RTK filters |
| [Compression Language Packs](docs/compression/COMPRESSION_LANGUAGE_PACKS.md) | Language detection and Caveman rule-pack authoring |
| [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md) | Circuit breakers, cooldowns, queue, anti-thundering herd, TLS spoofing |
| [Auto-Combo Engine](docs/routing/AUTO-COMBO.md) | 12-factor scoring, mode packs, self-healing |
| [Proxy Guide](docs/ops/PROXY_GUIDE.md) | 3-level proxy system, 1proxy marketplace, registry CRUD |
| [Free Tiers](docs/reference/FREE_TIERS.md) | 25+ free API providers consolidated directory |
| [Features Gallery](docs/guides/FEATURES.md) | Visual dashboard tour with screenshots |
| [Codebase Documentation](docs/architecture/CODEBASE_DOCUMENTATION.md) | Beginner-friendly codebase walkthrough |
### 🤖 Protocols & APIs
| Document | Description |
| ------------------------------------------------- | --------------------------------------------------- |
| [API Reference](docs/reference/API_REFERENCE.md) | All endpoints with examples |
| [OpenAPI Spec](docs/openapi.yaml) | OpenAPI 3.0 specification |
| [MCP Server](open-sse/mcp-server/README.md) | 95 MCP tools, IDE configs, Python/TS/Go clients |
| [MCP Server Guide](docs/frameworks/MCP-SERVER.md) | MCP installation, transports, and tool reference |
| [A2A Server](src/lib/a2a/README.md) | JSON-RPC 2.0 protocol, skills, streaming, task mgmt |
| [A2A Server Guide](docs/frameworks/A2A-SERVER.md) | A2A agent card, tasks, skills, and streaming |
| Document | Description                                                                                                                                                                             |
| ------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [API Reference](docs/reference/API_REFERENCE.md) | All endpoints with examples |
| [OpenAPI Spec](docs/openapi.yaml) | OpenAPI 3.0 specification |
| [MCP Server](open-sse/mcp-server/README.md) | 104 MCP tools, IDE configs, Python/TS/Go clients |
| [MCP Server Guide](docs/frameworks/MCP-SERVER.md) | MCP installation, transports, and tool reference |
| [A2A Server](src/lib/a2a/README.md) | JSON-RPC 2.0 protocol, skills, streaming, task mgmt |
| [A2A Server Guide](docs/frameworks/A2A-SERVER.md) | A2A agent card, tasks, skills, and streaming |
### 📋 Project & Quality
| Document | Description |
| -------------------------------------------------- | ----------------------------------------------- |
| [Contributing](CONTRIBUTING.md) | Development setup and guidelines |
| [Changelog](CHANGELOG.md) | Full per-version release history |
| [Security Policy](SECURITY.md) | Vulnerability reporting and security practices |
| [i18n Guide](docs/guides/I18N.md) | 40+ language support, translation workflow, RTL |
| [Release Checklist](docs/ops/RELEASE_CHECKLIST.md) | Pre-release validation steps |
| [Coverage Plan](docs/ops/COVERAGE_PLAN.md) | Test coverage strategy and 21,000+ test suite |
| Document | Description                                                                                                                                                                              |
| -------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [Contributing](CONTRIBUTING.md) | Development setup and guidelines |
| [Changelog](CHANGELOG.md) | Full per-version release history |
| [Security Policy](SECURITY.md) | Vulnerability reporting and security practices |
| [i18n Guide](docs/guides/I18N.md) | 40+ language support, translation workflow, RTL |
| [Release Checklist](docs/ops/RELEASE_CHECKLIST.md) | Pre-release validation steps |
| [Coverage Plan](docs/ops/COVERAGE_PLAN.md) | Test coverage strategy and 25,000+ test suite |
<br/>
@@ -1216,7 +1009,7 @@ OmniRoute stands on the shoulders of giants. It started as a fork of **[9router]
| Project | ⭐ | How it inspired OmniRoute |
| ---------------------------------------------------------------------------------------------- | ----: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **[TOON](https://github.com/toon-format/toon)** · toon-format | 24.7k | Token-Oriented Object Notation — its columnar, header-plus-rows model shaped our tabular compaction stage. |
| **[GCF – Graph Compact Format](https://github.com/blackwell-systems/gcf)** · Blackwell Systems | 14 | First inspired our tabular compaction stage; now its zero-dependency, lossless generic-profile encoder is **vendored directly** as the Headroom codec (MIT, SPDX-marked), current with GCF spec v3.2. |
| **[GCF – Graph Compact Format](https://github.com/blackwell-systems/gcf)** · Blackwell Systems | 14 | First inspired our tabular compaction stage; now its zero-dependency, lossless generic-profile encoder is **vendored directly** as the Headroom codec (MIT, SPDX-marked), current with GCF spec v3.2. |
| **[token-optimizer-mcp](https://github.com/ooples/token-optimizer-mcp)** · ooples | 421 | Brotli/SQLite cache + per-session context-delta — inspired our `session-dedup` engine. |
| **[token-savior](https://github.com/Mibayy/token-savior)** · Mibayy | 1.0k | Bash-output compaction + MCP profiles — inspired our compression bail-out discipline and MCP tool-manifest reduction. |
| **[token-saver](https://github.com/ppgranger/token-saver)** · ppgranger | 110 | Content-aware, per-file-type output compression with failure-aware bail-out — validated our per-type dispatch and minimum-gain skip. |
@@ -1284,7 +1077,7 @@ MIT License - see [LICENSE](LICENSE) for details.
**[⬆ Back to top](#-omniroute)** · Built with ❤️ for the open-source AI community.
<sub>OmniRoute v3.8.43 · Node ≥22.0.0 · MIT License · <a href="https://omniroute.online">omniroute.online</a></sub>
<sub>OmniRoute v3.8.49 · Node ≥22.22.2 · MIT License · <a href="https://omniroute.online">omniroute.online</a></sub>
</div>
<!-- GitHub Discussions enabled for community Q&A -->

