lynkr 9.14.15 → 9.14.17

package/config/difficulty-anchors.json

@@ -28,5 +28,17 @@
     "design a horizontally scalable architecture for this service with failure-mode analysis",
     "Compare how databricks.js and openai-format.js each handle non-2xx upstream responses, then propose a unified error-normalization helper both could share",
     "Code review the PR #84 routing hardening changes"
+  ],
+  "frontier": [
+    "Prove the correctness of this lock-free queue implementation and identify any ABA hazards",
+    "Design a novel conflict-free replicated data type for collaborative rich-text editing and argue its convergence from first principles",
+    "Derive the optimal cache eviction policy for this access distribution and prove its competitive ratio",
+    "Diagnose this heisenbug: a race that only reproduces under load across three services, given these interleaved logs",
+    "Design a Byzantine-fault-tolerant consensus protocol variant that tolerates f faults with 2f+1 replicas by weakening liveness, and analyze exactly which guarantees are lost",
+    "Formally verify that this state machine can never deadlock, or produce a counterexample trace",
+    "Given these profiler traces, determine whether the tail latency is queueing-theoretic or GC-driven, and prove which by constructing a discriminating experiment",
+    "Reason through the security of this key-rotation scheme under an adversary who can observe but not modify traffic, and find the weakest assumption it relies on",
+    "Work out the exact memory ordering constraints this concurrent hashmap needs on ARM, and justify each barrier from the C++ memory model",
+    "Given this failing distributed transaction trace, determine whether the anomaly is write skew or lost update, and design the minimal isolation-level change that eliminates it"
   ]
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "lynkr",
-  "version": "9.14.15",
+  "version": "9.14.17",
   "files": [
     "index.js",
     "install.sh",
@@ -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/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/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/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: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/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/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: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",

package/src/api/router.js

@@ -10,6 +10,7 @@ const providersRouter = require("./providers-handler");
 const claudeDesktopGatewayRouter = require("./claude-desktop-gateway");
 const { getRoutingHeaders, getRoutingStats, analyzeComplexity, getModelTierSelector, analyzeRisk, checkSessionPin, writeSessionPin, checkPinScoreDrift } = require("../routing");
 const { resolveTierForModelId } = require("../routing/model-slots");
+const { stripHarnessEnvelope } = require("../routing/harness-envelope");
 
 // Upstream streams can die without a clean end (reader.read() never
 // resolves on a dropped socket), hanging the client forever. Every
@@ -1409,7 +1410,11 @@ router.post("/v1/messages", rateLimiter, async (req, res, next) => {
       }
       return '';
     })();
+    // Suggestion-mode detection reads the RAW text (the marker is itself
+    // wrapper text); the force/risk probes below get envelope-stripped text
+    // so Cursor's <user_info>/<rules> blocks can't fire triggers on "Hi".
     const isSuggestionMode = _lastUserText.includes('[SUGGESTION MODE:');
+    const _lastUserAskClean = stripHarnessEnvelope(_lastUserText);
     // Tool-lessness alone is NOT harness evidence: generic API clients
     // (curl, benchmarks, SDKs) legitimately send bare messages and must get
     // full routing — live regression 2026-07-08: a benchmark's security-
@@ -1535,7 +1540,7 @@ router.post("/v1/messages", rateLimiter, async (req, res, next) => {
       let _pinForceBypass = null;
       if (!sideTier && pinCheck.serve && pinCheck.reason === 'guards_passed' && !isSideRequest) {
         try {
-          const _probe = { messages: [{ role: 'user', content: _lastUserText || '' }] };
+          const _probe = { messages: [{ role: 'user', content: _lastUserAskClean || '' }] };
           const ca = require("../routing/complexity-analyzer");
           if (_lastUserText && ca.shouldForceReasoning(_probe)) _pinForceBypass = 'force_reasoning';
           else if (_lastUserText && ca.shouldForceCloud(_probe)) _pinForceBypass = 'force_cloud';
@@ -1883,6 +1888,15 @@ router.post("/v1/messages", rateLimiter, async (req, res, next) => {
           tierMethod: tier?.method || null,
           tierPinned: tier?.pinned ?? null,
           cacheState: _pinCacheState,
+          // Mid tool-exchange frames must keep serving the in-flight model
+          // (same invariant as the orchestrator's tool_history pin serves).
+          hasToolHistory: (() => {
+            try { return require("../routing/session-affinity").payloadHasToolHistory(req.body); }
+            catch { return false; }
+          })(),
+          // This branch IS the flat-fee subscription: the gate's dollar
+          // break-even leg has no premium to amortize here.
+          flatRate: true,
           // Quota pressure shortens the hold horizon inside the gate (high
           // sustained burn → descents clear sooner). Zero when the ledger has
           // no history — the gate behaves exactly as before.
@@ -1919,6 +1933,36 @@ router.post("/v1/messages", rateLimiter, async (req, res, next) => {
           logger.debug({ err: err.message }, '[Routing] Pin-hold restore failed (non-fatal)');
         }
       }
+      // Upgrades must persist the SERVED model into the pin, mirroring the
+      // pin_hold restore above — the write at the fresh-decision site stored
+      // the pre-rewrite tier model, and a pin that forgets the upgrade lets
+      // later frames descend below what actually served. Unlike pin_hold,
+      // an upgrade usually happens with no prior pin, so the payload comes
+      // from the fresh tier object. Floored (+continuation_inherit) and
+      // risk-lifted tiers stay unpinned (writeSessionPin re-checks, but the
+      // method is overridden to 'session_pin' here, so guard at the source).
+      if (
+        _passthroughRoute.action === 'upgrade'
+        && _passthroughRoute.model
+        && pinCheck?.sessionId
+        && tier?.provider
+        && !String(tier?.method || '').includes('+continuation_inherit')
+        && tier?.escalation_source !== 'risk'
+      ) {
+        try {
+          const { writeSessionPin } = require("../routing/index");
+          writeSessionPin(pinCheck.sessionId, {
+            provider: tier.provider,
+            model: _passthroughRoute.model,
+            tier: tier.tier,
+            score: tier.score ?? null,
+            method: 'session_pin',
+            reason: 'passthrough_upgrade',
+          }, req.body);
+        } catch (err) {
+          logger.debug({ err: err.message }, '[Routing] Upgrade pin persist failed (non-fatal)');
+        }
+      }
       if (_passthroughRoute.action !== 'verbatim' && _passthroughRoute.model) {
         logger.info({
           from: _passthroughClientModel,

