ur-agent 1.13.7 → 1.13.9

package/CHANGELOG.md

@@ -1,5 +1,55 @@
 # Changelog
 
+## 1.13.9
+
+### Added
+- **Spec-driven development (`ur spec`).** Scaffolds `requirements.md ->
+  design.md -> tasks.md` plus a phase/approval `spec.json` under `.ur/specs/`,
+  then drives execution task-by-task through a headless agent, checking off each
+  task on a PASS verdict. Tasks use the GitHub Spec Kit / Kiro `- [ ] T1: ...`
+  checkbox format, so lists are drop-in portable. `generate` can model-fill a
+  phase; scaffolding and task parsing stay pure and offline.
+- **In-loop model escalation / local Oracle (`ur escalate`).** Picks a fast tier
+  and a strong "oracle" tier from `ur model-doctor`, starts routine work on the
+  fast model, and auto-escalates hard reasoning/debug/review (or a failed cheap
+  attempt) to the oracle. `escalate oracle` gets a one-shot second opinion;
+  `escalate policy` pins tiers. Tier selection and difficulty scoring are
+  deterministic and testable.
+- **Multi-agent best-of-N judging (`ur arena`).** Runs N agents on the same task
+  in isolated git worktrees, judges the resulting diffs with the deterministic
+  self-review gate plus verdict/diff-shape heuristics, surfaces the winner, and
+  can `--apply` it. Local-first take on parallel-agent judging.
+- **Self-healing CI loop (`ur ci-loop`).** Runs a build/test command and, on
+  failure, summarizes the error, hands it to a fix agent, and re-runs with a
+  bounded retry budget; `--commit`/`--push` are gated by the self-review check so
+  a fix can never push secrets. `--from-log` seeds the first failure from a log.
+- **Verifiable artifacts surface (`ur artifacts`).** Records reviewable
+  deliverables (plans, diffs, test runs, screenshots) under `.ur/artifacts/`
+  with pending/approved/rejected status and threaded feedback; `capture-diff`
+  and `capture-tests` snapshot the working tree and test output for audit.
+
+### Verified
+- Added focused unit suites for escalation, arena judging, the spec workflow,
+  the CI loop, and artifacts (26 tests); rebuilt `dist/cli.js` and verified
+  typecheck, the full test suite, release check, package check, secret scan,
+  version output, npm publish dry-run, and direct CLI smoke tests for
+  `ur spec`, `ur arena`, and `ur escalate`.
+
+## 1.13.8
+
+### Fixed
+- **Image paste resize fallback.** Clipboard image paste now falls back to
+  macOS `sips` when the normal Sharp/native resize path cannot process an
+  oversized pasted image.
+- **Under-limit image passthrough.** Images whose base64 payload is already
+  within the API limit now pass through even if local dimension downsampling
+  fails, avoiding unnecessary `Unable to resize image` paste failures.
+
+### Verified
+- Rebuilt `dist/cli.js` at 1.13.8 and verified focused image resize tests,
+  typecheck, full test suite, release check, package check, secret scan, and
+  npm publish dry-run.
+
 ## 1.13.7
 
 ### Added

package/README.md

@@ -99,6 +99,17 @@ ur mcp --help
 ur plugin --help
 ```
 
+Agent platform examples:
+
+```sh
+ur spec init demo --goal "1. add a utils.add function 2. add a test"
+ur spec run demo --all --dry-run
+ur arena "implement a debounce helper" --agents 2 --dry-run
+ur escalate run "refactor the cache layer" --force-oracle --dry-run
+ur ci-loop --command "bun test" --dry-run
+ur artifacts capture-diff
+```
+
 ## Documentation
 
 - [Usage Guide](docs/USAGE.md)