11
bin/cli/commands/dashboard.mjs
View File

@@ -1,17 +1,22 @@
import { execFile } from "node:child_process";
import { t } from "../i18n.mjs";
function parsePort(value, fallback) {
const parsed = parseInt(String(value), 10);
return Number.isFinite(parsed) && parsed > 0 && parsed <= 65535 ? parsed : fallback;
}
export function registerDashboard(program) {
program
.command("dashboard")
.description(t("dashboard.description"))
.option("--url", t("dashboard.urlOnly"))
.option("--port <port>", "Port the server is running on", "20128")
.option("--port <port>", "Port the server is running on")
.option("--tui", t("dashboard.tui") || "Open interactive TUI dashboard (terminal UI)")
.action(async (opts, cmd) => {
if (opts.tui) {
const globalOpts = cmd.optsWithGlobals();
const port = opts.port ? parseInt(String(opts.port), 10) : 20128;
const port = parsePort(opts.port ?? process.env.PORT ?? "20128", 20128);
const baseUrl = globalOpts.baseUrl ?? `http://localhost:${port}`;
const apiKey = globalOpts.apiKey ?? null;
const { startInteractiveTui } = await import("../tui/Dashboard.jsx");
@@ -24,7 +29,7 @@ export function registerDashboard(program) {
}
export async function runDashboardCommand(opts = {}) {
const port = opts.port ? parseInt(String(opts.port), 10) : 20128;
const port = parsePort(opts.port ?? process.env.PORT ?? "20128", 20128);
const dashboardUrl = `http://localhost:${port}`;
if (opts.url) {

25
bin/cli/utils/versionFastPath.mjs Normal file
View File

@@ -0,0 +1,25 @@
/**
* Decide whether a CLI invocation is a bare `--version`/`-V` query that should
* short-circuit BEFORE the runtime polyfill import, env-file loading, and
* Commander's command registration (~70 command modules) are loaded.
*
* Scope is intentionally narrow — only a single, unambiguous `--version`/`-V`
* argument fast-paths. Anything else (extra args, a subcommand, `--help`,
* global options like `--lang`/`--output` alongside it) falls through to the
* normal Commander flow. Unlike `--version`, OmniRoute's `--help` output is
* generated dynamically from every registered subcommand, so skipping
* registration would change (truncate) the help text — that flag is
* deliberately NOT fast-pathed here.
*
* Mirrors the intent of upstream 9router PR #2414 (fast-path help/version
* before expensive self-heal hooks), adapted to OmniRoute's Commander-based
* CLI where the equivalent expensive work is eager command registration
* rather than npm-install-based runtime self-healing.
*
* @param {string[]} argv - process.argv (node + script + args).
* @returns {boolean}
*/
export function isVersionFastPath(argv) {
const args = Array.isArray(argv) ? argv.slice(2) : [];
return args.length === 1 && (args[0] === "--version" || args[0] === "-V");
}

