ur-agent 1.12.2 → 1.13.0
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.
- package/CHANGELOG.md +37 -0
- package/README.md +2 -1
- package/bin/ur.js +192 -0
- package/dist/cli.js +45334 -43378
- package/docs/AGENT_FEATURES.md +56 -0
- package/docs/AGENT_TRENDS.md +11 -0
- package/docs/VALIDATION.md +1 -1
- package/examples/agent_features.md +48 -0
- package/package.json +1 -1
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
# Agent Feature Expansion
|
|
2
|
+
|
|
3
|
+
This page tracks the nine agent-platform additions that were prioritized after
|
|
4
|
+
comparing UR with current Codex, Claude Code, Copilot, and Jules-style agent
|
|
5
|
+
workflows.
|
|
6
|
+
|
|
7
|
+
## Commands
|
|
8
|
+
|
|
9
|
+
```sh
|
|
10
|
+
ur agent-features
|
|
11
|
+
ur agent-features init
|
|
12
|
+
ur agent-templates list
|
|
13
|
+
ur agent-templates install
|
|
14
|
+
ur agent-task status
|
|
15
|
+
ur agent-task diff
|
|
16
|
+
ur agent-task pr
|
|
17
|
+
ur agent-task pr --create --dry-run
|
|
18
|
+
ur automation list
|
|
19
|
+
ur automation create nightly --schedule "0 9 * * 1-5" --prompt "Review open tasks"
|
|
20
|
+
ur automation run nightly --dry-run
|
|
21
|
+
ur automation run-due
|
|
22
|
+
ur model-doctor
|
|
23
|
+
ur a2a serve --dry-run
|
|
24
|
+
ur semantic-memory build
|
|
25
|
+
ur semantic-memory search "release checks"
|
|
26
|
+
ur claim-ledger add --claim "..." --source web:https://example.com
|
|
27
|
+
ur claim-ledger validate
|
|
28
|
+
ur browser-qa validate
|
|
29
|
+
ur browser-qa run home-page-smoke --dry-run
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
## Nine Points
|
|
33
|
+
|
|
34
|
+
| Point | UR surface | What it adds |
|
|
35
|
+
| --- | --- | --- |
|
|
36
|
+
| Task-to-PR workflow | `ur agent-task status|diff|pr --create` | Summarizes task state, git changes, branch, and can create a GitHub PR through `gh` |
|
|
37
|
+
| Recurring automations | `ur automation` and `.ur/automations/` | Project-local automation specs with validation, next-run calculation, manual run, due-run, dry-run, and last-run state |
|
|
38
|
+
| Model capability report | `ur model-doctor` | Local Ollama model inventory with context length, advertised capabilities, and likely vision/code readiness |
|
|
39
|
+
| Reusable agent templates | `ur agent-templates install` | Project agents for review, tests, browser QA, docs research, security, release notes, PR fixes, and memory curation |
|
|
40
|
+
| GitHub agent runner | `.github/workflows/ur-agent.yml` scaffold | Opt-in CI entry point for manual prompts or `/ur` issue comments |
|
|
41
|
+
| A2A adapter handoff | `ur a2a serve` | Loopback Agent Card and token-gated task execution endpoint |
|
|
42
|
+
| Semantic memory index | `ur semantic-memory build|search` | Local memory index over durable memory, docs, README, and UR instructions |
|
|
43
|
+
| Claim provenance ledger | `ur claim-ledger add|list|validate` | Maps generated claims to web, file, MCP, tool, or user sources |
|
|
44
|
+
| Browser replay evals | `ur browser-qa list|validate|run` | Validates replay fixtures and performs lightweight target smoke checks |
|
|
45
|
+
|
|
46
|
+
## Design Notes
|
|
47
|
+
|
|
48
|
+
These additions keep network-facing behavior opt-in, but the local task, PR,
|
|
49
|
+
automation, model, and template surfaces are executable commands. UR already has
|
|
50
|
+
tasks, custom agents, memory files, browser workflows, evidence commands, A2A
|
|
51
|
+
Agent Card export, and local Ollama routing; these surfaces make those
|
|
52
|
+
capabilities easier to discover and reuse.
|
|
53
|
+
|
|
54
|
+
Network-facing behavior, such as a full A2A task server or a GitHub bot that can
|
|
55
|
+
push code, should remain explicitly opt-in because it changes the trust and
|
|
56
|
+
permission boundary.
|
package/docs/AGENT_TRENDS.md
CHANGED
|
@@ -10,6 +10,17 @@ ur agent-trends
|
|
|
10
10
|
ur agent-trends --json
|
|
11
11
|
ur a2a card
|
|
12
12
|
ur a2a card --base-url https://example.com
|
|
13
|
+
ur agent-features
|
|
14
|
+
ur agent-features init
|
|
15
|
+
ur agent-templates install
|
|
16
|
+
ur model-doctor
|
|
17
|
+
ur automation create nightly --schedule "0 9 * * 1-5" --prompt "Review open tasks"
|
|
18
|
+
ur automation run-due
|
|
19
|
+
ur agent-task pr --create --dry-run
|
|
20
|
+
ur a2a serve --dry-run
|
|
21
|
+
ur semantic-memory build
|
|
22
|
+
ur claim-ledger validate
|
|
23
|
+
ur browser-qa validate
|
|
13
24
|
```
|
|
14
25
|
|
|
15
26
|
Inside an interactive session:
|
package/docs/VALIDATION.md
CHANGED
|
@@ -0,0 +1,48 @@
|
|
|
1
|
+
# Agent Features
|
|
2
|
+
|
|
3
|
+
Use these commands to install and exercise the expanded agent feature surfaces.
|
|
4
|
+
|
|
5
|
+
```sh
|
|
6
|
+
ur agent-features
|
|
7
|
+
ur agent-features init
|
|
8
|
+
```
|
|
9
|
+
|
|
10
|
+
Install reusable project agents:
|
|
11
|
+
|
|
12
|
+
```sh
|
|
13
|
+
ur agent-templates list
|
|
14
|
+
ur agent-templates install reviewer test-runner browser-debugger
|
|
15
|
+
```
|
|
16
|
+
|
|
17
|
+
Create and dry-run a recurring project automation:
|
|
18
|
+
|
|
19
|
+
```sh
|
|
20
|
+
ur automation create nightly --schedule "0 9 * * 1-5" --prompt "Review open tasks and suggest the next action"
|
|
21
|
+
ur automation run nightly --dry-run
|
|
22
|
+
ur automation run-due --dry-run
|
|
23
|
+
```
|
|
24
|
+
|
|
25
|
+
Inspect task and PR handoff state:
|
|
26
|
+
|
|
27
|
+
```sh
|
|
28
|
+
ur agent-task status
|
|
29
|
+
ur agent-task diff
|
|
30
|
+
ur agent-task pr --create --dry-run
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
Use the local memory, evidence, and browser QA helpers:
|
|
34
|
+
|
|
35
|
+
```sh
|
|
36
|
+
ur semantic-memory build
|
|
37
|
+
ur semantic-memory search "release checks"
|
|
38
|
+
ur claim-ledger add --claim "Release checks include typecheck" --source file:package.json
|
|
39
|
+
ur claim-ledger validate
|
|
40
|
+
ur browser-qa validate
|
|
41
|
+
```
|
|
42
|
+
|
|
43
|
+
Run the opt-in A2A server on loopback:
|
|
44
|
+
|
|
45
|
+
```sh
|
|
46
|
+
ur a2a serve --dry-run
|
|
47
|
+
curl http://127.0.0.1:8765/healthz
|
|
48
|
+
```
|