feat: add OpenScale provider

.env.example

@@ -142,6 +142,16 @@ RUNCRATE_MODEL=deepseek-ai/DeepSeek-V4.1-Flash
 # DESCRIPTION: Runcrate Chat Completions endpoint.
 RUNCRATE_ENDPOINT=https://api.runcrate.ai/v1/chat/completions
 
+# ------------------------------------------------------------------------------
+# OpenScale (OpenAI-compatible)
+# ------------------------------------------------------------------------------
+# DESCRIPTION: OpenScale API key from https://app.openscale.so/app/keys.
+# OPENSCALE_API_KEY=your-openscale-api-key
+# DESCRIPTION: Default OpenScale text model.
+OPENSCALE_MODEL=deepseek/deepseek-v4.1-flash
+# DESCRIPTION: OpenScale Chat Completions endpoint.
+OPENSCALE_ENDPOINT=https://api.openscale.so/v1/chat/completions
+
 # ------------------------------------------------------------------------------
 # Ollama (local models)
 # ------------------------------------------------------------------------------

README.md

@@ -223,6 +223,7 @@ Claude Code / Cursor / Codex / Cline / Continue
 | **Cheaper Inference** | Cloud | GPT, Claude, Gemini, DeepSeek, and other OpenAI-compatible models | $-$$$ |
 | **AtmoRouter** | Cloud | Claude, GPT, Gemini, GLM, Kimi, Qwen, DeepSeek, and other OpenAI-compatible models | $-$$ |
 | **Runcrate** | Cloud | DeepSeek, GLM, Kimi, Qwen, gpt-oss, and other open-weight models | $-$$ |
+| **OpenScale** | Cloud | DeepSeek V4.1 Flash, GLM 5.3 Flash | $ |
 | **DeepSeek** | Cloud | DeepSeek R1, Reasoner | $ |
 | **Z.ai** | Cloud | GLM-4.7, GLM-4.5-Air | $ |
 | **Moonshot AI** | Cloud | Kimi K2.6, Kimi K3 | $ |

bin/lynkr-init.js

@@ -136,6 +136,17 @@ const PROVIDERS = {
     ],
     defaultModel: 'deepseek-ai/DeepSeek-V4.1-Flash',
   },
+  openscale: {
+    label: 'OpenScale (OpenAI-compatible)',
+    local: false,
+    creds: [
+      { key: 'OPENSCALE_API_KEY', label: 'OpenScale API key', secret: true },
+    ],
+    extras: [
+      { key: 'OPENSCALE_ENDPOINT', label: 'Chat Completions endpoint', default: 'https://api.openscale.so/v1/chat/completions' },
+    ],
+    defaultModel: 'deepseek/deepseek-v4.1-flash',
+  },
   openrouter: {
     label: 'OpenRouter (100+ models, one key)',
     local: false,
@@ -239,7 +250,7 @@ const PROVIDERS = {
 
 const PROVIDER_ORDER = [
   'ollama', 'llamacpp', 'lmstudio',
-  'azure-anthropic', 'azure-openai', 'openai', 'atlas', 'cheaperinference', 'atmorouter', 'runcrate', 'openrouter', 'edenai',
+  'azure-anthropic', 'azure-openai', 'openai', 'atlas', 'cheaperinference', 'atmorouter', 'runcrate', 'openscale', 'openrouter', 'edenai',
   'databricks', 'bedrock', 'vertex', 'zai', 'moonshot', 'baidu', 'fireworks', 'orcarouter',
 ];
 const TIERS = ['SIMPLE', 'MEDIUM', 'COMPLEX', 'REASONING'];