53
bin/omniroute.mjs
View File

@@ -4,6 +4,9 @@
* OmniRoute CLI entry point.
*
* Special bypasses (handled before Commander):
* --version / -V (alone) Fast-path: print the version and exit, skipping the
* tsx/esm + polyfill imports, env-file loading, and
* Commander's ~70-command registration entirely.
* --mcp Start MCP server over stdio
* reset-encrypted-columns Recovery tool for broken encrypted credentials
* reset-password Reset the admin/management password
@@ -11,7 +14,7 @@
* All other commands are routed through Commander (bin/cli/program.mjs).
*/
import { existsSync, readFileSync } from "node:fs";
import { existsSync, readFileSync, writeFileSync } from "node:fs";
import { join, dirname } from "node:path";
import { fileURLToPath, pathToFileURL } from "node:url";
import updateNotifier from "update-notifier";
@@ -19,6 +22,26 @@ import { isNativeBinaryCompatible } from "../scripts/build/native-binary-compat.
import { getNodeRuntimeSupport, getNodeRuntimeWarning } from "./nodeRuntimeSupport.mjs";
import { getDefaultDataDir } from "./cli/data-dir.mjs";
import { shouldProvisionStorageKey } from "./cli/utils/storageKeyProvision.mjs";
import { isVersionFastPath } from "./cli/utils/versionFastPath.mjs";
const __filename = fileURLToPath(import.meta.url);
const __dirname = dirname(__filename);
const ROOT = join(__dirname, "..");
// Fast-path a bare `--version`/`-V` query BEFORE the tsx/esm registration, the
// polyfill import, env-file loading, or Commander's command registration (~70
// modules — DB, providers, OAuth, etc.) run. None of that work is needed to answer
// "what version is this" — mirrors upstream 9router PR #2414 (fast-path help/version
// ahead of expensive self-heal hooks), adapted to OmniRoute's Commander CLI where the
// equivalent expensive work is eager command registration rather than npm-install-based
// runtime self-healing. `--help` is intentionally NOT fast-pathed here: its output is
// generated dynamically from every registered subcommand, so skipping registration
// would truncate the help text instead of just speeding it up.
if (isVersionFastPath(process.argv)) {
const pkg = JSON.parse(readFileSync(join(ROOT, "package.json"), "utf8"));
console.log(pkg.version);
process.exit(0);
}
// Register tsx so dynamic imports of .ts source files (referenced as .js per
// TypeScript conventions) resolve correctly. The build never emits .js for
@@ -26,10 +49,6 @@ import { shouldProvisionStorageKey } from "./cli/utils/storageKeyProvision.mjs";
await import("tsx/esm");
await import("../open-sse/utils/setupPolyfill.ts");
const __filename = fileURLToPath(import.meta.url);
const __dirname = dirname(__filename);
const ROOT = join(__dirname, "..");
// MCP stdio transport uses stdout exclusively for JSON-RPC messages.
// Redirect console.log/warn to stderr early (before loadEnvFile and DB init)
// so no startup output corrupts the protocol.
@@ -40,6 +59,28 @@ if (process.argv.includes("--mcp")) {
console.warn = stderrConsole.warn.bind(stderrConsole);
}
// Electron persists secrets (JWT_SECRET, API_KEY_SECRET, STORAGE_ENCRYPTION_KEY) to
// `<DATA_DIR>/server.env` (electron/main.js), never `.env`. Migrating an existing
// install (storage.sqlite + server.env) to the CLI left those secrets undiscoverable —
// the CLI only ever looked for `.env`, so the STORAGE_ENCRYPTION_KEY needed to decrypt
// the migrated database was silently dropped (#7302). One-time, one-directory migration:
// if `<dataDir>/.env` is absent but `<dataDir>/server.env` is present, copy it to `.env`
// so it flows through the normal env-loading path below. Never overwrites an existing
// `.env` — an explicit `.env` always wins over a legacy `server.env`.
function migrateElectronServerEnv(dataDir) {
try {
const envPath = join(dataDir, ".env");
const serverEnvPath = join(dataDir, "server.env");
if (existsSync(envPath) || !existsSync(serverEnvPath)) return;
writeFileSync(envPath, readFileSync(serverEnvPath, "utf-8"), "utf-8");
console.log(
` \x1b[2m♻ Migrated Electron secrets from ${serverEnvPath} to ${envPath}\x1b[0m`
);
} catch {
// Ignore errors migrating server.env — fall back to normal env loading below.
}
}
function loadEnvFile() {
const envPaths = [];
const loadedEnvPaths = [];
@@ -50,6 +91,8 @@ function loadEnvFile() {
envPaths.push(envPath);
};
migrateElectronServerEnv(process.env.DATA_DIR || getDefaultDataDir());
if (process.env.DATA_DIR) {
addEnvPath(join(process.env.DATA_DIR, ".env"));
}

1
changelog.d/features/6354-per-model-timeout.md Normal file
View File

@@ -0,0 +1 @@
- feat(sse): configurable per-model upstream header-response timeout override, precedence model > provider > global; applied to codex reasoning-heavy tiers (gpt-5.5-high/xhigh, gpt-5.6-\*-high/xhigh) (#6354)

1
changelog.d/features/6540-hidepaid-ui-selects.md Normal file
View File

@@ -0,0 +1 @@
- **feat(dashboard):** Replace free-text model inputs in the Routing (web search route), Combo Defaults (handoff model), and Background Degradation tabs with a `hidePaidModels`-aware `ModelSelectField`, add a fail-open "paid-only pattern" warning to the per-model routing rule pattern field, and reject paid-only model targets at save time on `PATCH /api/settings`, `PATCH /api/settings/combo-defaults`, and `PUT /api/settings/background-degradation` when `hidePaidModels` is on ([#6540](https://github.com/diegosouzapw/OmniRoute/issues/6540))

1
changelog.d/features/6593-ratelimit-admission-control.md Normal file
View File

@@ -0,0 +1 @@
- **feat(sse):** rate-limit request queue admission control — `resilienceSettings.requestQueue.maxQueueDepth` (default `0` = disabled, opt-in 0–100000) fast-rejects a request with a typed `RATE_LIMIT_QUEUE_FULL` error once the local per-provider+connection queue already holds `maxQueueDepth` requests, instead of growing the queue unboundedly; the factory default for `requestQueue.maxWaitMs` (how long a request may wait before being dropped) also fell from 120s to 15s so a saturated queue fails fast (#6593 — thanks @chirag127).

1
changelog.d/features/6650-g4f-space-gateway.md Normal file
View File

@@ -0,0 +1 @@
- feat(sse): add 5 no-key g4f.space gateway providers — `g4f-groq`, `g4f-gemini`, `g4f-pollinations`, `g4f-ollama`, `g4f-nvidia` — a free, no-signup reverse proxy (gpt4free project) fronting Groq, Gemini, Pollinations, Ollama, and NVIDIA NIM, rate-limited to 5 req/min per IP (#6650 — thanks @chirag127).

