ur-agent 1.22.1 → 1.22.3

package/CHANGELOG.md

@@ -1,5 +1,61 @@
 # Changelog
 
+## 1.22.3
+
+### Added
+- **Executable skill directories.** A `.ur/skills/<name>/` directory containing
+  `skill.yaml` is now an executable skill that compiles into a `WorkflowSpec`.
+  Supports `instructions.md`, `scripts/`, `templates/`, and `checklists/`.
+  `src/skills/skillSpec.ts` parses, validates, and compiles skills; step prompts
+  support `$ARGUMENTS`, `$0..$N`, and `$ARGUMENTS[N]` substitution.
+- **`ur skill` CLI.** New command surface: `ur skill list`, `ur skill show <name>`,
+  `ur skill run <name> [args]`, and `ur skill init <name>`. Registered in
+  `src/commands.ts` and `src/main.tsx`.
+- **Semantic repo index.** `src/utils/codeIndex/repoIndex.ts` builds offline,
+  dependency-free indexes under `.ur/code-index/`: `repo.json` (file
+  classification + imports/importedBy), `symbols.json`, `calls.json`,
+  `tests.json`, `docs.json`, and `configs.json`. `ur code-index repo` exposes
+  `build|status|search|symbols|callers|tests|docs|configs` subcommands.
+- **`--repo` flag for code-index build/watch.** `ur code-index build --repo`
+  builds both the embedding index and the repo index; `watch --repo` refreshes
+  the repo index on file changes.
+
+### Changed
+- Reused the existing workflow engine for executable skills and extended the
+  existing `ur code-index` surface for the repo index, keeping changes additive.
+
+### Verified
+- Added `test/skillSpec.test.ts`, `test/skillCommand.test.ts`, and
+  `test/repoIndex.test.ts` covering skill parsing, compilation, CLI scaffolding,
+  repo file classification, symbol/call/test/doc/config extraction, and index
+  round-trips.
+
+## 1.22.2
+
+### Added
+- **Lifecycle hooks.** Added six new hook events in `src/entrypoints/sdk/coreTypes.ts`
+  and `src/entrypoints/sdk/coreSchemas.ts`: `BeforeEdit`, `AfterEdit`,
+  `BeforeCommand`, `AfterCommand`, `BeforeCommit`, and `OnFailure`. Dispatchers
+  in `src/utils/hooks.ts` run them around file edits, shell commands, git commits,
+  and failure paths. Call sites are wired in `FileEditTool`, `BashTool`,
+  `PowerShellTool`, `toolExecution.ts`, and `query.ts`. Hooks are advisory by
+  default and can block actions or append project memory.
+- **Persistent project memory.** Extended `TaskMemoryKind` in
+  `src/services/context/projectContextManifest.ts` with `architecture`,
+  `preference`, `attempt`, `accepted`, and `rejected`. Entries now support
+  `status`, `rationale`, `alternativeTo`, `supersedesId`, `scope`, and `source`
+  metadata. `ur context-pack remember` accepts the new kinds and metadata flags.
+
+### Changed
+- **Compressed context** now includes sections for all memory kinds, including the
+  new project-memory categories.
+
+### Verified
+- Added `test/lifecycleHooks.test.ts` covering the new `HOOK_EVENTS` literals and
+  Zod schema validation.
+- Added `test/projectMemory.test.ts` covering append/read/compress/summarize for
+  the new memory categories and metadata.
+
 ## 1.22.1
 
