ur-agent 1.37.2 → 1.37.4

package/docs/providers.md

@@ -420,3 +420,32 @@ Local/server providers use their normal endpoints:
 - LM Studio: `http://localhost:1234/v1`
 - llama.cpp server mode: `http://localhost:8080/v1`
 - vLLM server mode: `http://localhost:8000/v1`
+
+## Optional Live Provider Smoke
+
+`bun run provider:smoke` runs optional live checks only for providers with the
+required environment variables present. With no variables set it exits
+successfully and reports every provider as skipped, so CI does not need secrets.
+
+Configured providers run one short text request, a finite-timeout streaming
+request, and, when `PROVIDER_SMOKE_TOOL_CALLS=1`, a forced tool-call request.
+
+Required variables:
+
+| Provider | Required env vars | Optional env vars |
+| --- | --- | --- |
+| OpenAI-compatible | `OPENAI_COMPATIBLE_BASE_URL`, `OPENAI_COMPATIBLE_MODEL` | `OPENAI_COMPATIBLE_API_KEY` |
+| OpenRouter | `OPENROUTER_API_KEY`, `OPENROUTER_MODEL` |  |
+| Anthropic | `ANTHROPIC_API_KEY`, `ANTHROPIC_MODEL` | `ANTHROPIC_BASE_URL` |
+| Gemini | `GEMINI_API_KEY`, `GEMINI_MODEL` | `GEMINI_BASE_URL` |
+| Ollama | `OLLAMA_MODEL` | `OLLAMA_BASE_URL` or `OLLAMA_HOST` |
+| LM Studio | `LMSTUDIO_BASE_URL`, `LMSTUDIO_MODEL` | `LMSTUDIO_API_KEY` |
+| vLLM | `VLLM_BASE_URL`, `VLLM_MODEL` | `VLLM_API_KEY` |
+
+Common knobs:
+
+```sh
+PROVIDER_SMOKE_TIMEOUT_MS=30000
+PROVIDER_SMOKE_MAX_RETRIES=0
+PROVIDER_SMOKE_TOOL_CALLS=1
+```

package/documentation/index.html

@@ -44,7 +44,7 @@
     <main id="content" class="content">
       <header class="topbar">
         <div>
-          <p class="eyebrow">Version 1.37.0</p>
+          <p class="eyebrow">Version 1.37.4</p>
           <h1>UR-AGENT Documentation</h1>
           <p class="lead">A practical, tutorial-style reference for installing, configuring, automating, extending, and operating UR-AGENT.</p>
         </div>
@@ -58,12 +58,12 @@
         <div class="section-heading">
           <p class="eyebrow">What UR Is</p>
           <h2>Autonomous engineering workflow engine</h2>
-          <p>UR is not only chat, autocomplete, or code edits. It turns work into a plan, executes patches, tests and verifies them, documents the result, benchmarks behavior, and keeps the run reproducible from the terminal.</p>
+          <p>UR is not only chat, autocomplete, or code edits. It turns work into a plan, executes patches, tests and verifies them, documents the result, benchmarks behavior, and keeps the run reproducible.</p>
         </div>
         <div class="stat-grid">
           <article>
             <strong>Local-first runtime</strong>
-            <span>Use local Ollama/OpenAI-compatible runtimes for private and offline work, or explicitly select configured API provider paths. Subscription access stays visible but unavailable when no independent backend exists.</span>
+            <span>Use local Ollama/OpenAI-compatible runtimes for private and offline work, or explicitly select configured API provider paths. Subscription access stays visible but unavailable when not authenticated.</span>
           </article>
           <article>
             <strong>Interactive and headless</strong>
@@ -128,7 +128,7 @@ ur -p --output-format json "Review the current diff"</code></pre>
         </div>
         <div class="callout">
           <strong>Runtime requirement</strong>
-          <p>UR expects Bun. For local-first work, run a local Ollama app/server at <code>http://localhost:11434/api</code>. Set <code>OLLAMA_MODEL</code> or <code>UR_MODEL</code> to force a model, or use <code>ur provider</code> and <code>ur config set</code> to select official subscription, API, or OpenAI-compatible providers.</p>
+          <p>UR expects Bun. For local-first work, run a local Ollama app/server at <code>http://localhost:11434/api</code>. Set <code>OLLAMA_MODEL</code> or <code>UR_MODEL</code> to force a model route.</p>
         </div>
       </section>
 