1
changelog.d/features/6653-deepinfra-video-provider.md Normal file
View File

@@ -0,0 +1 @@
- feat(sse): add DeepInfra as a video-generation provider via its native synchronous inference endpoint (#6653)

1
changelog.d/features/6654-freepik-pikaso-image-provider.md Normal file
View File

@@ -0,0 +1 @@
- feat(providers): add Freepik (Magnific Mystic) API-key image generation provider — async submit/poll flow with realism/fluid/zen/flexible/super_real/editorial_portraits models (#6654)

1
changelog.d/features/6655-revai-stt-provider.md Normal file
View File

@@ -0,0 +1 @@
- feat(providers): add Rev AI speech-to-text provider with async job upload/poll/transcript flow (#6655)

1
changelog.d/features/6656-segmind-image-video-provider.md Normal file
View File

@@ -0,0 +1 @@
- **feat(providers):** add **Segmind** as an image + video generation provider — `x-api-key` auth against `POST https://api.segmind.com/v1/{model}`, with a curated starter model list (Flux, Stable Diffusion XL/3.5, Kandinsky for image; Wan, Hunyuan, LTX, Kling for video) (#6656).

1
changelog.d/features/6657-gladia-stt-provider.md Normal file
View File

@@ -0,0 +1 @@
- feat(providers): add Gladia as an async speech-to-text provider (#6657)

1
changelog.d/features/6658-novita-video-gen-provider.md Normal file
View File

@@ -0,0 +1 @@
- feat(video): add Novita AI as a video-generation provider (Wan/Kling async submit-poll) (#6658)

1
changelog.d/features/6659-speechmatics-stt-provider.md Normal file
View File

@@ -0,0 +1 @@
- **feat(providers):** add Speechmatics as an STT provider — async batch transcription (Enhanced operating point), 8 hours/month free tier, no credit card required. Streaming (real-time) mode is out of scope for v1. (#6659)

1
changelog.d/features/6660-mixedbread-embeddings-provider.md Normal file
View File

@@ -0,0 +1 @@
- feat(providers): add Mixedbread AI as an embeddings provider (`mxbai-embed-large-v1`, `mxbai-embed-2d-large-v1`, free tier) (#6660)

1
changelog.d/features/6666-felo-chat-aggregator-provider.md Normal file
View File

@@ -0,0 +1 @@
- **feat(providers):** add Felo (felo.ai) as a free, no-signup, no-API-key chat/search-agent aggregator provider (`felo-web`) — joins the existing `-web` family (DuckDuckGo AI Chat, Blackbox, etc). Five models (`felo-chat`, `felo-search`, `felo-scholar`, `felo-social`, `felo-document`) map to Felo's search categories; the executor opens a search thread then translates Felo's bespoke SSE stream into OpenAI-compatible chunks (#6666).

1
changelog.d/features/6667-gtts-audio-tts-provider.md Normal file
View File

@@ -0,0 +1 @@
- **feat(providers):** add gTTS (Google Translate TTS) as a free, no-signup audio-speech provider — routes through Google's current `batchexecute` RPC endpoint (the previously proposed `translate_tts` endpoint is deprecated), splitting input at the 100-char-per-request limit. (#6667)

1
changelog.d/features/6668-edgetts-audio-tts-provider.md Normal file
View File

@@ -0,0 +1 @@
- **feat(sse):** add EdgeTTS (Microsoft Edge "Read Aloud") as a free, no-API-key `audio-tts` provider — the first WebSocket-transport speech provider, with per-client-IP rate limiting. (#6668)

1
changelog.d/features/6670-freetheai-gateway-provider.md Normal file
View File

@@ -0,0 +1 @@
- feat(providers): add FreeTheAi as an OpenAI-compatible gateway provider with a free Discord-signup tier (#6670)

1
changelog.d/features/6672-microsoftdesigner-image-provider.md Normal file
View File

@@ -0,0 +1 @@
- feat(sse): add Microsoft Designer as an unofficial web-session image provider, reverse-engineered submit-then-poll DallE.ashx flow (#6672)

1
changelog.d/features/6737-vary-accept-encoding.md Normal file
View File

@@ -0,0 +1 @@
- **feat(api):** add `Vary: Accept-Encoding` to token-authenticated `/v1*`/`/v1beta*` responses so downstream caches distinguish compressed vs uncompressed variants (RFC 9110 §12.5.5). (thanks @chirag127)

1
changelog.d/features/6758-notion-web-provider.md Normal file
View File

@@ -0,0 +1 @@
- feat(sse): add Notion AI Web (Unofficial/Experimental) cookie-session provider (#6758)

1
changelog.d/features/6760-compression-mode-selector-context-cache.md Normal file
View File

@@ -0,0 +1 @@
- **feat(dashboard):** add per-routing-combo compression-mode override to the Compression Combos page under Context & Cache, alongside the existing combo-card quick override. (#6760)

1
changelog.d/features/6771-fusion-preserve-tools-bypass.md Normal file
View File

@@ -0,0 +1 @@
- **feat(sse):** preserve `tools`/`tool_choice` for tool-bearing requests through fusion combos — bypass panel synthesis and route straight to the judge with tools intact (#6771 — thanks @chirag127).

