substrate-ai 0.2.38 → 0.2.39

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.
@@ -8,12 +8,12 @@ This project uses Substrate for automated implementation pipelines. **When the u
8
8
  **Just run it.** Substrate auto-detects which pipeline phase to start from (analysis → planning → solutioning → implementation) and auto-discovers pending stories. You do not need to determine the phase or find story keys manually.
9
9
 
10
10
  ```
11
- substrate supervisor --output-format json
11
+ substrate run --events
12
12
  ```
13
13
 
14
14
  To target specific stories (if the user names them):
15
15
  ```
16
- substrate supervisor --output-format json --stories 1-1,1-2,1-3
16
+ substrate run --events --stories 1-1,1-2,1-3
17
17
  ```
18
18
 
19
19
  If substrate needs input it can't auto-detect (e.g., a project concept for analysis), it will exit with a clear error message telling you what to provide.
@@ -36,13 +36,18 @@ Check process health if pipeline seems quiet:
36
36
  substrate health --output-format json
37
37
  ```
38
38
 
39
+ For long-running pipelines, attach the **supervisor** for automatic stall detection, kill-and-restart recovery, and post-run analysis. The supervisor monitors an active run — it does not start one. Start it alongside `substrate run`:
40
+ ```
41
+ substrate supervisor --output-format json
42
+ ```
43
+
39
44
  **Interpreting silence:** No output for 5 minutes = normal (agent is working). No output for 15+ minutes = likely stalled. Use `substrate health` to confirm, then consider killing and resuming.
40
45
 
41
46
  ### After Pipeline Completes
42
47
 
43
48
  1. **Summarize results** conversationally: X succeeded, Y failed, Z escalated
44
49
  2. **Check metrics**: `substrate metrics --output-format json`
45
- 3. **Read analysis** (if supervisor mode): `substrate metrics --analysis <run_id> --output-format json`
50
+ 3. **Read analysis** (if supervisor was attached): `substrate metrics --analysis <run_id> --output-format json`
46
51
 
47
52
  ### Handling Escalations and Failures
48
53
 
@@ -57,7 +62,7 @@ substrate health --output-format json
57
62
  | Command | Purpose |
58
63
  |---|---|
59
64
  | `substrate run --events` | Run pipeline with NDJSON event stream |
60
- | `substrate supervisor --output-format json` | Run with auto-recovery and analysis |
65
+ | `substrate supervisor --output-format json` | Monitor active run with auto-recovery and post-run analysis |
61
66
  | `substrate status --output-format json` | Poll current pipeline state |
62
67
  | `substrate health --output-format json` | Check process health and stall detection |
63
68
  | `substrate metrics --output-format json` | View historical run metrics |
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "substrate-ai",
3
- "version": "0.2.38",
3
+ "version": "0.2.39",
4
4
  "description": "Substrate — multi-agent orchestration daemon for AI coding agents",
5
5
  "type": "module",
6
6
  "license": "MIT",