ur-agent 1.65.9 → 1.65.11

package/docs/VALIDATION.md

@@ -19,7 +19,7 @@ You need:
 
 ```sh
 ur --version
-# expected for this release: "1.65.9 (UR-Nexus)"
+# expected for this release: "1.65.11 (UR-Nexus)"
 ```
 
 ## 0.1 First-workspace model selection (1.45.4)

package/documentation/index.html

@@ -45,7 +45,7 @@
     <main id="content" class="content">
       <header class="topbar">
         <div>
-          <p class="eyebrow">Version 1.65.9</p>
+          <p class="eyebrow">Version 1.65.11</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>

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

@@ -7,7 +7,7 @@ plugins {
 }
 
 group = "dev.urnexus"
-version = "1.65.9"
+version = "1.65.11"
 
 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": "1.65.9",
+  "version": "1.65.11",
   "publisher": "ur-nexus",
   "engines": {
     "vscode": "^1.92.0"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ur-agent",
-  "version": "1.65.9",
+  "version": "1.65.11",
   "description": "UR-Nexus — autonomous engineering workflow engine (plan, execute, test, verify, document, benchmark, reproduce)",
   "type": "module",
   "packageManager": "bun@1.3.14",

package/technical/04-tools.md

@@ -61,6 +61,54 @@ only after `EnterPlanMode` (or `/plan`) has successfully made the active mode
 `plan`. Plan approval may change that mode before permission-edited input is
 revalidated; the executor labels that second validation as post-permission so
 the already-validated exit can finish, while new out-of-mode calls still fail.
+`ExitPlanMode` is exempt from the implementation task-list gate because it is
+the approval/control transition that precedes implementation. Its own plan-mode
+validation remains authoritative, so the exemption does not make a stale
+second exit valid.
+
+For non-trivial work, the task list uses one record per cohesive outcome with
+an observable done check rather than one omnibus record. Genuine single-outcome
+work remains one task; files, commands, and tiny mechanical steps are not
+artificial task boundaries. Dependency edges represent only real ordering
+constraints. Mutually independent tasks with no conflicting shared mutations
+can be delegated together, while dependent or conflicting work stays
+sequential.
+
+Task IDs remain strings in storage and tool output. Model inputs for
+`TaskCreate` dependencies and `TaskGet`/`TaskUpdate` identifiers may also use a
+positive safe-integer JSON number; the tool boundary normalizes it to the
+canonical decimal string. Zero, negative, fractional, non-finite, Boolean, and
+precision-losing numeric IDs are rejected.
+
+Task-gate recovery names the tracking surface that is actually present:
+interactive Task V2 sessions use `TaskCreate`, while default headless sessions
+use `TodoWrite`. It never instructs a model to recover by calling a tool absent
+from that runtime. Runtime inspection tracks actionable and total user tasks
+separately: an all-terminal list is reported truthfully and the model is told
+to reopen or create the cohesive remaining task. Real Edit/Bash mutations stay
+gated. One simple `open <loopback-http(s)-URL>` Bash preview is exempt only
+from the task-list gate; remote/file URLs, flags, shell composition, expansion,
+redirection, backgrounding, sandbox overrides, and permission-time rewrites to
+mutating commands fail closed. The preview command remains a Bash side effect
+and still follows normal permission, sandbox, and plan-worker rules.
+
+`AskUserQuestion` exposes a request-only model schema: one top-level
+`questions` array with 1–4 complete question objects, each containing
+`question`, a header of at most 12 characters, and 2–8 labeled choices.
+Descriptions are optional and are never fabricated from labels. The runtime
+accepts only lossless compatibility forms such as string choices and recognized
+question-text aliases; it does not turn arbitrary prose or flat option rows into
+invented questions. More than four blocking decisions are asked in later
+rounds.
+
+Answers and annotations are not model input fields. They are accepted only
+during post-permission validation after the interactive UI has returned one
+non-empty answer for every question; an unchanged generic approval cannot
+produce a successful “user answered” result. The UI uses prototype-safe records,
+provides a real custom `Other` path for both ordinary and preview questions,
+and does not count selecting `Other` itself as an answer. HTML-configured
+previews are escaped into an inert preformatted-text wrapper rather than
+executed as model-provided markup.
 