documentation/providers.md

@@ -934,6 +934,42 @@ TIER_REASONING=runcrate:moonshotai/Kimi-K2.6
 
 ---
 
+### 8e. OpenScale (OpenAI-Compatible)
+
+**Best for:** Low-cost DeepSeek V4.1 Flash and GLM 5.3 Flash for agent workloads, through Lynkr's static or tier-based routing
+
+#### Configuration
+
+```env
+MODEL_PROVIDER=openscale
+OPENSCALE_API_KEY=your-openscale-api-key
+OPENSCALE_MODEL=deepseek/deepseek-v4.1-flash
+OPENSCALE_ENDPOINT=https://api.openscale.so/v1/chat/completions
+```
+
+Create a key at [app.openscale.so/app/keys](https://app.openscale.so/app/keys). The endpoint is OpenAI-compatible, so Lynkr converts Anthropic messages and tools to Chat Completions requests and transforms streamed OpenAI SSE events back to Anthropic events.
+
+OpenScale can also be selected per tier:
+
+```env
+TIER_SIMPLE=openscale:deepseek/deepseek-v4.1-flash
+TIER_MEDIUM=openscale:deepseek/deepseek-v4.1-flash
+TIER_COMPLEX=openscale:z-ai/glm-5.3-flash
+TIER_REASONING=openscale:deepseek/deepseek-v4.1-flash
+```
+
+`OPENSCALE_MODEL` is the static-routing default. A model named in `TIER_*` takes precedence for that tier. The full model list, with context windows, limits and prices, is public at `GET https://api.openscale.so/v1/models`.
+
+#### Behavior
+
+- Supports non-streaming and streaming Chat Completions
+- Supports Anthropic-format tools through Lynkr's existing OpenAI conversion path
+- Relays model reasoning as `reasoning_content`
+- Uses Bearer authentication and accepts a custom `OPENSCALE_ENDPOINT`
+- Does not automatically replay billable Chat Completions POST requests
+
+---
+
 ### 9. LM Studio (Local with GUI)
 
