lynkr 9.9.1 → 9.10.0

package/README.md

@@ -68,7 +68,7 @@ The fastest path is the interactive wizard:
 lynkr init
 ```
 
-It asks four questions — usage mode (Claude Pro/Max via wrap, or direct API keys), tier picks for SIMPLE/MEDIUM/COMPLEX/REASONING across the 12 supported providers, credentials for what you chose, and a few routing-intelligence knobs — then writes a fully-populated `.env` with sensible production defaults for everything else (caching, compression, policy budgets, MCP sandbox, agents, rate limiting).
+It asks four questions — usage mode (Claude Pro/Max via wrap, or direct API keys), tier picks for SIMPLE/MEDIUM/COMPLEX/REASONING across the 12 supported providers, credentials for what you chose, and a few routing-intelligence knobs — then writes a fully-populated `.env` with sensible production defaults for everything else (caching, compression, policy budgets, MCP sandbox, rate limiting).
 
 Useful flags:
 
@@ -271,17 +271,39 @@ Tier configuration is strictly authoritative — bandit exploration is constrain
 
 ## Advanced Features
 
+### Real-time SSE streaming (all tiers)
+
+Responses stream token-by-token instead of arriving all at once — including
+through the tier router. Two mechanisms, both on by default:
+
+- **Native passthrough**: when the upstream already speaks Anthropic SSE
+  (Anthropic endpoints, Z.AI, Ollama v0.14+), Lynkr pipes the bytes straight
+  through with backpressure. Kill switch: `LYNKR_NATIVE_PASSTHROUGH=false`.
+- **Cross-format transform**: OpenAI-format upstreams (OpenAI, Azure OpenAI,
+  OpenRouter, Databricks, llama.cpp, LM Studio) are reshaped into Anthropic
+  events in flight — including reassembling tool-call argument fragments into
+  clean `tool_use` blocks. Kill switch: `LYNKR_STREAM_TRANSFORM=false`.
+
+The `LYNKR_VISIBLE_ROUTING` badge streams too (injected as the first content
+block), and telemetry is recorded on stream close with real token counts.
+Fallback safety: if an upstream fails before the first byte, the request
+falls back to the buffered path automatically.
+
+```bash
+# Ollama thinking models (MiniMax): streaming skips the <think>-leak repair.
+# If you see raw <think> text in responses, buffer that provider instead:
+LYNKR_OLLAMA_BUFFER_RESPONSES=true   # default true; false = stream Ollama
+```
+
 ### Token Optimization (60-80% savings)
 ```bash
 # Enable all optimizations
 PROMPT_CACHE_ENABLED=true
 SEMANTIC_CACHE_ENABLED=true
-TOOL_INJECTION_ENABLED=false
-CODE_MODE_ENABLED=true
 ```
 
-Always-on (no config): **smart tool selection** (server mode), **RTK tool-result
-compression** (test/git/grep/lint/build/JSON output), **MCP tool dedup** (drops
+Always-on (no config): **RTK tool-result compression**
+(test/git/grep/lint/build/JSON output), **MCP tool dedup** (drops
 built-in WebSearch/WebFetch when an Exa/Tavily MCP tool is present), and
 **request bypass** (Claude CLI Warmup / title-extraction calls are answered
 locally, never hitting a provider).
@@ -292,6 +314,25 @@ CAVEMAN_ENABLED=true        # off by default — nudges the model to be concise
 CAVEMAN_LEVEL=lite          # lite | full | ultra
 ```
 
+### Built-in dashboard
+
+Open `http://localhost:8081/dashboard` while Lynkr is running. No setup, reads
+the local telemetry store:
+
+- **Spend & savings** — actual cost vs what the same traffic would have cost
+  on the flagship model (the counterfactual no pass-through gateway can show,
+  since they neither pick your model nor see local-model traffic)
+- **Tier mix** — daily request breakdown across SIMPLE/MEDIUM/COMPLEX/REASONING
+- **Routing accuracy** — over-/under-provisioned request counts, a self-audit
+  of the tier router's decisions
+- **Request logs** — filterable by provider, tier, and errors, with latency,
+  tokens, and cost per request
+- **Provider health** — configured providers, credential warnings, circuit
+  breaker states
+
+JSON APIs behind it (`/dashboard/api/overview|usage|routing|logs`) if you want
+the raw numbers.
+
 ### Cost tracking & model pricing
 Per-request cost is computed from a model-pricing registry (LiteLLM → models.dev,
 cached 24h) and recorded in telemetry. Models the registry doesn't know record
@@ -419,10 +460,9 @@ Head-to-head against **LiteLLM** on the **same backends** (Ollama `minimax-m2.5`
 
