ur-agent 1.46.0 → 1.47.1

package/docs/CONFIGURATION.md

@@ -107,6 +107,28 @@ GEMINI_API_KEY=...
 OPENROUTER_API_KEY=...
 ```
 
+### OpenAI Responses transport
+
+OpenAI uses Chat Completions unless the Responses transport is selected
+explicitly:
+
+```sh
+ur config set openai_transport responses
+ur config set responses.store false
+ur config set responses.compact_threshold 20000
+ur config set responses.tool_search hosted
+```
+
+Supported safe settings are `chat-completions|responses`, boolean
+`responses.store`, an integer compaction threshold of at least 1,000 tokens,
+and `off|hosted` tool search. Responses defaults to `store=false`, no server
+compaction, and no deferred tool search. Background and WebSocket state is kept
+under `.ur/openai-responses/` with private atomic writes; identifiers, status,
+model, mode, and cursors are the only plaintext durable fields. To retain an
+opaque compacted window, set `UR_OPENAI_RESPONSES_STATE_KEY` to exactly 32
+bytes encoded as 64 hexadecimal characters or base64. Without that key UR
+refuses to persist compacted context.
+
 ### Reconfiguring the Ollama host
 
 The endpoint can be changed from UR in three ways, in order of precedence:
@@ -415,6 +437,9 @@ ur context-pack remember --decision "Use package scripts before ad hoc commands"
 ur context-pack remember --constraint "Do not expose secret values"
 ur context-pack remember --command "bun run typecheck"
 ur context-pack remember --diff "Safety policy wired into Bash permission checks"
+ur context-pack memory verify
+ur context-pack memory quarantine
+ur context-pack memory rollback --to <entry-id>
 ur context-pack compress
 ```
 
@@ -425,8 +450,10 @@ Generated files:
   `.ur/safety-policy.json`, MCP config, editor settings, workflow files, and
   other manifests.
 - `.ur/context/architecture.md` — human-readable architecture summary.
-- `.ur/context/task-memory.jsonl` — decisions, constraints, commands, diffs,
-  and notes.
+- `.ur/context/task-memory.jsonl` — private, append-only decisions,
+  constraints, commands, diffs, and notes with explicit provenance, UUIDs, and
+  a SHA-256 content/hash chain. Legacy entries are anchored when the chain
+  starts rather than silently rewritten.
 - `.ur/context/compressed.md` — compressed task context summary.
 