@@ -136,7 +136,7 @@ ur -p --output-format json "Review the current diff"</code></pre>
         <div class="section-heading">
           <p class="eyebrow">Legal Access Paths</p>
           <h2>Providers and authentication</h2>
-          <p>UR-AGENT integrates official access paths only. It never scrapes browser sessions, extracts OAuth tokens, reads hidden provider auth files, bypasses provider restrictions, or proxies consumer web sessions as APIs.</p>
+          <p>UR-AGENT integrates official access paths only. It never scrapes browser sessions, extracts OAuth tokens, reads hidden provider auth files, bypasses provider restrictions, or proxies credentials.</p>
         </div>
         <div class="reference-grid">
           <article>
@@ -146,7 +146,7 @@ ur auth claude
 ur auth gemini
 ur auth antigravity
 ur provider doctor agy</code></pre>
-            <p>Codex CLI, Claude Code, Gemini CLI, and Antigravity are first-class providers that dispatch each turn through the vendor's official CLI using your subscription login. They are optional, never required, and never used as a silent fallback. The generic subscription entry is an internal placeholder hidden from listings and exposes no fake models.</p>
+            <p>Codex CLI, Claude Code, Gemini CLI, and Antigravity are first-class providers that dispatch each turn through the vendor's official CLI using your subscription login. They are optional and can be disabled.</p>
           </article>
           <article>
             <h3>API and local providers</h3>
@@ -155,12 +155,12 @@ ur config set provider openai-api
 ur config set base_url http://localhost:11434/v1
 ur config set model qwen3-coder:480b-cloud
 ur config set provider.fallback ollama</code></pre>
-            <p>API providers require explicit selection and read keys from a key stored via <code>ur connect</code> (OS keychain) or from environment variables. Local providers include Ollama, LM Studio, llama.cpp server mode, and vLLM OpenAI-compatible server mode. Subscription CLI providers (Codex CLI, Claude Code, Gemini CLI, Antigravity) dispatch through the official vendor CLIs.</p>
+            <p>API providers require explicit selection and read keys from a key stored via <code>ur connect</code> (OS keychain) or from environment variables. Local providers include Ollama, LM Studio, llama.cpp, and vLLM.</p>
           </article>
           <article>
             <h3>Status bar and updates</h3>
-            <pre><code>Ollama | llama3 | ask | main | update 1.37.0 available</code></pre>
-            <p>The interactive status bar shows only important runtime state: provider, model, mode, branch, active tasks, checks status when known, and update availability. It is hidden in CI, dumb terminals, and non-interactive mode.</p>
+            <pre><code>Ollama | llama3 | ask | main | update 1.37.3 available</code></pre>
+            <p>The interactive status bar shows only important runtime state: provider, model, mode, branch, active tasks, checks status when known, and update availability. It is hidden in CI, dumb terminals, and print mode.</p>
           </article>
         </div>
       </section>
@@ -169,7 +169,7 @@ ur config set provider.fallback ollama</code></pre>
         <div class="section-heading">
           <p class="eyebrow">Runtime</p>
           <h2>Architecture</h2>
-          <p>The CLI is the control plane. Project context and <code>.ur</code> assets feed agent orchestration, which uses approved provider adapters, local-first model runtimes, and approved tools to produce code, docs, PRs, reports, and automation outputs.</p>
+          <p>The CLI is the control plane. Project context and <code>.ur</code> assets feed agent orchestration, which uses approved provider adapters, local-first model runtimes, and approved tools to produce auditable results.</p>
         </div>
         <figure class="diagram">
           <img src="assets/ur-architecture.svg" alt="UR-AGENT runtime architecture diagram">

package/extensions/vscode-ur-inline-diffs/package.json

@@ -2,7 +2,7 @@
   "name": "ur-inline-diffs",
   "displayName": "UR Inline Diffs",
   "description": "Review, apply, and reject UR inline diff bundles from .ur/ide/diffs inside VS Code.",
-  "version": "1.37.2",
+  "version": "1.37.4",
   "publisher": "ur-agent",
   "engines": {
     "vscode": "^1.92.0"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ur-agent",
-  "version": "1.37.2",
+  "version": "1.37.4",
   "description": "UR-AGENT \u2014 autonomous engineering workflow engine (plan, execute, test, verify, document, benchmark, reproduce)",
   "type": "module",
   "packageManager": "bun@1.3.14",
@@ -49,11 +49,23 @@
     "bundle": "node scripts/bundle.mjs",
     "build": "node scripts/bundle.mjs",
     "release:check": "node scripts/release-check.mjs",
-    "typecheck": "bun run tsc --noEmit",
+    "release:create-source-zip": "bun scripts/source-zip-create.mjs",
+    "release:check-source-zip": "node scripts/source-zip-check.mjs",
+    "typecheck": "bun run tsc --noEmit && bun run typecheck:strict-core",
+    "typecheck:strict-core": "node scripts/strict-core-check.mjs",
     "lint": "node scripts/lint.mjs",
     "test": "bun test",
     "smoke": "node ./bin/ur.js --version",
     "secrets:scan": "bash scripts/secret-scan.sh",
+    "benchmark:report": "node scripts/benchmark-report.mjs",
+    "benchmark:smoke": "node scripts/benchmark-smoke.mjs",
+    "benchmark:local": "node scripts/benchmark-local.mjs",
+    "benchmark:compare": "node scripts/benchmark-compare.mjs",
+    "benchmark:swe-bench-lite": "node scripts/benchmark-external.mjs swe-bench-lite",
+    "benchmark:terminal-bench": "node scripts/benchmark-external.mjs terminal-bench",
+    "benchmark:aider-polyglot": "node scripts/benchmark-external.mjs aider-polyglot",
+    "safety:matrix": "bun scripts/generate-safety-matrix.mjs",
+    "provider:smoke": "bun scripts/provider-smoke.mjs",
     "package:check": "node scripts/package-check.mjs",
     "prepack": "bun run release:check"
   },