 **Best for:** Local models with graphical interface

package.json

@@ -38,7 +38,7 @@
     "start:supervised": "while true; do node index.js 2>&1 | npx pino-pretty --sync; code=$?; echo \"[supervisor] lynkr exited ($code) — restarting in 3s\"; sleep 3; done",
     "lint": "eslint src index.js",
     "test": "npm run test:unit && npm run test:performance",
-    "test:unit": "LYNKR_KNN_DIR=/tmp/lynkr-test-knn DATABRICKS_API_KEY=test-key DATABRICKS_API_BASE=http://test.com LOG_FILE_ENABLED=false node --test test/routing.test.js test/hybrid-routing-integration.test.js test/retry-logic.test.js test/sse-transformer.test.js test/passthrough-stream.test.js test/passthrough-mode.test.js test/openrouter-error-resilience.test.js test/format-conversion.test.js test/azure-openai-config.test.js test/azure-openai-format-conversion.test.js test/azure-openai-routing.test.js test/azure-openai-streaming.test.js test/azure-openai-error-resilience.test.js test/azure-openai-integration.test.js test/openai-integration.test.js test/atlas-integration.test.js test/cheaperinference-integration.test.js test/atmorouter-integration.test.js test/runcrate-integration.test.js test/toon-compression.test.js test/gcf-compression.test.js test/llamacpp-integration.test.js test/resilience.test.js test/telemetry-routing.test.js test/memory/store.test.js test/memory/surprise.test.js test/memory/extractor.test.js test/memory/search.test.js test/memory/retriever.test.js test/memory/distiller.test.js test/memory/distiller-freeze.test.js test/memory/wiki.test.js test/memory/skills-cache.test.js test/memory/tencentdb-launcher.test.js test/distill.test.js test/large-payload.test.js test/prompt-cache-injection.test.js test/risk-analyzer.test.js test/interaction-block.test.js test/preflight.test.js test/token-reduction.test.js test/session-affinity.test.js test/cache-state.test.js test/cache-switch-cost.test.js test/lens-recommendations.test.js test/model-registry-cost.test.js test/output-format-guard.test.js test/tier-fallback.test.js test/wrap.test.js test/init.test.js test/tool-call-response-metadata.test.js test/degradation.test.js test/routing-telemetry-columns.test.js test/sticky-routing.test.js test/knn-ambiguous-escalate.test.js test/deescalator.test.js test/client-profiles.test.js test/openai-ingress-tool-injection.test.js test/tool-result-compression-gate.test.js test/strip-internal-fields.test.js test/complexity-tool-subtraction.test.js test/bandit.test.js test/routing-propensity.test.js test/reward-pipeline.test.js test/knn-cold-start.test.js test/calibration.test.js test/feedback-loop.test.js test/session-fingerprint.test.js test/side-request-guards.test.js test/verifier.test.js test/intent-score.test.js test/difficulty-classifier.test.js test/classifier-setup.test.js test/usage-stats.test.js test/loop-guard.test.js test/moonshot-model-mapping.test.js test/baidu-model-mapping.test.js test/tenant-policy-ingress-parity.test.js test/decide.test.js test/embeddings-degradation.test.js test/health-probe.test.js test/stuck-detector.test.js test/onnx-embedder.test.js test/ope.test.js test/hierarchical-budget.test.js test/token-rate-limit.test.js test/otel-export.test.js test/mcp-broker.test.js test/compression-budget.test.js test/gpt-utils.test.js test/dedup-observe-only.test.js test/context-window-header.test.js test/token-budget-auto.test.js test/opencode-setup.test.js test/auth-mode-first-party.test.js test/harness-envelope.test.js test/task-ledger.test.js test/jev-router.test.js test/jev-routing.test.js test/force-patterns.test.js test/upstream-fidelity.test.js test/tool-schema-compression.test.js test/passthrough-route.test.js test/quota-ledger.test.js test/shortfall-semantic.test.js test/routing-decisions.test.js test/routing-corpus.test.js test/switch-gate-grounding.test.js",