1
changelog.d/features/6801-xp-audit-log-retention.md Normal file
View File

@@ -0,0 +1 @@
- feat(db): include `xp_audit_log` in the automatic retention/prune cycle, with a configurable `retention.xpAuditLog` setting (#6801)

1
changelog.d/features/6836-import-providers-from-file.md Normal file
View File

@@ -0,0 +1 @@
- feat(dashboard): import multiple, possibly different providers from a CSV/JSON file — per-row validation, a checklist to pick which parsed rows to import, and a new `POST /api/providers/import` route with partial-failure results (#6836)

1
changelog.d/features/6842-openrouter-quota-tracking.md Normal file
View File

@@ -0,0 +1 @@
- **feat(sse):** OpenRouter quota tracking — a dedicated fetcher polls `/api/v1/key` + `/api/v1/credits` (per-key credit cap/remaining/reset, daily/weekly/monthly USD spend, BYOK usage) with a 45s cache and graceful degradation, a local per-account counter tracks the `:free`-model 50-or-1000-per-day + 20 RPM windows (corrected from `X-RateLimit-*` headers and `Retry-After` on 429), and OpenRouter `402` responses now lock the connection with a real cooldown instead of triggering an immediate reselection of the same credit-exhausted key (#6842).

1
changelog.d/features/6845-v0-vercel-quota-tracking.md Normal file
View File

@@ -0,0 +1 @@
- feat(sse): add dual-window quota tracking for the `v0-vercel` provider — polls the credits (`/v1/user/billing`) and daily Platform-API operation (`/v1/rate-limits`) endpoints with the existing routing API key, defensively degrading to an `unknown` billing type rather than misparsing a future v0 billing-model migration, feeding preflight + the dashboard's Provider Quota card (#6845).

1
changelog.d/features/6850-agentrouter-quota-tracking.md Normal file
View File

@@ -0,0 +1 @@
- feat(sse): add quota tracking for the `agentrouter` provider — polls the New-API `/api/user/self` balance endpoint with a separate System Access Token + `New-Api-User` id (configured via `providerSpecificData.consoleApiKey` / `newApiUserId`), converting raw quota units into a dollar balance and feeding preflight + the dashboard's Provider Quota card (#6850).

1
changelog.d/features/6872-relay-routing-fallback-reason-header.md Normal file
View File

@@ -0,0 +1 @@
- feat(api): add a structured `X-Routing-Fallback-Reason` header to relay routing responses, exposing a stable machine-readable reason code alongside the legacy `X-Routing-Fallback` detail string (#6872)

1
changelog.d/features/6873-model-latency-stats-api.md Normal file
View File

@@ -0,0 +1 @@
- **feat(api):** new **GET /api/usage/model-latency-stats** management endpoint exposes the existing rolling per-provider/model latency aggregate (avg/p50/p95/p99, success rate) already used internally by auto-combo routing — supports `windowHours`/`minSamples`/`maxRows`/`provider`/`model` filters (#6873).

1
changelog.d/features/6874-vibeproxy-openai-provider-node-preset.md Normal file
View File

@@ -0,0 +1 @@
- **feat(providers):** add a `vibeproxy-openai` provider-node preset to `POST /api/provider-nodes` — defaults name/prefix/apiType for VibeProxy's local OpenAI-compatible gateway and normalizes the caller-supplied base URL to its `/v1` root; `baseUrl` remains mandatory. (#6874, idea from #6137 by @KooshaPari)

1
changelog.d/features/6875-latency-stats-ttft.md Normal file
View File

@@ -0,0 +1 @@
- feat(usage): add avgTtftMs/avgE2ELatencyMs/avgTokensPerSecond to `getModelLatencyStats()` and feed them into auto-combo's speed-ranking factor (#6875)

1
changelog.d/features/6879-default-reasoning-effort.md Normal file
View File

@@ -0,0 +1 @@
- feat(sse): per-model default `reasoning_effort` (`ModelSpec.defaultReasoningEffort`, injected only when the request carries no reasoning field) and make `no-think/` express `reasoning_effort:"none"` instead of deleting the field on the OpenAI path, so thinks-by-default models actually stop thinking (#6879)

1
changelog.d/features/6880-connection-cache-override.md Normal file
View File

@@ -0,0 +1 @@
- **feat(providers):** let a custom/openai-compatible connection opt into prompt-cache behavior via a per-connection `cache` capability override, unblocking `prompt_cache_key` injection, the compression cache-aware guard, and `cache_control` passthrough for `openai-compatible-chat-<uuid>`-style connections. (thanks @andrea-kingautomation)

1
changelog.d/features/6915-free-rankings-auth-type-filter.md Normal file
View File

@@ -0,0 +1 @@
- **feat(dashboard):** add a Type filter (No Signup / OAuth Login / API Key) and an "Easiest first" sort toggle to Free Provider Rankings, so zero-setup NOAUTH providers can be surfaced without eyeballing the Type column. (#6915)

1
changelog.d/features/6928-comfyui-base-url-field.md Normal file
View File

@@ -0,0 +1 @@
- **feat(providers):** expose an editable base-URL field on the ComfyUI connection so Docker-network setups (e.g. `http://comfyui:8188`) work for image, video, and music generation ([#6928](https://github.com/diegosouzapw/OmniRoute/issues/6928))

1
changelog.d/features/6976-openrouter-embeddings.md Normal file
View File

@@ -0,0 +1 @@
- **feat(providers):** refresh the curated OpenRouter embeddings catalog (`open-sse/config/embeddingRegistry.ts`) with the current lineup — `openai/text-embedding-3-small`/`-large`, `qwen/qwen3-embedding-8b`/`-4b`, `baai/bge-m3`, `mistralai/mistral-embed-2312`, `google/gemini-embedding-001` — and fold curated embedding/rerank entries into OpenRouter's live model-discovery response (`src/app/api/providers/[id]/models/route.ts`), additively and deduped by id, so they no longer only appear on the no-config `local_catalog` fallback. OpenRouter serves embeddings via a dedicated `/api/v1/embeddings` endpoint (omitted from `/v1/models`), so the live-discovery success path previously returned chat models only ([#6976](https://github.com/diegosouzapw/OmniRoute/issues/6976)). Regression guard: `tests/unit/openrouter-embeddings-catalog-6976.test.ts`.