 Two related slash commands:
@@ -448,6 +475,7 @@ ur mcp get <name>
 ur mcp add-json <name> '<json>'
 ur mcp remove <name>
 ur mcp serve
+UR_MCP_HTTP_TOKEN='<secret>' ur mcp serve-http --port 8976
 ```
 
 MCP servers may execute code or access external services. Only enable servers you trust, and keep credentials out of committed config.
@@ -459,6 +487,15 @@ adjusted with `UR_MCP_MAX_CALLS_PER_MINUTE`,
 `UR_MCP_MAX_CONCURRENT_CALLS`, `UR_MCP_TOOL_TIMEOUT_MS`,
 `UR_MCP_MAX_INPUT_CHARS`, and `UR_MCP_MAX_OUTPUT_CHARS`.
 
+`serve-http` is a separate, opt-in MCP 2026-07-28 compatibility surface at
+`POST /mcp`. It is stateless at the transport layer and exposes capability-
+negotiated Tasks and a self-contained overview App backed by UR's real MCP
+tool registry. Every call must supply matching protocol/method/name metadata.
+Off-loopback binds require `UR_MCP_HTTP_TOKEN`; browser clients also require an
+exact `--allow-origin`. HTTP request, rate, concurrency, task-retention, and
+runtime limits use the `UR_MCP_HTTP_*` prefix. Durable task state is private,
+owner-isolated, bounded, atomic, and quarantined if corrupt.
+
 ## Background Agents
 
 Detached `ur bg` task state is stored under `.ur/background/`. Manifest updates
@@ -476,17 +513,27 @@ For native editor integration, `ur acp stdio` implements stable Agent Client
 Protocol v1 through the official SDK. Its resource controls use the
 `UR_ACP_STDIO_*` prefix. It supports client-provided MCP stdio/HTTP/SSE
 servers, additional workspace roots, native permission requests, cancellation,
-and persistent `session/resume`; see the [ACP Guide](ACP.md).
+and persistent list/load/delete/resume/close with exact history replay, modes,
+config options, and available commands; see the [ACP Guide](ACP.md).
 
 `ur acp serve` is a separate UR HTTP JSON-RPC API. Set `UR_ACP_TOKEN` instead
 of putting its bearer token in argv. Request, task, and tool limits use the
 `UR_ACP_*` prefix.
 
-`ur a2a serve` exposes the stable official-SDK A2A v0.3 JSON-RPC binding and a
-separate UR compatibility task API. Use `UR_A2A_TOKEN` for a static operator
-token or `UR_A2A_DELEGATION_SECRET` for issuer-minted scoped tokens. Limits use
-the `UR_A2A_*` prefix. See the [A2A Guide](A2A.md) for endpoints, proxy setup,
-scope isolation, and the A2A v1 migration status.
+`ur a2a serve` exposes strict v1 JSON-RPC and HTTP+JSON bindings alongside the
+stable official-SDK v0.3 JSON-RPC binding and a separate UR compatibility task
+API. Use `UR_A2A_TOKEN` for a static operator token or
+`UR_A2A_DELEGATION_SECRET` for issuer-minted skill/tenant-scoped tokens. Limits
+use the `UR_A2A_*` prefix. See the [A2A Guide](A2A.md) for endpoints, protocol
+negotiation, proxy setup, and isolation.
+
+`ur ag-ui serve` exposes an opt-in AG-UI HTTP/SSE adapter at `POST /ag-ui`,
+with capability discovery at `GET /ag-ui/capabilities`. It binds to loopback by
+default; off-loopback binds require `UR_AG_UI_TOKEN`, and browser clients must
+be listed with exact `--allow-origin` values. Request, rate, concurrency,
+runtime, and output controls use the `UR_AG_UI_*` prefix. Unsupported client
+tools, multimodal/encrypted input, interrupts, and unimplemented transports are
+rejected rather than silently ignored. See the [AG-UI Guide](AG_UI.md).
 
 ## Plugins and Skills
 
@@ -499,7 +546,43 @@ ur plugin update <plugin>
 ur plugin disable <plugin>
 ```
 
-Skills can be stored in `.ur/skills/` for project-specific workflows or in `~/.ur/skills/` for personal workflows.
+Skills can be stored in `.ur/skills/` for project-specific workflows or in
+`~/.ur/skills/` for personal workflows. UR also discovers the cross-client
+`.agents/skills/` and `~/.agents/skills/` locations from the Agent Skills
+integration guide. At an equal scope, native `.ur` skills win; project skills
+win over user skills, and nearer project roots win over parent roots.
+
+Portable `SKILL.md` directories are validated against the Agent Skills
+frontmatter contract and receive deterministic content and permission digests.
+Inspect and sign them with:
+
+```sh
+ur skill verify <name-or-directory> [--require-trusted] [--json]
+ur skill keygen <key-id> [--out <private-key.pem>]
+ur skill sign <name-or-directory> --key <private-key.pem> --key-id <key-id>
+```
+
+Set `UR_SKILLS_STRICT_SPEC=true` to reject spec-invalid file skills and
+`UR_SKILLS_REQUIRE_TRUSTED_SIGNATURE=true` to require a verified key at load
+and invocation. `UR_SKILL_TRUSTED_KEYS_FILE` can override the private trusted
+key store (normally under the UR config directory). Signed skills cannot
+contain symlinks and are re-hashed immediately before every invocation.
+
+## OpenTelemetry
+
+No telemetry exporter is enabled by default. Configure each signal with the
+standard `OTEL_TRACES_EXPORTER`, `OTEL_METRICS_EXPORTER`, and
+`OTEL_LOGS_EXPORTER` variables; supported values are `otlp`, `console`, or
+`none`. OTLP uses HTTP/protobuf and the standard
+`OTEL_EXPORTER_OTLP[_<SIGNAL>]_ENDPOINT` variables. UR validates endpoints,
+protocols, and export intervals before registering providers.
+
+GenAI spans and metrics cover inference, agent/workflow invocation, tools, memory,
+duration, token/cache usage, response identity, finish reason, time to first
+chunk, and bounded error type. Content is excluded unless
+`OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=true`; use
+`UR_OTEL_GENAI_PROVIDER` only when a gateway hides the provider identity.
+`OTEL_SDK_DISABLED=true` disables the SDK globally.
 