+    "test:unit": "LYNKR_KNN_DIR=/tmp/lynkr-test-knn DATABRICKS_API_KEY=test-key DATABRICKS_API_BASE=http://test.com LOG_FILE_ENABLED=false node --test test/routing.test.js test/hybrid-routing-integration.test.js test/retry-logic.test.js test/sse-transformer.test.js test/passthrough-stream.test.js test/passthrough-mode.test.js test/openrouter-error-resilience.test.js test/format-conversion.test.js test/azure-openai-config.test.js test/azure-openai-format-conversion.test.js test/azure-openai-routing.test.js test/azure-openai-streaming.test.js test/azure-openai-error-resilience.test.js test/azure-openai-integration.test.js test/openai-integration.test.js test/atlas-integration.test.js test/cheaperinference-integration.test.js test/atmorouter-integration.test.js test/runcrate-integration.test.js test/openscale-integration.test.js test/toon-compression.test.js test/gcf-compression.test.js test/llamacpp-integration.test.js test/resilience.test.js test/telemetry-routing.test.js test/memory/store.test.js test/memory/surprise.test.js test/memory/extractor.test.js test/memory/search.test.js test/memory/retriever.test.js test/memory/distiller.test.js test/memory/distiller-freeze.test.js test/memory/wiki.test.js test/memory/skills-cache.test.js test/memory/tencentdb-launcher.test.js test/distill.test.js test/large-payload.test.js test/prompt-cache-injection.test.js test/risk-analyzer.test.js test/interaction-block.test.js test/preflight.test.js test/token-reduction.test.js test/session-affinity.test.js test/cache-state.test.js test/cache-switch-cost.test.js test/lens-recommendations.test.js test/model-registry-cost.test.js test/output-format-guard.test.js test/tier-fallback.test.js test/wrap.test.js test/init.test.js test/tool-call-response-metadata.test.js test/degradation.test.js test/routing-telemetry-columns.test.js test/sticky-routing.test.js test/knn-ambiguous-escalate.test.js test/deescalator.test.js test/client-profiles.test.js test/openai-ingress-tool-injection.test.js test/tool-result-compression-gate.test.js test/strip-internal-fields.test.js test/complexity-tool-subtraction.test.js test/bandit.test.js test/routing-propensity.test.js test/reward-pipeline.test.js test/knn-cold-start.test.js test/calibration.test.js test/feedback-loop.test.js test/session-fingerprint.test.js test/side-request-guards.test.js test/verifier.test.js test/intent-score.test.js test/difficulty-classifier.test.js test/classifier-setup.test.js test/usage-stats.test.js test/loop-guard.test.js test/moonshot-model-mapping.test.js test/baidu-model-mapping.test.js test/tenant-policy-ingress-parity.test.js test/decide.test.js test/embeddings-degradation.test.js test/health-probe.test.js test/stuck-detector.test.js test/onnx-embedder.test.js test/ope.test.js test/hierarchical-budget.test.js test/token-rate-limit.test.js test/otel-export.test.js test/mcp-broker.test.js test/compression-budget.test.js test/gpt-utils.test.js test/dedup-observe-only.test.js test/context-window-header.test.js test/token-budget-auto.test.js test/opencode-setup.test.js test/auth-mode-first-party.test.js test/harness-envelope.test.js test/task-ledger.test.js test/jev-router.test.js test/jev-routing.test.js test/force-patterns.test.js test/upstream-fidelity.test.js test/tool-schema-compression.test.js test/passthrough-route.test.js test/quota-ledger.test.js test/shortfall-semantic.test.js test/routing-decisions.test.js test/routing-corpus.test.js test/switch-gate-grounding.test.js",
     "test:memory": "LYNKR_KNN_DIR=/tmp/lynkr-test-knn DATABRICKS_API_KEY=test-key DATABRICKS_API_BASE=http://test.com node --test test/memory/store.test.js test/memory/surprise.test.js test/memory/extractor.test.js test/memory/search.test.js test/memory/retriever.test.js test/memory/distiller.test.js test/memory/distiller-freeze.test.js test/memory/wiki.test.js test/memory/skills-cache.test.js test/memory/tencentdb-launcher.test.js",
     "test:new-features": "LYNKR_KNN_DIR=/tmp/lynkr-test-knn DATABRICKS_API_KEY=test-key DATABRICKS_API_BASE=http://test.com node --test test/passthrough-mode.test.js test/openrouter-error-resilience.test.js test/format-conversion.test.js",
     "test:performance": "LYNKR_KNN_DIR=/tmp/lynkr-test-knn DATABRICKS_API_KEY=test-key DATABRICKS_API_BASE=http://test.com node test/hybrid-routing-performance.test.js && DATABRICKS_API_KEY=test-key DATABRICKS_API_BASE=http://test.com node test/performance-tests.js",