1
changelog.d/features/6977-quota-auto-ping.md Normal file
View File

@@ -0,0 +1 @@
- **feat(quota):** Add opt-in auto-ping to keep Codex quota windows warm — per-connection toggle in Settings → AI that sends a tiny request right after a Codex session window resets, so it isn't cold on the next real request ([#6977](https://github.com/diegosouzapw/OmniRoute/issues/6977))

1
changelog.d/features/7023-optional-enum-null-sentinel.md Normal file
View File

@@ -0,0 +1 @@
- **feat(sse):** Add optional-enum `null`-omission idiom for Responses-API (codex) strict-mode tool schemas, closing the #6951 follow-up ([#7023](https://github.com/diegosouzapw/OmniRoute/issues/7023))

1
changelog.d/features/7034-x-goog-api-key-client-auth.md Normal file
View File

@@ -0,0 +1 @@
- **feat(auth):** accept the `x-goog-api-key` header for client-facing auth so `gemini-cli` and other `@google/genai`-based clients can use OmniRoute as a native `/v1beta` gateway (#7034 — thanks @QRcode1337).

1
changelog.d/features/7075-freemodel-quota-tracking.md Normal file
View File

@@ -0,0 +1 @@
- feat(sse): add a local dual-window (5h + 7d, per-account) quota tracker for the `freemodel-dev` provider, feeding preflight + the dashboard's Provider Quota card with user-overridable request caps (`FREEMODEL_5H_REQUEST_LIMIT` / `FREEMODEL_7D_REQUEST_LIMIT`) since FreeModel publishes no usage API — phase 1 of #7075 (tracker + registration); live hot-path request metering and the forward-compatible endpoint prober are tracked as follow-ups.

1
changelog.d/features/7209-kiro-gpt56-family.md Normal file
View File

@@ -0,0 +1 @@
- **feat(kiro):** register the GPT-5.6 Sol/Terra/Luna model family (272k context window). (thanks @SemonCat)

1
changelog.d/features/7210-codex-plan-labels.md Normal file
View File

@@ -0,0 +1 @@
- **feat(dashboard):** show the Codex subscription plan label in provider connection rows and the quota view, falling back to the plan captured at OAuth import when the live usage endpoint doesn't report one. (thanks @CarmeloCampos)

1
changelog.d/features/7211-reorder-connections-by-availability.md Normal file
View File

@@ -0,0 +1 @@
- **feat(dashboard):** add a "Reorder" button to provider connections that sorts them by availability (using OmniRoute's connection-cooldown/testStatus model), persisting the new priority order. (thanks @fzrilsh)

1
changelog.d/features/7213-usage-extended-periods.md Normal file
View File

@@ -0,0 +1 @@
- **feat(dashboard):** add 180D and 365D periods to the Cost Explorer range selector. The new ranges thread through `parseCostRange`/`COST_RANGE_VALUES` and the `getRangeStartIso` handlers in the analytics and requests-by-provider-date usage routes, so cost/usage analytics can be viewed over a half-year and full-year window (#7213)

1
changelog.d/features/7223-github-copilot-claude-native-messages.md Normal file
View File

@@ -0,0 +1 @@
- **feat(sse):** GitHub Copilot Claude models now route through Copilot's native `/v1/messages` endpoint (prompt-cache token counts, no more lossy tool-call round-trip). (thanks @yidecode)

1
changelog.d/features/7228-antigravity-reasoning-effort-overrides.md Normal file
View File

@@ -0,0 +1 @@
- **feat(mitm):** Antigravity MITM model mappings now support an optional per-model reasoning-effort override (Default/None/Low/Medium/High/XHigh) alongside the destination-model remap. (thanks @trfi)

1
changelog.d/features/7238-xai-grok-imagine-video.md Normal file
View File

@@ -0,0 +1 @@
- **feat(sse):** add native xAI Grok Imagine video generation provider — `xai/grok-imagine-video` on `/v1/videos/generations` using your own xAI key, instead of only via the kie proxy market. (thanks @anndev-69)

1
changelog.d/features/7241-grok-build-cli-setup.md Normal file
View File

@@ -0,0 +1 @@
- **feat(cli):** add Grok Build CLI tool setup — writes a `[model.omniroute]` custom model into `~/.grok/config.toml` and restores your previous default on Reset. (thanks @rixzkiye)

1
changelog.d/features/7246-chenzk-provider.md Normal file
View File

@@ -0,0 +1 @@
- **feat(provider):** add Chenzk API OpenAI-compatible gateway. (thanks @CahyokPutraDev99)

1
changelog.d/features/7274-generic-session-affinity.md Normal file
View File

@@ -0,0 +1 @@
- **feat(sse):** session affinity (`X-Session-Id` / `x-codex-session-id` / `x-omniroute-session`) now works for **any** provider, not just Codex — the `codex`-only early-return in `resolveSessionAffinityTtlMs()` was removed, and the global TTL setting was renamed `codexSessionAffinityTtlMs` → `sessionAffinityTtlMs` (dashboard label updated to "Session affinity") with a backward-compatible migration that carries over an existing Codex TTL as the new default (#7274 — thanks @tenshiak).