 ### Added

package/QUALITY.md

@@ -10,6 +10,7 @@ Run these commands before tagging or pushing a release:
 
 ```sh
 bun run typecheck
+bun run lint
 bun test
 bun run bundle
 bun run smoke

package/README.md

@@ -10,9 +10,10 @@
   <a href="./QUALITY.md"><img alt="quality gate" src="https://img.shields.io/badge/quality-release%20gated-brightgreen.svg"></a>
 </p>
 
-UR Agent is a Bun and TypeScript command-line coding agent. It opens a stateful
-interactive terminal session by default, can run one-shot prompts for scripts,
-and includes workflow commands for specification-driven development,
+UR Agent is a Bun and TypeScript command-line coding agent: a reproducible
+autonomous software engineering agent. It opens a stateful interactive terminal
+session by default, can run one-shot prompts for scripts, and includes workflow
+commands for specification-driven development,
 multi-agent execution, test-first quality loops, CI repair loops, background
 agents, MCP servers, plugins, skills, memory, permission safety policy,
 project context packing, verification, and local model routing.
@@ -27,6 +28,9 @@ UR is built around the work that happens after a prompt: reading a repository,
 editing files, running commands, validating the result, preserving context, and
 handing work off to other tools or agents when needed.
 
+- **Reproducible engineering loop.** Substantial tasks should move through
+  `spec -> plan -> patch -> test -> report -> rollback`, with command evidence
+  captured before success is claimed.
 - **Terminal-native agent loop.** Run `ur` for an interactive coding session or
   `ur -p` for automation-friendly output.
 - **Local model runtime.** Use any model exposed by Ollama, set a specific host
@@ -38,7 +42,13 @@ handing work off to other tools or agents when needed.
   AST-aware rename plans, patch previews, and rollback-safe multi-file apply.
 - **Permission and context control.** Use `ur safety` and `ur context-pack` to
   inspect command risk, initialize project safety policy, summarize repository
-  architecture, and preserve task decisions, constraints, commands, and diffs.
+  architecture, and preserve task decisions, constraints, commands, diffs,
+  architecture decisions, preferred commands, failed attempts, accepted patterns,
+  and rejected approaches.
+- **Lifecycle hooks.** Configure `BeforeEdit`, `AfterEdit`, `BeforeCommand`,
+  `AfterCommand`, `BeforeCommit`, and `OnFailure` hooks in `.ur/hooks.json` or
+  `UR.md` to run custom commands when the agent edits files, runs shell commands,
+  commits, or hits a failure.
 - **Verification and provenance.** Use `ur test-first`, the built-in verifier,
   `/verify`, `.ur/verify.json`, `ur artifacts`, `ur claim-ledger`, and `/trace`
   to make results easier to inspect.
@@ -124,13 +134,14 @@ as first-class subcommands in the shipped CLI.
 | --- | --- |
 | `ur` | Start an interactive terminal agent session in the current workspace. |
 | `ur -p` | Run a non-interactive prompt with text, JSON, or stream-JSON output. |
-| `ur spec` | Create requirements, design, and task documents under `.ur/specs/`, run the task list, and verify with strict proof gates. |
+| `ur spec` | Default spec-first workflow: create requirements, design, and task documents under `.ur/specs/`, run the task list, and verify with strict proof gates. |
 | `ur escalate` | Plan or run work with fast and oracle model tiers selected from local model capabilities. |
 | `ur arena` | Run multiple agents on the same task in isolated worktrees and surface the winning diff. |
 | `ur ci-loop` | Run a build or test command, hand failures to a fix agent, and retry with a bounded budget. |
 | `ur test-first` | Detect the project stack, run compile/test/lint commands, store failure traces, and install edit-time verify gates. |
 | `ur safety` | Inspect or initialize project shell safety policy and evaluate command risk before execution. |
-| `ur context-pack` | Write project architecture context, task memory, and compressed context under `.ur/`. |
+| `ur context-pack` | Write project architecture context, task memory, and compressed context under `.ur/`. Supports memory kinds `decision`, `constraint`, `command`, `diff`, `note`, `architecture`, `preference`, `attempt`, `accepted`, and `rejected`. |
+| `ur hooks` | Configure lifecycle hooks (`BeforeEdit`, `AfterEdit`, `BeforeCommand`, `AfterCommand`, `BeforeCommit`, `OnFailure`) via settings files. |
 | `ur bg` | Run and manage detached local background agents with optional worktrees and PR creation. |
 | `ur worktree` | List, inspect, and clean up UR agent worktrees. |
 | `ur automation` | Store and run project-local scheduled automation specs under `.ur/automations/`. |
@@ -139,7 +150,7 @@ as first-class subcommands in the shipped CLI.
 | `ur pattern` | Run multi-agent collaboration patterns (PEER, DOE, concurrent, handoff, debate, parallel); `--execute` runs them as a workflow. |
 | `ur goal` | Track long-horizon objectives that persist across sessions. |
 | `ur repo-edit` | Build a repo edit index, plan AST-aware renames, preview patches, and apply with rollback. |
-| `ur code-index` | Build, query, or watch a local semantic code index using Ollama embeddings. |
+| `ur code-index` | Build, query, or watch a local semantic code index using Ollama embeddings; `ur code-index repo` adds files/symbols/calls/tests/docs/configs. |
 | `ur semantic-memory` | Build and search a project-local memory index. |
 | `ur knowledge` | Manage a curated project knowledge base with provenance. |
 | `ur artifacts` | Capture diffs, test runs, notes, and review feedback under `.ur/artifacts/`. |
@@ -167,6 +178,14 @@ Install matching agent templates with `ur agent-templates install`.
 
 New built-in tools (exposed through MCP and the ACP server): GitHub, API, Browser, Docker, TestRunner, Database. File-system and terminal tools are already built in (FileRead, FileEdit, FileWrite, Glob, Grep, Bash, PowerShell).
 
+UR also documents the core Cursor-style agent primitives as first-class,
+project-backed features: Agent surfaces (`ur`, `ur agents`, `ur crew`, `ur bg`),
+Rules (`AGENTS.md`, `UR.md`, `.cursor/rules/*.mdc`, `.cursorrules`, safety and
+guardrail config), MCP (`ur mcp`, `.mcp.json`, plugin MCP servers), Skills
+(`/skills`, bundled, project, user, and plugin skills), CLI (`ur --help`, `ur -p`,
+`ur exec`, `ur acp`), and Models (`ur model`, `ur model-doctor`, Ollama routing
+and discovery).
+
 Examples:
 