 | Mechanism | Lynkr | LiteLLM | Result |
 |---|---|---|---|
-| Smart tool selection (14 tools) | **959** tokens · $0.0044 | 2,085 tokens · $0.0091 | **53% fewer tokens, 52% cheaper** |
 | TOON compression (60-item grep JSON) | **427** tokens · $0.009 | 3,458 tokens · $0.018 | **87.6% fewer tokens, 50% cheaper** |
 
-Lynkr strips irrelevant tool schemas (smart tool selection) and binary-compresses large JSON tool results (TOON) — both in-process, no added latency.
+Lynkr binary-compresses large JSON tool results (TOON) in-process, with no added latency.
 
 ### Semantic cache
 
@@ -509,10 +549,11 @@ With tier routing + token optimization: **additional 50-87% savings** on cloud p
 | **Local models** | Ollama, llama.cpp, LM Studio | Ollama only | ❌ | ❌ |
 | **Automatic tier routing** | ✅ embedding intent + 13-dimension scorer, verified cascade | ⚠️ Auto Router v2 (v1.94): heuristic under-routes, LLM classifier billed per request | ❌ | ❌ Manual metadata |
 | **TOON JSON compression** | ✅ up to 87.6% | ❌ | ❌ | ❌ |
-| **Smart tool selection** | ✅ up to 60% token reduction | ❌ | ❌ | ❌ |
+| **Upstream SSE streaming** | ✅ native passthrough + cross-format transform | ⚠️ passthrough only | ✅ | ⚠️ |
 | **Semantic cache** | ✅ 171ms hits, 0 tokens | ❌ | ❌ | ✅ Prompt cache only |
+| **Savings & routing dashboard** | ✅ spend, savings vs flagship, tier mix, routing accuracy, request logs | ⚠️ spend UI only | ⚠️ usage page | ✅ observability suite (no routing accuracy) |
 | **Long-term memory** | ✅ SQLite, per-session | ❌ | ❌ | ❌ |
-| **MCP integration** | ✅ + Code Mode (96% reduction) | ❌ | ❌ | ❌ |
+| **MCP integration** | ✅ | ❌ | ❌ | ❌ |
 | **Self-hosted** | ✅ Node.js only | ✅ Python stack | ❌ SaaS | ✅ Docker |
 | **Dependencies** | Node.js 20+ | Python, Prisma, PostgreSQL | None | Docker, Python |
 

package/bin/cli.js

@@ -11,6 +11,7 @@ const SUBCOMMANDS = {
   trajectory: path.join(__dirname, "lynkr-trajectory.js"),
   wrap:       path.join(__dirname, "wrap.js"),
   init:       path.join(__dirname, "lynkr-init.js"),
+  reset:      path.join(__dirname, "lynkr-reset.js"),
 };
 
 const sub = process.argv[2];
@@ -53,6 +54,7 @@ Usage:
   lynkr usage [options]            Show AI spend report and tier-routing savings
   lynkr stats [options]            Shareable savings-receipt card (also: lynkr usage --card)
   lynkr trajectory [options]       Export agent trajectories as JSONL training data
+  lynkr reset <resource>           Clear a stored resource (e.g. session_pins, all)
 
 Options:
   -h, --help      Show this help message

package/bin/lynkr-init.js

@@ -197,12 +197,9 @@ const BASELINE_ENV = {
   LYNKR_KNN_CONFIDENCE_HIGH: '0.55',
   LYNKR_KNN_CONFIDENCE_LOW: '0.30',
 
-  // ── Tool execution ────────────────────────────────────────────────────
-  TOOL_EXECUTION_MODE: 'client',
-  TOOL_INJECTION_ENABLED: 'false',
+  // ── Tool selection (routing signals) ──────────────────────────────────
   SMART_TOOL_SELECTION_MODE: 'disabled',
   SMART_TOOL_SELECTION_TOKEN_BUDGET: '2500',
-  CODE_MODE_ENABLED: 'true',
 