 ## Multi-agent tools
 
@@ -124,3 +172,18 @@ File Edit/Write/NotebookEdit require the exact content snapshot the model read,
 not only a modification timestamp. Full and ranged reads are compared at the
 final write boundary, preventing same-timestamp external replacements from
 being overwritten.
+
+`Write` requires `file_path` and the complete literal `content` in the same
+structured call. Prose outside the call is never treated as file content, and a
+missing-content failure states that no file was written instead of fabricating
+the intended file.
+
+`Edit` remains fail-closed rather than applying a fuzzy replacement to similar
+code. When an exact contiguous `old_string` is absent, its bounded error points
+to a verified matching line when one exists and tells the model to re-read that
+region, use a smaller current 2–4-line anchor, split distant HTML/CSS/JavaScript
+sections, and never retry the unchanged call. One narrow idempotent case returns
+success without writing: a non-`replace_all` deletion-only edit whose
+`new_string` is already present uniquely and whose larger `old_string` is
+absent. General stale, fuzzy, empty-replacement, and ambiguous matches still
+fail.

package/technical/09-multi-agent.md

@@ -15,7 +15,31 @@ The main agent can spawn subagents. Built-in agent types
 | `verification` | verifies a change actually works (used by `/verify`) |
 | `statusline-setup` | configures the status line |
 | `ur-code-guide` | answers UR/SDK/API questions |
-| `Explore`, `Plan` | read-only search and planning agents, available only in builds compiled with `BUILTIN_EXPLORE_PLAN_AGENTS` and when their runtime gate is enabled; the standard npm bundle does not compile that feature |
+| `Explore`, `Plan` | built-in read-only search and planning agents; registered in the standard npm bundle so plan-mode instructions never advertise missing worker types |
+
+Ordinary `Agent` subagents do not require experimental Teams/swarm mode.
+Approved-plan handoff checks the actual tool pool, agent-type allowlist, live
+`Agent(type)` deny rules, and active built-in definitions. It can fan out
+independent ready tasks only when a selectable implementation worker remains.
+The Teams gate applies only to named teammates, team files/mailboxes, and
+`TeamCreate`/`TeamDelete`.
+
+While the parent is in plan mode, only the exact active built-in `Explore` and
+`Plan` definitions may pass the task-list gate as read-only delegations.
+Plan prompts apply the same type allowlist and live deny rules as the eventual
+`Agent` call, so they do not advertise a planning worker that policy will
+reject.
+Custom agents reusing those names, generic agents, teammates, background
+launches, custom working directories, and worktree launches remain mutating and
+task-gated. `TeamCreate` and `TeamDelete` also reject plan mode explicitly;
+team lifecycle state starts only after the plan is approved.
+
+In the standard bundle, `Explore` and `Plan` receive only `Glob`, `Grep`, and
+`Read`, use `dontAsk` permission mode, and have a second runtime boundary that
+rejects any operation classified as mutating even if an actionable task or
+inherited allow rule exists. Ant-native embedded-search builds substitute
+read-only Bash `find`/`grep` access for the dedicated search tools; the same
+runtime mutation boundary remains in force.
 
 Custom agents:
 - `/agents` — interactive management UI.
@@ -30,7 +54,7 @@ Custom agents:
   `/role-mode install architect|code|debug|ask` installs the four classic role modes as
   scoped agents.
 
-When present, read-only `Explore`/`Plan` agents omit the UR.md hierarchy only
+Read-only `Explore`/`Plan` agents omit the UR.md hierarchy only
 when the default-on `tengu_slim_subagent_agentmd` gate remains enabled and the
 caller did not explicitly provide user context (token saving; see
 `loadAgentsDir.ts`).
@@ -105,6 +129,21 @@ Interactive sessions use the canonical Task V2 tools. Print/headless sessions
 use legacy `TodoWrite` by default, or Task V2 when
 `UR_CODE_ENABLE_TASKS=1`. Both feed the same mutation gate:
 
