lynkr 9.6.0 → 9.7.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "lynkr",
-  "version": "9.6.0",
+  "version": "9.7.0",
   "description": "Self-hosted LLM gateway and tier-routing proxy for Claude Code, Cursor, and Codex. Routes across Ollama, AWS Bedrock, OpenRouter, Databricks, Azure OpenAI, llama.cpp, and LM Studio with prompt caching, MCP tools, and 60-80% cost savings.",
   "main": "index.js",
   "bin": {
@@ -16,7 +16,7 @@
     "dev": "nodemon index.js",
     "lint": "eslint src index.js",
     "test": "npm run test:unit && npm run test:performance",
-    "test:unit": "DATABRICKS_API_KEY=test-key DATABRICKS_API_BASE=http://test.com node --test test/routing.test.js test/hybrid-routing-integration.test.js test/web-tools.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/toon-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/distill.test.js test/large-payload.test.js test/code-mode.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/model-registry-cost.test.js test/task-decomposition.test.js test/output-format-guard.test.js test/tier-fallback.test.js",
+    "test:unit": "DATABRICKS_API_KEY=test-key DATABRICKS_API_BASE=http://test.com node --test test/routing.test.js test/hybrid-routing-integration.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/toon-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/distill.test.js test/large-payload.test.js test/code-mode.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/model-registry-cost.test.js test/task-decomposition.test.js test/output-format-guard.test.js test/tier-fallback.test.js test/wrap.test.js",
     "test:memory": "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:new-features": "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": "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",
@@ -79,6 +79,7 @@
     "express": "^5.1.0",
     "express-rate-limit": "^8.2.1",
     "fast-glob": "^3.3.2",
+    "graphify": "^1.0.0",
     "hnswlib-node": "^3.0.0",
     "js-tiktoken": "^1.0.20",
     "js-yaml": "^4.1.1",
@@ -89,7 +90,7 @@
     "undici": "^6.22.0"
   },
   "optionalDependencies": {
-    "better-sqlite3": "^12.6.2",
+    "better-sqlite3": "^12.11.1",
     "dockerode": "^4.0.2",
     "tree-sitter": "^0.21.1",
     "tree-sitter-javascript": "^0.21.0",

package/scripts/build-knn-index.js

@@ -51,7 +51,7 @@ async function _readTelemetry(days) {
     return db
       .prepare(
         `SELECT request_text AS query, provider, model, quality_score AS quality,
-                cost, total_latency_ms AS latency, tier
+                cost_usd AS cost, latency_ms AS latency, tier
            FROM routing_telemetry
           WHERE timestamp >= ?
             AND quality_score IS NOT NULL

package/scripts/convert-routellm.py

@@ -0,0 +1,105 @@
+#!/usr/bin/env python3
+"""
+Convert routellm/gpt4_dataset (train.jsonl) → Lynkr kNN bootstrap JSONL.
+
+Stream-downloads from HuggingFace and maps mixtral_score (1-5) to your
+TIER_* model config so the kNN index learns to recommend YOUR real models,
+not RouteLLM's pool (mixtral / gpt-4).
+
+Output format matches scripts/build-knn-index.js bootstrap input:
+    {"query": "...", "provider": "ollama", "model": "minimax-m2.5:cloud",
+     "quality": 95, "cost": 0.001, "latency": 200, "tier": "SIMPLE"}
+
+Usage:
+    .venv/bin/python scripts/convert-routellm.py [--limit 30000] -o routellm.jsonl
+"""
+import argparse
+import json
+import sys
+import urllib.request
+import ssl
+
+# Map mixtral_score → user's tier config.
+# Spread is intentionally aggressive: only score=5 (Mixtral truly nailed it)
+# stays SIMPLE; score=4 escalates to MEDIUM so the kNN index has enough MEDIUM
+# examples to actually recommend non-SIMPLE tiers (vs the previous mapping
+# where 86% of records were SIMPLE and kNN never disagreed with the heuristic).
+SCORE_TO_ROUTE = {
+    5: {"tier": "SIMPLE",    "provider": "ollama",          "model": "minimax-m2.5:cloud", "quality": 95, "cost": 0.001, "latency": 200},
+    4: {"tier": "MEDIUM",    "provider": "azure-anthropic", "model": "claude-sonnet-4-6",  "quality": 80, "cost": 0.003, "latency": 1500},
+    3: {"tier": "MEDIUM",    "provider": "azure-anthropic", "model": "claude-sonnet-4-6",  "quality": 70, "cost": 0.003, "latency": 1500},
+    2: {"tier": "COMPLEX",   "provider": "azure-anthropic", "model": "claude-sonnet-4-6",  "quality": 55, "cost": 0.003, "latency": 1500},
+    1: {"tier": "REASONING", "provider": "azure-anthropic", "model": "claude-opus-4-8",    "quality": 40, "cost": 0.015, "latency": 3500},
+}
+
+URL = "https://huggingface.co/datasets/routellm/gpt4_dataset/resolve/main/train.jsonl"
+
+
+def main():
+    p = argparse.ArgumentParser()
+    p.add_argument("--output", "-o", default="data/routellm-bootstrap.jsonl")
+    p.add_argument("--limit", type=int, default=None,
+                   help="Only convert first N rows")
+    args = p.parse_args()
+
+    print(f"Streaming {URL} …", file=sys.stderr)
+    # Some macOS Python builds have SSL issues with huggingface.co — fall back
+    # to unverified context if needed. The data is public, no auth.
+    ctx = ssl.create_default_context()
+    try:
+        with urllib.request.urlopen(URL, context=ctx, timeout=60) as resp:
+            _stream(resp, args.output, args.limit)
+    except (ssl.SSLError, OSError) as e:
+        print(f"SSL strict failed ({e}); retrying with unverified context", file=sys.stderr)
+        ctx = ssl._create_unverified_context()
+        with urllib.request.urlopen(URL, context=ctx, timeout=60) as resp:
+            _stream(resp, args.output, args.limit)
+
+
+def _stream(resp, out_path, limit):
+    written = 0
+    by_score = {s: 0 for s in SCORE_TO_ROUTE}
+    skipped = 0
+    with open(out_path, "w") as out:
+        for line in resp:
+            if limit and written >= limit:
+                break
+            try:
+                row = json.loads(line)
+            except Exception:
+                skipped += 1
+                continue
+            score = row.get("mixtral_score")
+            if score not in SCORE_TO_ROUTE:
+                skipped += 1
+                continue
+            route = SCORE_TO_ROUTE[score]
+            rec = {
+                "query": row.get("prompt", ""),
+                "provider": route["provider"],
+                "model": route["model"],
+                "quality": route["quality"],
+                "cost": route["cost"],
+                "latency": route["latency"],
+                "tier": route["tier"],
+            }
+            if not rec["query"]:
+                skipped += 1
+                continue
+            out.write(json.dumps(rec) + "\n")
+            written += 1
+            by_score[score] += 1
+            if written % 5000 == 0:
+                print(f"  {written} written…", file=sys.stderr)
+
+    print(f"\nWrote {written} records to {out_path} ({skipped} skipped)", file=sys.stderr)
+    print(f"By mixtral_score: {by_score}", file=sys.stderr)
+    print(f"\nTier distribution:", file=sys.stderr)
+    for score, route in SCORE_TO_ROUTE.items():
+        n = by_score[score]
+        if n:
+            print(f"  {route['tier']:>10}  {route['provider']}:{route['model']:30s}  n={n}", file=sys.stderr)
+
+
+if __name__ == "__main__":
+    main()