 ```sh
@@ -186,6 +205,11 @@ ur test-first install
 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 --architecture "Repository pattern for data access" --status accepted --rationale "Testability"
+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 compress
 ur ci-loop --command "bun test" --max-attempts 3 --dry-run
 ur bg run "fix the flaky parser test" --worktree --dry-run
@@ -193,6 +217,10 @@ ur automation create nightly --schedule "0 9 * * 1-5" --prompt "Review open task
 ur repo-edit preview rename oldName --to newName
 ur repo-edit apply rename oldName --to newName --check "bun test"
 ur code-index search "where is the rate limiter configured"
+ur code-index repo build
+ur code-index repo search "rate limiter"
+ur skill init security-review
+ur skill run security-review "src/auth.ts"
 ur artifacts capture-tests --command "bun test"
 ur agent-task pr --create --dry-run
 ur acp serve --port 8123
@@ -214,7 +242,9 @@ UR reads repository instructions and local runtime state from project files:
 - `.ur/safety-policy.json` configures project shell safety rules for read,
   write, execute, and network command classes.
 - `.ur/project-manifest.json` and `.ur/context/` hold architecture summaries,
-  task memory, compressed context, and command/constraint decisions.
+  task memory, compressed context, and project memory including architecture
+  decisions, preferred commands, failed attempts, accepted patterns, and rejected
+  approaches.
 - `.ur/specs/`, `.ur/artifacts/`, `.ur/automations/`, `.ur/test-first/`,
   `.ur/memory/`, and `.ur/index/` hold workflow state, review artifacts,
   scheduled jobs, failure traces, memory, and indexes.
@@ -292,6 +322,7 @@ Build and verify a release:
 
 ```sh
 bun run typecheck
+bun run lint
 bun test
 bun run bundle
 bun run smoke