+- Approved non-trivial plans are translated into a complete task graph before
+  workspace changes: one task record per cohesive outcome with its own
+  observable completion check. Separate deliverables are not hidden in one
+  umbrella item, while files, tool calls, and tiny mechanical steps are not
+  artificial task boundaries.
+- Independent Task V2 records are created together (up to the eight-call
+  prompt batch limit), then real dependency edges are added once task IDs are
+  known. Default headless sessions instead write the complete outcome list
+  through `TodoWrite`; approval handoff detects this capability rather than
+  naming unavailable Task V2 tools. When an actual built-in implementation
+  worker is active, ready tasks without conflicting shared mutations launch in
+  waves of up to eight with bounded scope, acceptance checks, and dependency
+  inputs. Dependent or conflicting writes stay sequential, and the lead
+  verifies worker evidence before completion. An exposed `Agent` tool with no
+  selectable implementation worker is not advertised as delegation support.
 - Task IDs are ordered numerically (`1, 2, 10`), with non-numeric external IDs
   sorted stably after numeric IDs.
 - Dependencies block transition or claim until prerequisites are complete.
@@ -113,6 +152,9 @@ use legacy `TodoWrite` by default, or Task V2 when
 - Reads remain unrestricted. Ordinary mutations have a default allowance of
   three preceding tool calls, counted by tool call rather than message.
   Delegation and child mutations always require an actionable parent task.
+  The sole delegation exception is a foreground built-in `Explore` or `Plan`
+  call during live plan mode; those agents omit workspace-editing and nested
+  delegation tools and remain subject to their child permission checks.
 - An unreadable task store fails closed. Task create/update/list/get tools stay
   exempt so the agent can repair the plan.
 - Creating or updating the exact current-session plan-mode Markdown file is
@@ -124,10 +166,12 @@ use legacy `TodoWrite` by default, or Task V2 when
 - Configure the behavior at
   `tasks.requireBeforeChanges.{enabled,freeReads}`.
 
-The prompt contract tells the model to update each task after observing its
-tool result. Runtime dependencies and mutation gating enforce ordering and
+The prompt contract, plan-file structure, plan-agent output, approval handoff,
+task-tool result, and gate recovery text all reinforce the same decomposition
+and worker rules. Runtime dependencies and mutation gating enforce ordering and
 plan presence; they cannot prove that an arbitrary natural-language task is
-semantically complete. Workflows and crews add stricter verdict rules where a
+semantically complete, so the gate deliberately does not require a fake
+minimum task count. Workflows and crews add stricter verdict rules where a
 machine-checkable execution boundary exists.
 
 ## Task routing
@@ -222,6 +266,9 @@ to false.
   `TeamDelete`, `SendMessage`, `InProcessTeammateTask`, and the
   `TeammateIdle` hook. `--agent-teams` is registered only in ant builds, so it
   is not a supported external CLI flag.
+- Team creation and deletion are unavailable while plan mode is active. Use the
+  standard read-only `Explore`/`Plan` subagents for parallel planning, then
+  create an implementation team after approval.
 - Coordinator mode (`UR_CODE_COORDINATOR_MODE=1`) is additionally behind the
   compile-time `COORDINATOR_MODE` feature. The standard npm bundle does not
   include it; setting the environment variable there has no effect.

package/technical/12-security-sandbox-stability.md

@@ -38,6 +38,23 @@ feature. Its AI-classified `auto` mode is therefore source-only. The accepted
 `permissions.classifierPermissionsEnabled` schema field is not read by a
 shipped enforcement path and must not be treated as an active control.
 
+Tools that require user interaction are semantically validated again after the
+permission decision even when their input signature did not change. This keeps
+an unchanged generic approval or hook allow-result from being mistaken for the
+interaction result.
+For `AskUserQuestion`, model requests cannot supply `answers` or `annotations`;
+post-permission execution requires an exact, complete, non-empty answer map.
+Question-keyed UI state uses null-prototype records and own-property checks, so
+model-controlled names such as `constructor` or `__proto__` cannot become
+inherited answers or mutate the record prototype. The tool rejects those
+reserved question names at its outer schema as an additional boundary.
+
+Model-provided Ask previews are never trusted as executable HTML. When an SDK
+selects the HTML preview format, the runtime escapes raw input into one inert
+`<pre data-ur-preview="text">…</pre>` wrapper and validates that wrapper before
+interaction. Scripts, event handlers, URL attributes, style injection, and
+closing-tag escapes remain text rather than active markup.
+
 Bash adds command parsing, command-injection checks, dangerous-pattern
 classification, project safety policy, path validation, and sandbox-aware
 permission decisions. `UR_CODE_DISABLE_COMMAND_INJECTION_CHECK` weakens one of

package/technical/README.md

@@ -1,6 +1,6 @@
 # UR-Nexus — Technical Specifications
 
-> Audited against the executable source and tests for `ur-agent` v1.65.9.
+> Audited against the executable source and tests for `ur-agent` v1.65.11.
 > Command, tool, flag, provider, and setting claims are checked against the
 > implementation rather than copied from product prose. Release validation
 > keeps this version synchronized and packages the complete `technical/`