 ## Secrets
 

package/docs/USAGE.md

@@ -128,12 +128,23 @@ ur config set provider openai-compatible
 ur config set model <model>
 ur config set base_url <url>
 ur config set provider.fallback ollama
+ur config set openai_transport responses
+ur config set responses.store false
+ur config set responses.compact_threshold 20000
+ur config set responses.tool_search hosted
 ```
 
 `provider.fallback` only controls the recovery suggestion printed by provider
 diagnostics. UR does not switch or retry across providers automatically; use
 `ur config set provider <id>` after reviewing the failure.
 
+The OpenAI API continues to use Chat Completions by default. Selecting
+`openai_transport responses` opts into Responses semantic streaming,
+background/poll/cancel support, WebSocket continuation, server compaction, and
+deferred tool search. Remote storage is off by default. Local state contains
+only bounded identifiers/status/cursors unless a 32-byte
+`UR_OPENAI_RESPONSES_STATE_KEY` is supplied for AES-256-GCM compacted context.
+
 In the interactive app, `/model` chooses a provider first and then a model from
 that provider only. The saved pair controls the runtime backend for the next
 agent request. There is no cross-provider fallback: OpenAI API does not fall
@@ -210,9 +221,17 @@ ur context-pack remember --preference "Use bun test over jest"
 ur context-pack remember --accepted "Use p-map for bounded concurrency" --scope project
 ur context-pack remember --rejected "Switch to esbuild" --alternative-to "Keep bun bundle"
 ur context-pack remember --attempt "Tried Deno runtime" --status superseded
+ur context-pack memory verify
+ur context-pack memory quarantine
+ur context-pack memory rollback --to <entry-id>
 ur context-pack compress
 ```
 
+New entries carry explicit source provenance and form a SHA-256 hash chain.
+Reads fail closed on malformed or tampered state. `quarantine` preserves the
+complete original privately and restores the verified prefix; `rollback`
+preserves a backup before truncating to the requested entry.
+
 ## Lifecycle hooks
 
 UR supports lifecycle hook events that fire around agent actions. Hooks are configured in `.ur/hooks.json` or `UR.md` frontmatter and receive JSON payloads.
@@ -244,7 +263,10 @@ UR includes slash commands and CLI subcommands for common workflows:
 