1
changelog.d/features/7318-router-eval-harness.md Normal file
View File

@@ -0,0 +1 @@
- **feat(eval):** added a router-eval harness (`npm run eval:router`, `eval:router:compare`, `eval:router:patch-compare`, `eval:router:search`, `eval:router:trends`, `check:router-eval`) that replays routing decisions — from NDJSON corpora or the `usage_history`/`call_logs` SQLite tables — into an AIQ (success/latency/cost) score, compares baseline vs. candidate router configs with a retained-run regression gate, and ranks Pareto-optimal candidates; a sibling tool to the existing `eval:compression` harness (#7318 — thanks @KooshaPari).

1
changelog.d/features/7361-confirm-remove-account.md Normal file
View File

@@ -0,0 +1 @@
- feat(dashboard): confirm before removing a single connection, naming the account, mirroring the existing batch-delete confirm UX (#7361)

1
changelog.d/features/7399-xai-oauth-pkce.md Normal file
View File

@@ -0,0 +1 @@
- **feat(providers):** Add a first-class xAI OAuth PKCE provider for `api.x.ai` models, including Grok 4.5 and refresh-token rotation ([#7399](https://github.com/diegosouzapw/OmniRoute/pull/7399)) — thanks @fenix007

1
changelog.d/features/7530-compression-guidance.md Normal file
View File

@@ -0,0 +1 @@
- **feat(dashboard):** surface in-product guidance for the Settings → Prompt Compression engines — each `engineCatalog.ts` entry now carries a `guidance` block (quality/latency tradeoffs, lossy flag, cache impact) sourced from `docs/compression/*.md`, rendered as an expandable per-engine detail with a "safe default" indicator for lossless engines (Session Dedup, CCR, Lite, Headroom) plus a link to the full compression guide (#7530).

1
changelog.d/features/7601-lmstudio-embeddings.md Normal file
View File

@@ -0,0 +1 @@
- **feat(providers):** register `lmstudio` in the embedding provider registry (`open-sse/config/embeddingRegistry.ts`) — LM Studio's local OpenAI-compatible `/v1/embeddings` endpoint, no auth required, passthrough model list (a user-configured provider_node still takes priority). Previously any `lmstudio/<model>` embedding request failed with `"Unknown embedding provider: lmstudio"` even though the model appeared fine in `/v1/models` ([#7601](https://github.com/diegosouzapw/OmniRoute/issues/7601) — thanks @ekinnee). Regression guard: `tests/unit/lmstudio-embedding-provider-7601.test.ts`.

1
changelog.d/features/7622-noauth-autocombo-exclude.md Normal file
View File

@@ -0,0 +1 @@
- feat(sse): honor a no-auth provider connection's **Excluded Models** field (`providerSpecificData.excludedModels`) in the auto-combo/fusion candidate pool builder, so an excluded no-auth model (e.g. `minimax-m3-free`) is filtered out upfront instead of only failing over after being picked (#7622).

1
changelog.d/features/notion-web-available-models.md Normal file
View File

@@ -0,0 +1 @@
- feat(providers): notion-web live model discovery via getAvailableModels (spaceId + token_v2 cookie)

3
changelog.d/features/provider-quota-connection-visibility.md Normal file
View File

@@ -0,0 +1,3 @@
- Provider connections can now be shown or hidden individually on the Provider Quota page. The
visibility setting is available on each account in the provider detail view and does not affect
routing or account activation.

1
changelog.d/fixes/1253-kiro-sso-cache-clientid.md Normal file
View File

@@ -0,0 +1 @@
- **fix(oauth):** resolve Kiro AWS SSO cache client credentials by matching the token's own `clientId` (including tokens with a direct `clientId` field instead of `clientIdHash`) instead of a region/latest-expiry guess, fixing spurious "Bad credentials" on refresh when multiple stale SSO client registrations are cached (thanks @XCrag).

1
changelog.d/fixes/180-3980-responses-completed-tool-calls.md Normal file
View File

@@ -0,0 +1 @@
- **fix(translator):** synthesize tool call chunks from `response.completed` batched output when upstream omits individual `output_item.added`/`done` events, fixing `finish_reason: "stop"` instead of `"tool_calls"` for agentic clients ([#180](https://github.com/diegosouzapw/OmniRoute/issues/180), [#3980](https://github.com/diegosouzapw/OmniRoute/issues/3980))

1
changelog.d/fixes/2057-combo-custom-provider-models.md Normal file
View File

@@ -0,0 +1 @@
- **fix(dashboard):** include never-tested custom provider connections in the combo builder's active-provider list so their models load without requiring a manual connection test first. (thanks @fajarbossit)