   // ── Caching ───────────────────────────────────────────────────────────
   PROMPT_CACHE_ENABLED: 'true',
@@ -253,7 +250,6 @@ const BASELINE_ENV = {
   MEMORY_DEDUP_LOOKBACK: '5',
   MEMORY_TTL: '3600000',
   TOKEN_TRACKING_ENABLED: 'true',
-  TOOL_TRUNCATION_ENABLED: 'true',
 
   // ── Prompt/output shaping ─────────────────────────────────────────────
   SYSTEM_PROMPT_MODE: 'dynamic',
@@ -280,12 +276,8 @@ const BASELINE_ENV = {
   POLICY_FILE_BLOCKED_PATHS: '/.env,.env,/etc/passwd,/etc/shadow',
   POLICY_SAFE_COMMANDS_ENABLED: 'true',
 
-  // ── Agents ────────────────────────────────────────────────────────────
+  // ── Agents (delegation prompt injection; execution is client-side) ────
   AGENTS_ENABLED: 'true',
-  AGENTS_MAX_CONCURRENT: '10',
-  AGENTS_DEFAULT_MODEL: 'haiku',
-  AGENTS_MAX_STEPS: '15',
-  AGENTS_TIMEOUT: '300000',
 
   // ── Rate limiting ─────────────────────────────────────────────────────
   RATE_LIMIT_ENABLED: 'true',
@@ -606,12 +598,12 @@ function buildEnvContent(env, isWrap, tierConfig) {
   // Group output by section in the order it appears in the generated file.
   // Mirrors the layout of the .env.example reference doc.
   const SERVER_KEYS = new Set(['PORT', 'NODE_ENV', 'REQUEST_JSON_LIMIT', 'SESSION_DB_PATH', 'WORKSPACE_ROOT', 'ENABLE_TOOL_SEARCH']);
-  const TOOL_EXEC_KEYS = new Set(['TOOL_EXECUTION_MODE', 'TOOL_INJECTION_ENABLED', 'SMART_TOOL_SELECTION_MODE', 'SMART_TOOL_SELECTION_TOKEN_BUDGET', 'CODE_MODE_ENABLED']);
+  const TOOL_EXEC_KEYS = new Set(['SMART_TOOL_SELECTION_MODE', 'SMART_TOOL_SELECTION_TOKEN_BUDGET']);
   const CACHE_KEYS = new Set([
     'PROMPT_CACHE_ENABLED', 'PROMPT_CACHE_MAX_ENTRIES', 'PROMPT_CACHE_TTL_MS',
     'SEMANTIC_CACHE_ENABLED', 'SEMANTIC_CACHE_THRESHOLD', 'SEMANTIC_CACHE_MAX_ENTRIES', 'SEMANTIC_CACHE_TTL_MS',
   ]);
-  const MEMORY_KEYS = new Set(Object.keys(merged).filter((k) => k.startsWith('MEMORY_') || k === 'TOKEN_TRACKING_ENABLED' || k === 'TOOL_TRUNCATION_ENABLED'));
+  const MEMORY_KEYS = new Set(Object.keys(merged).filter((k) => k.startsWith('MEMORY_') || k === 'TOKEN_TRACKING_ENABLED'));
   const SHAPING_KEYS = new Set([
     'SYSTEM_PROMPT_MODE', 'TOOL_DESCRIPTIONS',
     'HISTORY_COMPRESSION_ENABLED', 'HISTORY_KEEP_RECENT_TURNS', 'HISTORY_SUMMARIZE_OLDER',