 - `/help` or `ur --help` for command discovery
 - `ur connect ...` to connect provider accounts (subscription login or stored API key)
-- `ur mcp ...` to configure MCP servers
+- `ur mcp ...` to configure MCP servers, run the stdio server, or start the
+  opt-in stateless MCP 2026 Tasks/Apps adapter with `ur mcp serve-http`
+- `ur ag-ui serve` to expose the secure AG-UI HTTP/SSE adapter to an explicitly
+  allowed user-facing application
 - `ur plugin ...` to manage plugins and marketplaces. Marketplace plugins can
   add MCP tools, commands, executable skills, templates, validators, language
   adapters, LSP servers, agents, hooks, and output styles.
@@ -257,7 +279,8 @@ UR includes slash commands and CLI subcommands for common workflows:
 - `ur context-pack ...` to summarize architecture and persist project memory (decisions, constraints, commands, diffs, architecture, preferences, attempts, accepted, rejected)
 - `ur code-index watch` to keep the local semantic code index fresh
 - `ur code-index repo build` to build a richer semantic repo index (files, symbols, calls, tests, docs, configs)
-- `ur skill init ...` and `ur skill run ...` for executable skill workflows
+- `ur skill init|run ...` for executable skill workflows, plus
+  `ur skill verify|sign|keygen` for strict provenance and Ed25519 trust
 - `ur memory retention ...` to prune project-local memory by TTL, max entries, and decay
 - `ur spec ...` to scaffold requirements, design, and tasks, run a spec task list, and verify with strict proof gates
 - `ur escalate ...` to plan, run, or ask an oracle model for hard tasks
@@ -268,7 +291,9 @@ UR includes slash commands and CLI subcommands for common workflows:
   after one attempt and reports how to correct `--cwd`.
 - `ur artifacts ...` to capture reviewable diffs, test runs, notes, and feedback
 - `ur ide diff ...` to capture editor-readable inline diff bundles
-- `ur acp stdio` for the official-SDK Agent Client Protocol v1 editor transport, and `ur acp serve|stop|status` for the separate UR HTTP JSON-RPC API
+- `ur acp stdio` for the official-SDK ACP v1 editor transport with durable
+  list/load/delete/resume, modes, config options, and commands; and
+  `ur acp serve|stop|status` for the separate UR HTTP JSON-RPC API
 - `ur exec ...` to run prompts in non-interactive mode with optional concurrency
 - `ur eval run ...` to run a suite, grade results, and capture execution metrics
 - `ur eval report ...` to show a saved report or write a single-suite dashboard
@@ -292,7 +317,9 @@ UR includes slash commands and CLI subcommands for common workflows:
 - `ur trigger ...` to parse GitHub/Slack webhook payloads and optionally launch a headless run
 - `ur agent-templates ...`, `ur agent-task ...`, `ur agent-inspect`, `ur agent-features`, and `ur agent-trends` for agent template, PR handoff, timeline, and coverage utilities
 - `ur role-mode ...` to install built-in Architect, Code, Debug, and Ask role modes
-- `ur a2a ...` for Agent Card metadata, issuer-signed delegation tokens, the stable A2A v0.3 JSON-RPC binding, and UR compatibility task routes
+- `ur a2a ...` for negotiated v1 JSON-RPC/HTTP+JSON, the stable v0.3 SDK
+  binding, scoped delegation tokens, durable protocol state, and separate UR
+  compatibility task routes
 - `ur sdk ...` to scaffold TS/Python headless SDK examples
 - `ur doctor` to inspect CLI health
 - `ur update` or `ur upgrade` to check for updates
@@ -347,6 +374,7 @@ ur test-first detect
 ur test-first --dry-run
 ur skill init security-review
 ur skill run security-review "src/auth.ts"
+ur skill verify security-review --require-trusted
 ur code-index repo build
 ur code-index repo search "rate limiter"
 ur test-first install
@@ -355,7 +383,9 @@ ur safety check --command "rm -rf build"
 ur context-pack scan
 ur context-pack remember --constraint "Run command evidence before claiming success"
 ur context-pack remember --accepted "Use p-map for concurrency" --scope project
+ur context-pack memory verify
 ur context-pack compress
+UR_MCP_HTTP_TOKEN='<secret>' ur mcp serve-http --port 8976
 ur acp serve --port 8123
 ur exec "add tests for the parser" --concurrency 4 --json
 ur ci-loop --command "bun test" --cwd . --dry-run

package/docs/VALIDATION.md

@@ -19,7 +19,7 @@ You need:
 
 ```sh
 ur --version
-# expected for this release: "1.46.0 (UR-Nexus)"
+# expected for this release: "1.47.1 (UR-Nexus)"
 ```
 
 ## 0.1 First-workspace model selection (1.45.4)
@@ -84,6 +84,8 @@ Expected:
 - `context-pack scan` writes `.ur/project-manifest.json` and
   `.ur/context/architecture.md`.
 - `remember` appends task memory entries under `.ur/context/task-memory.jsonl`.
+- `ur context-pack memory verify` reports a valid integrity chain. Tamper tests
+  must use a disposable copy; quarantine and rollback preserve private backups.
 - `compress` writes `.ur/context/compressed.md`.
 
 ## 0.3 Test-first execution loop (1.18.0)
@@ -149,6 +151,34 @@ ur --ollama-host http://localhost:11434 -p "say hi"
 ur --settings '{"ollama":{"host":"http://localhost:11434"}}' -p "say hi"
 ```
 
+## 0.6 v1.47 protocol, provenance, and telemetry gates
+
+These deterministic tests use local fixtures, fake transports, and mock
+exporters. They do not require a paid provider account or make paid model calls:
+
+```sh
+bun test test/acpStdio.test.ts test/a2aV1.test.ts test/mcp2026.test.ts
+bun test test/openaiResponses.test.ts test/genAiTelemetry.test.ts
+bun test test/agUi.test.ts test/skillCommand.test.ts
+bun test test/skillProvenance.test.ts test/taskMemoryIntegrity.test.ts
+```
+
+Expected: ACP lifecycle/replay, A2A dual-stack isolation, MCP Tasks/Apps,
+Responses HTTP/SSE/WebSocket/background behavior, OpenTelemetry redaction,
+AG-UI lifecycle/security, `.agents/skills/` precedence, Ed25519 skill trust,
+and task-memory quarantine/rollback all pass. Then run:
+
+```sh
+bun run typecheck
+bun run lint
+bun test
+bun run build
+bun run secrets:scan
+bun run dependencies:audit
+bun run release:check
+bun run package:check
+```
+
 ## 1. Marketplace tree resolves
 
 In a fresh interactive session:

package/docs/providers.md

@@ -105,12 +105,22 @@ ur config set model <model>
 ur provider select-model <provider> <model> --json
 ur config set base_url <url>
 ur config set provider.fallback ollama
+ur config set openai_transport responses
+ur config set responses.store false
+ur config set responses.compact_threshold 20000
+ur config set responses.tool_search hosted
 ```
 
 The fallback setting is a recovery hint for `ur provider doctor`; it does not
 route a failed request to another provider. Review the failure and use
 `ur config set provider <id>` to switch explicitly.
 
