ur-agent 1.13.8 → 1.14.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (11) hide show
  1. package/CHANGELOG.md +43 -0
  2. package/README.md +11 -0
  3. package/dist/cli.js +3298 -1774
  4. package/docs/AGENT_FEATURES.md +30 -0
  5. package/docs/AGENT_TRENDS.md +28 -0
  6. package/docs/USAGE.md +16 -0
  7. package/docs/VALIDATION.md +21 -1
  8. package/documentation/app.js +88 -12
  9. package/documentation/index.html +71 -1
  10. package/examples/agent_features.md +14 -0
  11. package/package.json +1 -1
package/CHANGELOG.md CHANGED
@@ -1,5 +1,48 @@
1
1
  # Changelog
2
2
 
3
+ ## 1.14.0
4
+
5
+ ### Changed
6
+ - **Version bump.** Updated from 1.13.9 to 1.14.0 across `package.json`, `bunfig.toml`, and bundled CLI.
7
+
8
+ ### Verified
9
+ - Rebuilt `dist/cli.js` at 1.14.0 and verified release check, package check, and version output.
10
+
11
+ ## 1.13.9
12
+
13
+ ### Added
14
+ - **Spec-driven development (`ur spec`).** Scaffolds `requirements.md ->
15
+ design.md -> tasks.md` plus a phase/approval `spec.json` under `.ur/specs/`,
16
+ then drives execution task-by-task through a headless agent, checking off each
17
+ task on a PASS verdict. Tasks use the GitHub Spec Kit / Kiro `- [ ] T1: ...`
18
+ checkbox format, so lists are drop-in portable. `generate` can model-fill a
19
+ phase; scaffolding and task parsing stay pure and offline.
20
+ - **In-loop model escalation / local Oracle (`ur escalate`).** Picks a fast tier
21
+ and a strong "oracle" tier from `ur model-doctor`, starts routine work on the
22
+ fast model, and auto-escalates hard reasoning/debug/review (or a failed cheap
23
+ attempt) to the oracle. `escalate oracle` gets a one-shot second opinion;
24
+ `escalate policy` pins tiers. Tier selection and difficulty scoring are
25
+ deterministic and testable.
26
+ - **Multi-agent best-of-N judging (`ur arena`).** Runs N agents on the same task
27
+ in isolated git worktrees, judges the resulting diffs with the deterministic
28
+ self-review gate plus verdict/diff-shape heuristics, surfaces the winner, and
29
+ can `--apply` it. Local-first take on parallel-agent judging.
30
+ - **Self-healing CI loop (`ur ci-loop`).** Runs a build/test command and, on
31
+ failure, summarizes the error, hands it to a fix agent, and re-runs with a
32
+ bounded retry budget; `--commit`/`--push` are gated by the self-review check so
33
+ a fix can never push secrets. `--from-log` seeds the first failure from a log.
34
+ - **Verifiable artifacts surface (`ur artifacts`).** Records reviewable
35
+ deliverables (plans, diffs, test runs, screenshots) under `.ur/artifacts/`
36
+ with pending/approved/rejected status and threaded feedback; `capture-diff`
37
+ and `capture-tests` snapshot the working tree and test output for audit.
38
+
39
+ ### Verified
40
+ - Added focused unit suites for escalation, arena judging, the spec workflow,
41
+ the CI loop, and artifacts (26 tests); rebuilt `dist/cli.js` and verified
42
+ typecheck, the full test suite, release check, package check, secret scan,
43
+ version output, npm publish dry-run, and direct CLI smoke tests for
44
+ `ur spec`, `ur arena`, and `ur escalate`.
45
+
3
46
  ## 1.13.8
4
47
 
5
48
  ### Fixed
package/README.md CHANGED
@@ -99,6 +99,17 @@ ur mcp --help
99
99
  ur plugin --help
100
100
  ```
101
101
 
102
+ Agent platform examples:
103
+
104
+ ```sh
105
+ ur spec init demo --goal "1. add a utils.add function 2. add a test"
106
+ ur spec run demo --all --dry-run
107
+ ur arena "implement a debounce helper" --agents 2 --dry-run
108
+ ur escalate run "refactor the cache layer" --force-oracle --dry-run
109
+ ur ci-loop --command "bun test" --dry-run
110
+ ur artifacts capture-diff
111
+ ```
112
+
102
113
  ## Documentation
103
114
 
104
115
  - [Usage Guide](docs/USAGE.md)