package/bin/lynkr-reset.js

@@ -0,0 +1,71 @@
+#!/usr/bin/env node
+
+const path = require("path");
+const fs = require("fs");
+
+const DB_PATH =
+  process.env.LYNKR_TELEMETRY_DB ||
+  path.join(__dirname, "..", ".lynkr", "telemetry.db");
+
+const RESOURCES = {
+  session_pins: {
+    describe: "Session → provider affinity pins",
+    table: "session_pins",
+  },
+};
+
+function usage(code = 0) {
+  const lines = Object.entries(RESOURCES).map(
+    ([k, v]) => `  ${k.padEnd(16)} ${v.describe}`
+  );
+  console.log(
+`Usage: lynkr reset <resource>
+
+Resources:
+${lines.join("\n")}
+  all              Clear every resource above
+
+DB: ${DB_PATH}
+`
+  );
+  process.exit(code);
+}
+
+const target = process.argv[2];
+if (!target || target === "-h" || target === "--help") usage(0);
+
+if (target !== "all" && !RESOURCES[target]) {
+  console.error(`Error: unknown resource '${target}'.`);
+  usage(1);
+}
+
+if (!fs.existsSync(DB_PATH)) {
+  console.error(`Error: telemetry DB not found at ${DB_PATH}`);
+  process.exit(1);
+}
+
+let Database;
+try {
+  Database = require("better-sqlite3");
+} catch (err) {
+  console.error("Error: better-sqlite3 not installed. Run `npm install` in ~/claude-code.");
+  process.exit(1);
+}
+
+const db = new Database(DB_PATH);
+const targets = target === "all" ? Object.keys(RESOURCES) : [target];
+
+let hadError = false;
+for (const t of targets) {
+  const { table } = RESOURCES[t];
+  try {
+    const before = db.prepare(`SELECT COUNT(*) as n FROM ${table}`).get().n;
+    db.prepare(`DELETE FROM ${table}`).run();
+    console.log(`✓ cleared ${t} (${before} rows)`);
+  } catch (err) {
+    hadError = true;
+    console.error(`✗ ${t}: ${err.message}`);
+  }
+}
+db.close();
+process.exit(hadError ? 1 : 0);