+OpenAI API uses Chat Completions by default. `openai_transport responses` is an
+explicit opt-in to the native Responses adapter; it defaults to `store=false`
+and supports semantic streaming, background polling/cancellation, WebSocket
+continuation, server compaction, and deferred tool search. It does not change
+OpenAI-compatible, OpenRouter, local, or subscription-CLI providers.
+
 ## Provider-scoped model selection
 
 UR-Nexus shows providers first, then only models available for the selected provider. This prevents incompatible model/provider pairs and keeps API-key, local/server, subscription, and external app bridge model lists separate. The generic `subscription` entry has no models unless a real independent subscription runtime is configured; UR does not list fake subscription models.
@@ -120,7 +130,7 @@ UR-Nexus shows providers first, then only models available for the selected prov
 When you select a UR-native provider and model, every agent request is routed
 through that provider's backend:
 
-- **API providers** make direct HTTP calls in each provider's native wire format: Anthropic uses `x-api-key` + `anthropic-version` against `/v1/messages`; OpenAI uses `Authorization: Bearer` against `/v1/chat/completions`; Gemini uses `x-goog-api-key` against `…:generateContent`; OpenRouter uses its OpenAI-compatible chat endpoint.
+- **API providers** make direct HTTP calls in each provider's native wire format: Anthropic uses `x-api-key` + `anthropic-version` against `/v1/messages`; OpenAI uses `Authorization: Bearer` against `/v1/chat/completions` by default or `/v1/responses` when explicitly selected; Gemini uses `x-goog-api-key` against `…:generateContent`; OpenRouter uses its OpenAI-compatible chat endpoint.
 - **Local/server providers** connect to the configured local or OpenAI-compatible endpoint (`/v1/chat/completions` for LM Studio, llama.cpp and vLLM; the native tags/chat API for Ollama)
 - **Subscription CLI providers** (Codex CLI, Claude Code, Gemini CLI,
   Antigravity) dispatch the turn through the vendor's official CLI using your

package/documentation/app.js

@@ -49,9 +49,9 @@ const featureGroups = [
   },
   {
     title: 'Interoperability',
-    tags: ['MCP', 'plugins', 'A2A', 'SDK'],
-    text: 'MCP servers, plugin marketplaces for skills, templates, validators, language adapters, A2A Agent Card and task server, delegation tokens, and a TypeScript SDK wrapper around headless UR.',
-    commands: ['ur mcp', 'ur plugin', 'ur a2a', 'ur sdk'],
+    tags: ['MCP', 'plugins', 'A2A', 'AG-UI', 'SDK'],
+    text: 'MCP servers, plugin marketplaces, native and cross-client Agent Skills, ACP editor transport, A2A Agent Card/task bindings, a secure AG-UI frontend stream, delegation tokens, and a TypeScript SDK wrapper around headless UR.',
+    commands: ['ur mcp', 'ur plugin', 'ur acp', 'ur a2a', 'ur ag-ui', 'ur sdk'],
   },
   {
     title: 'Providers and auth',
@@ -86,16 +86,23 @@ const commands = [
     name: 'acp',
     category: 'Interop',
     aliases: [],
-    summary: 'Agent Communication Protocol server for IDE extensions: serve, stop, and status.',
-    examples: ['ur acp serve --port 8123', 'ur acp status --json', 'ur acp stop'],
+    summary: 'Run official-SDK ACP v1 over stdio, or manage the distinct UR HTTP JSON-RPC API used by bundled IDE integrations.',
+    examples: ['ur acp stdio', 'ur acp serve --port 8123', 'ur acp status --json'],
   },
   {
     name: 'a2a',
     category: 'Interop',
     aliases: [],
-    summary: 'A2A interoperability utilities: Agent Card, local task server, and delegation tokens.',
+    summary: 'Run negotiated strict A2A v1 JSON-RPC/HTTP+JSON beside the stable-SDK v0.3 binding, or inspect cards and delegation tokens.',
     examples: ['ur a2a card', 'ur a2a serve --dry-run', 'ur a2a token mint --secret "$UR_A2A_DELEGATION_SECRET" --scope coding,review'],
   },
+  {
+    name: 'ag-ui',
+    category: 'Interop',
+    aliases: [],
+    summary: 'Start the secure AG-UI HTTP/SSE adapter for user-facing applications with official events and truthful capability discovery.',
+    examples: ['ur ag-ui serve', 'ur ag-ui serve --allow-origin https://app.example', 'UR_AG_UI_TOKEN="$TOKEN" ur ag-ui serve --host 0.0.0.0'],
+  },
   {
     name: 'bg',
     category: 'Agent Platform',
@@ -718,6 +725,11 @@ const examples = [
     text: 'Expose Agent Card discovery and token-gated task execution.',
     code: 'ur a2a card\nur a2a serve --host 127.0.0.1 --port 8765 --dry-run',
   },
+  {
+    title: 'AG-UI frontend stream',
+    text: 'Expose the official-schema SSE adapter on loopback, or require a bearer token and exact browser origin for network use.',
+    code: 'ur ag-ui serve\nUR_AG_UI_TOKEN="$TOKEN" ur ag-ui serve --host 0.0.0.0 --allow-origin https://app.example',
+  },
   {
     title: 'Delegated A2A token',
     text: 'Mint an attenuated token scoped to selected skills.',