package/src/cache/embeddings.js

@@ -145,6 +145,9 @@ const STRICT = process.env.LYNKR_EMBEDDINGS_STRICT === 'true';
 function _noteFallback(providerName, err) {
   fallbackCount += 1;
   lastProviderError = err?.message || String(err);
+  // Cooldown counts from the LAST failed dial, not the first attempt's start —
+  // the in-place retry delay must not eat into the cooldown window.
+  lastProviderAttempt = Date.now();
   if (embeddingProviderAvailable !== false) {
     embeddingProviderAvailable = false;
     degradedSince = Date.now();
@@ -168,6 +171,14 @@ function _noteRecovery(providerName) {
   degradedSince = null;
 }
 
+// One in-place retry before tripping degradation: a single transient failure
+// (Ollama cold-loading the model at boot, a blip mid-restart) was flipping
+// the WHOLE provider to hash embeddings for a full cooldown after every
+// server start (recurring live incident, last 2026-09-26). A short backoff
+// absorbs the blip; a provider that is actually down fails twice and
+// degrades exactly as before.
+const TRANSIENT_RETRY_DELAY_MS = 1500;
+
 function _wrapProvider(providerName, providerFn) {
   return async (text) => {
     // While degraded, only re-attempt the provider after the cooldown; serve
@@ -184,9 +195,25 @@ function _wrapProvider(providerName, providerFn) {
       const result = await providerFn(text);
       _noteRecovery(providerName);
       return result;
-    } catch (err) {
-      _noteFallback(providerName, err);
-      if (STRICT) throw err;
+    } catch (firstErr) {
+      // Already-degraded providers get no second chance (this attempt WAS the
+      // post-cooldown probe); healthy ones earn one retry before the flip.
+      if (embeddingProviderAvailable !== false) {
+        await new Promise((r) => setTimeout(r, TRANSIENT_RETRY_DELAY_MS));
+        try {
+          const result = await providerFn(text);
+          _noteRecovery(providerName);
+          logger.debug({ provider: providerName, error: firstErr?.message },
+            '[Embeddings] Transient provider failure absorbed by retry');
+          return result;
+        } catch (secondErr) {
+          _noteFallback(providerName, secondErr);
+          if (STRICT) throw secondErr;
+          return generateHashEmbedding(text);
+        }
+      }
+      _noteFallback(providerName, firstErr);
+      if (STRICT) throw firstErr;
       return generateHashEmbedding(text);
     }
   };