src/api/providers-handler.js

@@ -160,6 +160,19 @@ async function getConfiguredProviders() {
     });
   }
 
+  // Check OpenScale (OpenAI-compatible Chat Completions)
+  if (config.openscale?.apiKey) {
+    providers.push({
+      name: "openscale",
+      type: "openscale",
+      baseUrl: config.openscale.endpoint || "https://api.openscale.so/v1/chat/completions",
+      enabled: true,
+      models: [
+        { id: config.openscale.model || "deepseek/deepseek-v4.1-flash", name: "Configured Model" },
+      ]
+    });
+  }
+
   // Check OpenRouter
   if (config.openrouter?.apiKey) {
     providers.push({

src/clients/databricks.js

@@ -1932,6 +1932,72 @@ async function invokeRuncrate(body) {
   return response;
 }
 
+async function invokeOpenScale(body) {
+  if (!config.openscale?.apiKey) {
+    throw new Error("OpenScale API key is not configured.");
+  }
+
+  const {
+    convertAnthropicToolsToOpenRouter,
+    convertAnthropicMessagesToOpenRouter
+  } = require("./openrouter-utils");
+
+  const endpoint = config.openscale.endpoint || "https://api.openscale.so/v1/chat/completions";
+  const headers = {
+    "Authorization": `Bearer ${config.openscale.apiKey}`,
+    "Content-Type": "application/json",
+  };
+
+  const messages = convertAnthropicMessagesToOpenRouter(body.messages || []);
+  if (body.system) {
+    messages.unshift({ role: "system", content: body.system });
+  }
+
+  const openScaleBody = {
+    model: body._suggestionModeModel || body._tierModel || config.openscale.model || "deepseek/deepseek-v4.1-flash",
+    messages,
+    temperature: body.temperature ?? 0.7,
+    max_tokens: body.max_tokens ?? 16384,
+    top_p: body.top_p ?? 1.0,
+    stream: body.stream ?? false,
+  };
+
+  const toolsToSend = Array.isArray(body.tools) ? body.tools : [];
+
+  if (toolsToSend.length > 0) {
+    openScaleBody.tools = convertAnthropicToolsToOpenRouter(toolsToSend);
+    openScaleBody.parallel_tool_calls = false;
+    openScaleBody.tool_choice = forwardToolChoice(body);
+  }
+
+  logger.debug({
+    endpoint,
+    model: openScaleBody.model,
+    hasTools: !!openScaleBody.tools,
+    toolCount: openScaleBody.tools?.length || 0,
+    temperature: openScaleBody.temperature,
+    max_tokens: openScaleBody.max_tokens,
+  }, "=== OPENSCALE REQUEST ===");
+
+  // Chat completions are billable POSTs, so OpenScale requests are never
+  // replayed automatically (same policy as invokeAtmoRouter). A 429 is thrown
+  // so invokeModel's caller can escalate to a different provider/tier.
+  const response = await performJsonRequest(endpoint, {
+    headers,
+    body: openScaleBody,
+    maxRetriesOverride: 0,
+    retryableStatusesOverride: [],
+  }, "OpenScale");
+
+  if (!response.ok && response.status === 429) {
+    const err = new Error(`OpenScale rate-limited: ${String(response.json?.error?.message || '').slice(0, 120)}`);
+    err.status = 429;
+    throw err;
+  }
+
+  return response;
+}
+
 async function invokeLlamaCpp(body, _incomingHeaders = {}) {
   if (!config.llamacpp?.endpoint) {
     throw new Error("llama.cpp endpoint is not configured.");
@@ -3962,6 +4028,7 @@ const PROVIDER_INVOKERS = {
   cheaperinference: invokeCheaperInference,
   atmorouter: invokeAtmoRouter,
   runcrate: invokeRuncrate,
+  openscale: invokeOpenScale,
   llamacpp: invokeLlamaCpp,
   lmstudio: invokeLMStudio,
   bedrock: invokeBedrock,
@@ -4900,6 +4967,7 @@ module.exports = {
   invokeCheaperInference,
   invokeAtmoRouter,
   invokeRuncrate,
+  invokeOpenScale,
   invokeOrcaRouter,
   invokeCursor,
   PROVIDER_INVOKERS,

src/clients/provider-capabilities.js

@@ -9,7 +9,7 @@ const NATIVE_THINKING_BEDROCK_MODELS = [
   "claude-haiku",
 ];
 
-const REASONING_CONTENT_PROVIDERS = new Set(["moonshot", "openrouter", "edenai", "openai", "azure-openai", "atlas", "cheaperinference", "atmorouter", "runcrate", "orcarouter"]);
+const REASONING_CONTENT_PROVIDERS = new Set(["moonshot", "openrouter", "edenai", "openai", "azure-openai", "atlas", "cheaperinference", "atmorouter", "runcrate", "openscale", "orcarouter"]);
 
 function supportsNativeThinking(providerType, model) {
   if (NATIVE_THINKING_PROVIDERS.has(providerType)) return true;