package/documentation/index.html

@@ -44,7 +44,7 @@
     <main id="content" class="content">
       <header class="topbar">
         <div>
-          <p class="eyebrow">Version 1.46.0</p>
+          <p class="eyebrow">Version 1.47.1</p>
           <h1>UR-Nexus Documentation</h1>
           <p class="lead">A practical, tutorial-style reference for installing, configuring, automating, extending, and operating UR-Nexus.</p>
         </div>
@@ -71,7 +71,7 @@
           </article>
           <article>
             <strong>Agent platform</strong>
-            <span>Workflows, patterns, crews, goals, evals, memory, knowledge, A2A, provenance, and templates are first-class commands.</span>
+            <span>Workflows, patterns, crews, goals, evals, memory, knowledge, ACP, A2A, AG-UI, provenance, and templates are first-class commands.</span>
           </article>
           <article>
             <strong>Plugin marketplace</strong>
@@ -158,12 +158,14 @@ ur provider doctor agy</code></pre>
 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, and vLLM.</p>
+ur config set provider.fallback ollama
+ur config set openai_transport responses
+ur config set responses.store false</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. OpenAI Responses is opt-in and privacy-first; Chat Completions remains the default. 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 1.46.0 available</code></pre>
+            <pre><code>Ollama | llama3 | ask | main | update 1.47.1 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>
           <article>
@@ -298,13 +300,14 @@ ur test-first install</code></pre>
 ur safety check --command "rm -rf build"
 ur context-pack scan
 ur context-pack remember --decision "Use manifest commands first"
+ur context-pack memory verify
 ur context-pack compress</code></pre>
           </article>
 
           <article>
             <h3>Start the ACP server and run a prompt pool</h3>
             <ol>
-              <li>Start the Agent Communication Protocol server for IDE extensions.</li>
+              <li>Start the Agent Client Protocol server for IDE extensions.</li>
               <li>Run one or more prompts in non-interactive mode with concurrency.</li>
               <li>Capture per-prompt outputs to a directory.</li>
             </ol>
@@ -314,6 +317,18 @@ ur exec "add tests for the parser" --concurrency 4 --json
 ur exec --file prompts.jsonl --output-dir ./outputs --dry-run</code></pre>
           </article>
 