package/config/model-tiers.json

@@ -2,80 +2,226 @@
   "tiers": {
     "SIMPLE": {
       "description": "Greetings, simple Q&A, confirmations, basic lookups",
-      "range": [0, 25],
+      "range": [
+        0,
+        25
+      ],
       "priority": 1,
       "preferred": {
-        "ollama": ["llama3.2", "gemma2", "phi3", "qwen2.5:7b", "mistral"],
-        "llamacpp": ["default"],
-        "lmstudio": ["default"],
-        "openai": ["gpt-4o-mini", "gpt-3.5-turbo"],
-        "azure-openai": ["gpt-4o-mini", "gpt-35-turbo"],
-        "anthropic": ["claude-3-haiku-20240307", "claude-3-5-haiku-20241022"],
-        "bedrock": ["anthropic.claude-3-haiku-20240307-v1:0", "amazon.nova-lite-v1:0"],
-        "databricks": ["databricks-claude-haiku-4-5", "databricks-gpt-5-nano"],
-        "google": ["gemini-2.0-flash", "gemini-1.5-flash"],
-        "openrouter": ["google/gemini-flash-1.5", "deepseek/deepseek-chat"],
-        "zai": ["GLM-4-Flash"],
-        "moonshot": ["kimi-k2-turbo-preview"]
+        "ollama": [
+          "llama3.2",
+          "gemma2",
+          "phi3",
+          "qwen2.5:7b",
+          "mistral"
+        ],
+        "llamacpp": [
+          "default"
+        ],
+        "lmstudio": [
+          "default"
+        ],
+        "openai": [
+          "gpt-4o-mini",
+          "gpt-3.5-turbo"
+        ],
+        "azure-openai": [
+          "gpt-4o-mini",
+          "gpt-35-turbo"
+        ],
+        "anthropic": [
+          "claude-3-haiku-20240307",
+          "claude-3-5-haiku-20241022"
+        ],
+        "bedrock": [
+          "anthropic.claude-3-haiku-20240307-v1:0",
+          "amazon.nova-lite-v1:0"
+        ],
+        "databricks": [
+          "databricks-claude-haiku-4-5",
+          "databricks-gpt-5-nano"
+        ],
+        "google": [
+          "gemini-2.0-flash",
+          "gemini-1.5-flash"
+        ],
+        "openrouter": [
+          "google/gemini-flash-1.5",
+          "deepseek/deepseek-chat"
+        ],
+        "zai": [
+          "GLM-4-Flash"
+        ],
+        "moonshot": [
+          "kimi-k2-turbo-preview"
+        ]
       }
     },
     "MEDIUM": {
       "description": "Code reading, simple edits, research, documentation",
-      "range": [26, 50],
+      "range": [
+        26,
+        50
+      ],
       "priority": 2,
       "preferred": {
-        "ollama": ["qwen2.5:32b", "deepseek-coder:33b", "codellama:34b"],
-        "llamacpp": ["default"],
-        "lmstudio": ["default"],
-        "openai": ["gpt-4o", "gpt-4-turbo"],
-        "azure-openai": ["gpt-4o", "gpt-4"],
-        "anthropic": ["claude-sonnet-4-20250514", "claude-3-5-sonnet-20241022"],
-        "bedrock": ["anthropic.claude-3-5-sonnet-20241022-v2:0", "amazon.nova-pro-v1:0"],
-        "databricks": ["databricks-claude-sonnet-4-5", "databricks-gpt-5-1"],
-        "google": ["gemini-1.5-pro", "gemini-2.0-pro"],
-        "openrouter": ["anthropic/claude-3.5-sonnet", "openai/gpt-4o"],
-        "zai": ["GLM-4.7"],
-        "moonshot": ["kimi-k2-turbo-preview"]
+        "ollama": [
+          "qwen2.5:32b",
+          "deepseek-coder:33b",
+          "codellama:34b"
+        ],
+        "llamacpp": [
+          "default"
+        ],
+        "lmstudio": [
+          "default"
+        ],
+        "openai": [
+          "gpt-4o",
+          "gpt-4-turbo"
+        ],
+        "azure-openai": [
+          "gpt-4o",
+          "gpt-4"
+        ],
+        "anthropic": [
+          "claude-sonnet-4-20250514",
+          "claude-3-5-sonnet-20241022"
+        ],
+        "bedrock": [
+          "anthropic.claude-3-5-sonnet-20241022-v2:0",
+          "amazon.nova-pro-v1:0"
+        ],
+        "databricks": [
+          "databricks-claude-sonnet-4-5",
+          "databricks-gpt-5-1"
+        ],
+        "google": [
+          "gemini-1.5-pro",
+          "gemini-2.0-pro"
+        ],
+        "openrouter": [
+          "anthropic/claude-3.5-sonnet",
+          "openai/gpt-4o"
+        ],
+        "zai": [
+          "GLM-4.7"
+        ],
+        "moonshot": [
+          "kimi-k2-turbo-preview"
+        ]
       }
     },
     "COMPLEX": {
       "description": "Multi-file changes, debugging, architecture, refactoring",
-      "range": [51, 75],
+      "range": [
+        51,
+        75
+      ],
       "priority": 3,
       "preferred": {
-        "ollama": ["qwen2.5:72b", "llama3.1:70b", "deepseek-coder-v2:236b"],
-        "openai": ["o1-mini", "o3-mini", "gpt-4o"],
-        "azure-openai": ["o1-mini", "gpt-4o"],
-        "anthropic": ["claude-sonnet-4-20250514", "claude-3-5-sonnet-20241022"],
