@m8i-51/shoal 0.1.18 → 0.1.19

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 (2) hide show
  1. package/README.md +15 -1
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -114,12 +114,26 @@ npm run serve # from cloned repo
114
114
  Opens at `http://localhost:4000`. From there you can:
115
115
 
116
116
  - **Start a run** — configure agent count, target URL, and custom instructions
117
- - **Monitor live progress** — watch agents explore and file findings in real time
117
+ - **Watch agents swim live** — the Swarm tab shows an animated real-time view of agents as they explore. When a finding is discovered, the agent's chip flashes with the finding title.
118
118
  - **Review past runs** — findings by category, agent count, duration, and estimated cost
119
+ - **Generate an Agent Diary** — after a run completes, one LLM call turns the raw log into a story-style narrative of the exploration, readable by anyone on the team
120
+ - **Hall of Issues** — browse all findings across every run with full-text search and category filter. Export as JSON to share, or paste a community findings URL to import findings from other projects.
119
121
  - **Edit app goals** — guide the goal-gap detector by defining what the app should achieve
120
122
 
121
123
  ---
122
124
 
125
+ ## Cross-run intelligence
126
+
127
+ shoal gets smarter with each run.
128
+
129
+ **Diff exploration** — after every browser navigation, shoal hashes the page content (SHA-256 of `innerText`). On the next run, agents that land on an unchanged page are nudged to move on: *"page content unchanged since last run — consider exploring a different area."* The hashes accumulate in `cache/page-hashes/` and steer future agents toward parts of the app that have actually changed.
130
+
131
+ **Finding hotspots** — the persona designer has access to a `get_finding_hotspots` tool that aggregates findings by URL area across all past runs. It uses this to recruit agents toward under-investigated parts of the app, or to send specialists into zones where problems keep clustering.
132
+
133
+ Both signals work passively — no configuration needed. They improve automatically as runs accumulate.
134
+
135
+ ---
136
+
123
137
  ## Configuration
124
138
 
125
139
  | Variable | Default | Description |
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@m8i-51/shoal",
3
- "version": "0.1.18",
3
+ "version": "0.1.19",
4
4
  "type": "module",
5
5
  "description": "Multi-agent web exploration framework — finds bugs, UX issues, and missing features by running AI agents against your app",
6
6
  "repository": {