+          <article>
+            <h3>Connect a user-facing app with AG-UI</h3>
+            <ol>
+              <li>Start the official-schema HTTP/SSE adapter on loopback.</li>
+              <li>Inspect its truthful capability document.</li>
+              <li>For browser or network use, require a bearer token and exact allowed origin.</li>
+            </ol>
+            <pre><code>ur ag-ui serve
+curl http://127.0.0.1:8977/ag-ui/capabilities
+UR_AG_UI_TOKEN="$TOKEN" ur ag-ui serve --host 0.0.0.0 --allow-origin https://app.example</code></pre>
+          </article>
+
           <article>
             <h3>Use a multi-agent pattern</h3>
             <ol>
@@ -477,8 +492,9 @@ ur safety check --command "rm -rf build"</code></pre>
             <h3>Project context</h3>
             <pre><code>ur context-pack scan
 ur context-pack remember --constraint "Run command evidence before success claims"
+ur context-pack memory verify
 ur context-pack compress</code></pre>
-            <p>Context packs summarize architecture from manifests and preserve task decisions, constraints, commands, and diffs under <code>.ur/context</code>.</p>
+            <p>Context packs summarize architecture and preserve provenance-rich, hash-chained task memory under <code>.ur/context</code>, with verification, quarantine, and rollback recovery.</p>
           </article>
           <article>
             <h3>Verifier</h3>
@@ -493,9 +509,12 @@ UR_VERIFIER_AUTO_SUBAGENT=1</code></pre>
             <h3>MCP and plugins</h3>
             <pre><code>ur mcp list
 ur mcp add-json local-tools '{"command":"node","args":["server.js"]}'
+ur mcp serve-http --port 8976
+ur skill verify &lt;name-or-directory&gt;
+ur ag-ui serve --help
 ur plugin list
 ur plugin install &lt;plugin&gt;</code></pre>
-            <p>MCP servers and marketplace plugins expand tools, executable skills, templates, validators, language adapters, and review workflows. Treat them as trusted code.</p>
+            <p>The opt-in stateless MCP HTTP adapter exposes negotiated Tasks and Apps. Portable skills load from native and cross-client roots with strict validation and Ed25519 provenance. AG-UI provides a bounded, opt-in frontend stream. Treat MCP servers and plugins as trusted code.</p>
           </article>
           <article>
             <h3>IDE inline diffs</h3>

package/examples/agent_features.md

@@ -56,6 +56,7 @@ ur safety check --command "rm -rf build"
 ur context-pack scan
 ur context-pack remember --decision "Use package scripts before ad hoc commands"
 ur context-pack remember --constraint "Never expose secret values"
+ur context-pack memory verify
 ur context-pack compress
 ```
 
@@ -90,3 +91,20 @@ Run the opt-in A2A server on loopback:
 ur a2a serve --dry-run
 curl http://127.0.0.1:8765/healthz
 ```
+
+Inspect signed skills and the stateless MCP adapter:
+
+```sh
+ur skill verify <name-or-directory>
+ur mcp serve-http --help
+```
+
+Inspect the provider-free AG-UI surface and cross-client skill discovery:
+
+```sh
+ur ag-ui serve --help
+ur skill verify <name-or-directory>
+```
+
+Portable skills may be placed in `.agents/skills/<name>/SKILL.md`; project
+skills override user skills, and native `.ur/skills/` wins at the same scope.

package/examples/agent_trends.md

@@ -3,11 +3,16 @@
 - Run `ur agent-trends` for a human-readable coverage report.
 - Run `ur agent-trends --json` when another tool needs structured coverage data.
 - Run `ur a2a card` to print UR's Agent Card metadata for A2A discovery.
+- Run `ur ag-ui serve --help` to inspect the user-facing HTTP/SSE adapter
+  without starting a model call.
 - Run `ur test-first --dry-run` to preview the detected compile/test/lint
   evidence loop for the current project.
 - Run `ur safety check --command "rm -rf build"` to preview command permission
   class, destructive approval, and sandbox posture.
 - Run `ur context-pack scan` and `ur context-pack compress` to preserve
   manifest-derived architecture context and task memory.
+- Run `ur context-pack memory verify`, `ur skill verify <name>`, and
+  `ur mcp serve-http --help`, and `ur ag-ui serve --help` to inspect the v1.47 integrity and protocol
+  surfaces without making a paid model call.
 - Use `/agent-trends` inside a session before planning upgrades to local
   runtime, MCP, A2A, memory, browser, eval, identity, or provenance workflows.

package/examples/mcp.md

@@ -5,3 +5,7 @@
   their tools into the registry and runs them through the same approval +
   evidence-ledger path as built-in tools (so MCP calls appear in `/evidence`).
 - Risky MCP tools require approval before they run.
+- `ur mcp serve` exposes the fail-closed stdio server. The separate
+  `UR_MCP_HTTP_TOKEN='<secret>' ur mcp serve-http` command starts the opt-in
+  stateless MCP 2026 HTTP surface with negotiated Tasks and a self-contained
+  App; off-loopback use requires bearer authentication.