1
changelog.d/fixes/2482-minimax-image-provider.md Normal file
View File

@@ -0,0 +1 @@
- **fix(providers):** MiniMax Text-to-Image now works — a `minimax` image-generation provider (`minimax-image` format, `image-01`/`image-01-live` models) was registered, since MiniMax previously had entries in the music/audio/video registries but none in the image registry, so any MiniMax image-model request fell through to a 404/unmatched-format response. (thanks @felipeleite)

1
changelog.d/fixes/2540-gpt5-tools-reasoning-effort.md Normal file
View File

@@ -0,0 +1 @@
- **fix(openai):** strip `reasoning_effort`/`reasoning` for GPT-5.x models on the raw `openai` Chat Completions surface when the request carries function `tools` — upstream rejects that combination with HTTP 400 ("Function tools with reasoning_effort are not supported ... Please use /v1/responses instead"), and the dashboard has no `reasoning_effort:"none"` override to work around it client-side — thanks @techsolutionmta

1
changelog.d/fixes/6764-fusion-combo-ref.md Normal file
View File

@@ -0,0 +1 @@
- **fix(routing):** fusion combos no longer silently drop `combo-ref` panel members — a referenced combo is now dispatched as one black-box panel voice instead of being dropped (#6764)

1
changelog.d/fixes/6916-provider-limits-spacing-local.md Normal file
View File

@@ -0,0 +1 @@
- fix(providers): `PROVIDER_LIMITS_SYNC_SPACING_MS` now also throttles local / API-key (Ollama) connections, not just OAuth — spaced between concurrency chunks so a local endpoint isn't hit by a simultaneous refresh burst (#6916)

1
changelog.d/fixes/6953-empty-signature-thinking-block.md Normal file
View File

@@ -0,0 +1 @@
- fix(sse): stop forwarding empty-signature thinking blocks verbatim to Anthropic-native legs, which permanently poisoned combo fallback (#6953)

1
changelog.d/fixes/6984-hide-disabled-connections-combos.md Normal file
View File

@@ -0,0 +1 @@
- **fix(dashboard):** the combos builder now hides provider connections the user has explicitly disabled, instead of relying only on stale test-status (#6984 — thanks @attid).

1
changelog.d/fixes/6986-grok-cli-tools-cap.md Normal file
View File

@@ -0,0 +1 @@
- **fix(providers):** cap grok-cli tools at 200 per request, matching xAI's cli-chat-proxy limit, and document the non-reasoning capability of grok-build/grok-composer-2.5-fast in the registry (#6986, thanks @gitcommit90)

1
changelog.d/fixes/7032-auggie-model-ids-v032.md Normal file
View File

@@ -0,0 +1 @@
- **fix(providers):** Auggie (Augment CLI) model registry updated to the real v0.32.0 CLI model IDs, with a live `auggie model list` auto-discovery fallback for future renames; the old pre-v0.32.0 IDs (`claude-sonnet-4.6`, `claude-opus-4.6`, `claude-haiku-4.5`, `gemini-3.1-pro`, `gemini-3.0-flash`, the `gpt-5.4`/`gpt-5.5` high/medium variants) are a **breaking rename**, but a backward-compat alias map in `resolveAuggieModel()` transparently remaps them to their v0.32.0 equivalents so existing saved combos keep working without any manual update (#7032 — thanks @oyi77).

1
changelog.d/fixes/7049-dashboard-port-env-fallback.md Normal file
View File

@@ -0,0 +1 @@
- **fix(cli):** `omniroute dashboard` (no `--port` flag) now respects `PORT` from the environment instead of always opening `localhost:20128`, matching `serve`/`launch` precedence (`--port` > `PORT` env > `20128` default) (#7049 — thanks @kaon0388v1).

1
changelog.d/fixes/7171-codex-responses-lite-parallel-tools.md Normal file
View File

@@ -0,0 +1 @@
- **fix(executors):** Codex Responses Lite requests force serial tool calls required by the upstream API ([#7171](https://github.com/diegosouzapw/OmniRoute/pull/7171)) — thanks @fenix007

1
changelog.d/fixes/7206-preserve-reasoning-openai-bridge.md Normal file
View File

@@ -0,0 +1 @@
- **fix(translator):** preserve Gemini thinking-mode `thought:true` parts as `reasoning_content` instead of leaking them into visible assistant text on the OpenAI request bridge. (thanks @warelik)

1
changelog.d/fixes/7207-openai-projection-gemini-clients.md Normal file
View File

@@ -0,0 +1 @@
- **fix(translator):** register the missing OpenAI→Gemini response projection so combo-routed OpenAI-native providers no longer leak raw `chat.completion.chunk` shapes to Gemini-format clients. (thanks @warelik)

1
changelog.d/fixes/7208-cli-version-fastpath.md Normal file
View File

@@ -0,0 +1 @@
- **fix(cli):** `omniroute --version` now fast-paths before the tsx/esm + polyfill imports, env-file loading, and Commander's full command registration, cutting local runtime from ~1.5s to ~0.3s. (thanks @Jordannst)

1
changelog.d/fixes/7226-dast-smoke-backend-only.md Normal file
View File

@@ -0,0 +1 @@
- fix(ci): build dast-smoke and nightly API-only smoke workflows with `OMNIROUTE_BUILD_BACKEND_ONLY=1` to skip the unused dashboard UI graph and stop the multi-minute build variance/timeouts (#7226)

Some files were not shown because too many files have changed in this diff Show More