-        "bedrock": ["anthropic.claude-3-5-sonnet-20241022-v2:0"],
-        "databricks": ["databricks-claude-sonnet-4-5", "databricks-gpt-5-1-codex-max"],
-        "google": ["gemini-2.5-pro", "gemini-1.5-pro"],
-        "openrouter": ["anthropic/claude-3.5-sonnet", "meta-llama/llama-3.1-405b"],
-        "zai": ["GLM-4.7"],
-        "moonshot": ["kimi-k2-turbo-preview"]
+        "ollama": [
+          "qwen2.5:72b",
+          "llama3.1:70b",
+          "deepseek-coder-v2:236b"
+        ],
+        "openai": [
+          "o1-mini",
+          "o3-mini",
+          "gpt-4o"
+        ],
+        "azure-openai": [
+          "o1-mini",
+          "gpt-4o"
+        ],
+        "anthropic": [
+          "claude-sonnet-4-20250514",
+          "claude-3-5-sonnet-20241022"
+        ],
+        "bedrock": [
+          "anthropic.claude-3-5-sonnet-20241022-v2:0"
+        ],
+        "databricks": [
+          "databricks-claude-sonnet-4-5",
+          "databricks-gpt-5-1-codex-max"
+        ],
+        "google": [
+          "gemini-2.5-pro",
+          "gemini-1.5-pro"
+        ],
+        "openrouter": [
+          "anthropic/claude-3.5-sonnet",
+          "meta-llama/llama-3.1-405b"
+        ],
+        "zai": [
+          "GLM-4.7"
+        ],
+        "moonshot": [
+          "kimi-k2-turbo-preview"
+        ]
       }
     },
     "REASONING": {
       "description": "Complex analysis, security audits, novel problems, deep thinking",
-      "range": [76, 100],
+      "range": [
+        76,
+        100
+      ],
       "priority": 4,
       "preferred": {
-        "openai": ["o1", "o1-pro", "o3"],
-        "azure-openai": ["o1", "o1-pro"],
-        "anthropic": ["claude-opus-4-20250514", "claude-3-opus-20240229"],
-        "bedrock": ["anthropic.claude-3-opus-20240229-v1:0"],
-        "databricks": ["databricks-claude-opus-4-6", "databricks-claude-opus-4-5", "databricks-gpt-5-2"],
-        "google": ["gemini-2.5-pro"],
-        "openrouter": ["anthropic/claude-3-opus", "deepseek/deepseek-reasoner", "openai/o1"],
-        "deepseek": ["deepseek-reasoner", "deepseek-r1"],
-        "moonshot": ["kimi-k2-thinking", "kimi-k2-turbo-preview"]
+        "openai": [
+          "o1",
+          "o1-pro",
+          "o3"
+        ],
+        "azure-openai": [
+          "o1",
+          "o1-pro"
+        ],
+        "anthropic": [
+          "claude-opus-4-20250514",
+          "claude-3-opus-20240229"
+        ],
+        "bedrock": [
+          "anthropic.claude-3-opus-20240229-v1:0"
+        ],
+        "databricks": [
+          "databricks-claude-opus-4-6",
+          "databricks-claude-opus-4-5",
+          "databricks-gpt-5-2"
+        ],
+        "google": [
+          "gemini-2.5-pro"
+        ],
+        "openrouter": [
+          "anthropic/claude-3-opus",
+          "deepseek/deepseek-reasoner",
+          "openai/o1"
+        ],
+        "deepseek": [
+          "deepseek-reasoner",
+          "deepseek-r1"
+        ],
+        "moonshot": [
+          "kimi-k2-thinking",
+          "kimi-k2-turbo-preview"
+        ]
       }
     }
   },
   "localProviders": {
-    "ollama": { "free": true, "defaultTier": "SIMPLE" },
-    "llamacpp": { "free": true, "defaultTier": "SIMPLE" },
-    "lmstudio": { "free": true, "defaultTier": "SIMPLE" }
+    "ollama": {
+      "free": true,
+      "defaultTier": "SIMPLE"
+    },
+    "llamacpp": {
+      "free": true,
+      "defaultTier": "SIMPLE"
+    },
+    "lmstudio": {
+      "free": true,
+      "defaultTier": "SIMPLE"
+    }
   },
   "providerAliases": {
     "azure": "azure-openai",
@@ -84,6 +230,7 @@
     "claude": "anthropic",
     "gemini": "google",
     "vertex": "google",
-    "kimi": "moonshot"
+    "kimi": "moonshot",
+    "z-ai": "zai"
   }
-}
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "lynkr",
-  "version": "9.9.1",
+  "version": "9.10.0",
   "files": [
     "index.js",
     "install.sh",
@@ -36,7 +36,7 @@
     "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 LOG_FILE_ENABLED=false 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/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/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/init.test.js test/agent-learning.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:unit": "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/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/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/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: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",