package/examples/memory.md

@@ -9,7 +9,10 @@
   `.ur/context/architecture.md` from package scripts, instruction files,
   `.ur/verify.json`, and safety config.
 - `ur context-pack remember --decision|--constraint|--command|--diff|--note`
-  appends durable task memory to `.ur/context/task-memory.jsonl`; `compress`
-  writes `.ur/context/compressed.md`.
+  appends provenance-rich, hash-chained task memory to
+  `.ur/context/task-memory.jsonl`; `ur context-pack memory verify|quarantine`
+  checks or repairs a corrupt tail, `memory rollback --to <entry-id>` preserves
+  a private backup before truncation, and `compress` writes
+  `.ur/context/compressed.md`.
 - `/ur-init` scaffolds the `.ur/` asset folder (docs, superpowers, brainstorming,
   memory, prompts).

package/extensions/jetbrains-ur/build.gradle.kts

@@ -7,7 +7,7 @@ plugins {
 }
 
 group = "dev.urnexus"
-version = "1.46.0"
+version = "1.47.1"
 
 repositories {
     mavenCentral()

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": "1.46.0",
+  "version": "1.47.1",
   "publisher": "ur-nexus",
   "engines": {
     "vscode": "^1.92.0"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ur-agent",
-  "version": "1.46.0",
+  "version": "1.47.1",
   "description": "UR-Nexus — autonomous engineering workflow engine (plan, execute, test, verify, document, benchmark, reproduce)",
   "type": "module",
   "packageManager": "bun@1.3.14",
@@ -71,7 +71,9 @@
     "prepack": "bun run release:check"
   },
   "overrides": {
-    "fast-uri": "3.1.3",
+    "@hono/node-server": "2.0.11",
+    "body-parser": "2.3.0",
+    "fast-uri": "3.1.4",
     "form-data": "4.0.6",
     "hono": "4.12.30",
     "ip-address": "10.2.0",
@@ -79,6 +81,8 @@
   },
   "dependencies": {
     "@a2a-js/sdk": "0.3.14",
+    "@ag-ui/core": "0.0.57",
+    "@ag-ui/encoder": "0.0.57",
     "diff2html": "^3.4.56",
     "playwright-core": "^1.61.1",
     "sharp": "^0.35.3"
@@ -93,6 +97,9 @@
     "@opentelemetry/api": "1.9.1",
     "@opentelemetry/api-logs": "0.220.0",
     "@opentelemetry/core": "2.9.0",
+    "@opentelemetry/exporter-logs-otlp-http": "0.220.0",
+    "@opentelemetry/exporter-metrics-otlp-http": "0.220.0",
+    "@opentelemetry/exporter-trace-otlp-http": "0.220.0",
     "@opentelemetry/resources": "2.9.0",
     "@opentelemetry/sdk-logs": "0.220.0",
     "@opentelemetry/sdk-metrics": "2.9.0",

package/plugins/core/engineering-discipline/skills/reproducible-release/SKILL.md

@@ -1,5 +1,6 @@
 ---
-name: Reproducible Release
+name: reproducible-release
+display-name: Reproducible Release
 description: Use when preparing a UR-style engineering change for release. Enforces spec -> plan -> patch -> test -> verify -> document -> benchmark -> reproduce, with explicit command evidence and rollback notes.
 version: 0.1.0
 ---

package/plugins/core/github/skills/github-workflow/SKILL.md

@@ -1,5 +1,6 @@
 ---
-name: GitHub Workflow
+name: github-workflow
+display-name: GitHub Workflow
 description: Reference for operating GitHub safely from an agent — the official MCP server toolsets, gh CLI cheatsheet, token scopes, pull-request etiquette, and guardrails. Use when reviewing or creating PRs, triaging issues, or inspecting CI on GitHub.
 version: 0.1.0
 ---

package/plugins/core/gitlab/skills/gitlab-workflow/SKILL.md

@@ -1,5 +1,6 @@
 ---
-name: GitLab Workflow
+name: gitlab-workflow
+display-name: GitLab Workflow
 description: Reference for operating GitLab from an agent — the official MCP server transport and prerequisites, glab CLI cheatsheet, token scopes, merge-request etiquette, pipeline triage, and guardrails. Use when reviewing or creating MRs, triaging issues, or inspecting CI/CD on GitLab.
 version: 0.1.0
 ---