package/scripts/validate-difficulty-classifier.js

@@ -17,22 +17,29 @@ const path = require("path");
 const { classifyDifficulty, _clearCacheForTests } = require("../src/routing/difficulty-classifier");
 
 const EVAL_FILE = path.join(__dirname, "../data/difficulty-eval.jsonl");
-const RESULTS_FILE = path.join(__dirname, "../data/difficulty-eval-results.jsonl");
 const TIERS = ["SIMPLE", "MEDIUM", "COMPLEX", "REASONING"];
 
 async function main() {
+  // --file=data/xyz.jsonl runs an alternate eval set (e.g. the follow-up
+  // slice with conversation context). Results land next to the input file.
+  const fileArg = process.argv.find((a) => a.startsWith("--file="));
+  const evalFile = fileArg ? path.resolve(fileArg.slice(7)) : EVAL_FILE;
+  const resultsFile = evalFile.replace(/\.jsonl$/, "-results.jsonl");
+
   _clearCacheForTests();
-  const lines = fs.readFileSync(EVAL_FILE, "utf8").split("\n").filter(Boolean);
+  const lines = fs.readFileSync(evalFile, "utf8").split("\n").filter(Boolean);
   const rows = lines.map(l => JSON.parse(l));
-  console.log(`Loaded ${rows.length} eval rows`);
+  console.log(`Loaded ${rows.length} eval rows from ${path.basename(evalFile)}`);
 
   // Persist incrementally so a crash mid-run preserves partial data.
-  const resultsFd = fs.openSync(RESULTS_FILE, "w");
+  const resultsFd = fs.openSync(resultsFile, "w");
   const results = [];
   const t0 = Date.now();
   let done = 0;
   for (const row of rows) {
-    const r = await classifyDifficulty(row.text);
+    // context is threaded the same way production does (router window loop
+    // → scoreIntent → classifyDifficulty); absent for standalone prompts.
+    const r = await classifyDifficulty(row.text, { context: row.context });
     const record = {
       ...row,
       predicted: r?.tier ?? null,
@@ -47,7 +54,7 @@ async function main() {
     }
   }
   fs.closeSync(resultsFd);
-  console.log(`\nDone in ${((Date.now() - t0) / 1000).toFixed(0)}s (results saved to ${RESULTS_FILE})`);
+  console.log(`\nDone in ${((Date.now() - t0) / 1000).toFixed(0)}s (results saved to ${resultsFile})`);
 
   // Overall + per-tier accuracy
   const perTier = {};
@@ -108,6 +115,20 @@ async function main() {
   console.log(`SIMPLE→REASONING: ${simpleToReasoning}`);
   console.log(`MEDIUM→COMPLEX: ${confusion.MEDIUM?.COMPLEX || 0}`);
 
+  // Confidence histogram — validates whether the confidence gate in
+  // _reconcile carries signal. A degenerate distribution (everything ≥0.9)
+  // means confidence is decorative and the band cap is the only real guard.
+  const buckets = { "<0.6": 0, "0.6-0.8": 0, "0.8-0.9": 0, "0.9-1.0": 0 };
+  for (const r of results) {
+    if (r.confidence == null) continue;
+    if (r.confidence < 0.6) buckets["<0.6"]++;
+    else if (r.confidence < 0.8) buckets["0.6-0.8"]++;
+    else if (r.confidence < 0.9) buckets["0.8-0.9"]++;
+    else buckets["0.9-1.0"]++;
+  }
+  console.log(`\n=== Confidence histogram ===`);
+  for (const [b, n] of Object.entries(buckets)) console.log(`  ${b}: ${n}`);
+
   // List misclassifications (cap at 20 per tier)
   console.log(`\n=== Misclassifications (up to 5 per tier) ===`);
   for (const t of TIERS) {

package/src/api/providers-handler.js

@@ -401,7 +401,6 @@ router.get("/config", (req, res) => {
       fallback_provider: config.modelProvider?.fallbackProvider || null,
       fallback_enabled: config.modelProvider?.fallbackEnabled || false,
       tier_routing_enabled: config.modelTiers?.enabled || false,
-      tool_execution_mode: config.toolExecutionMode || "server",
       configured_providers: providers.map(p => p.name),
       memory_enabled: config.memory?.enabled || false,
       smart_tool_selection: config.smartToolSelection?.enabled || false