pi-loopflows 0.1.1 → 0.1.2

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 CHANGED
@@ -1,5 +1,10 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.1.2 - 2026-06-22
4
+
5
+ - Tighten README positioning around loopflows as LEGO-like subagent workflows.
6
+ - Remove the dedicated Launch Control README section while keeping it listed as a bundled workflow.
7
+
3
8
  ## 0.1.1 - 2026-06-22
4
9
 
5
10
  - Polish product README and usage guidance for public release.
package/README.md CHANGED
@@ -2,9 +2,7 @@
2
2
 
3
3
  Build deterministic AI workflows out of Pi subagents.
4
4
 
5
- A **loopflow** is a reusable process for agent work: steps, gates, feedback loops, stop rules, and evidence artifacts. Instead of asking one agent to “do the whole thing”, you describe how specialist agents should cooperate: one agent gathers context, another plans, another builds, another reviews, and a gate decides whether the work moves forward, loops back for fixes, or stops.
6
-
7
- `pi-loopflows` ships with a production-ready **Launch Control** loopflow out of the box, and it is also a flexible constructor for your own workflows.
5
+ Think of **loopflows** as LEGO for subagents. You take small specialist agents, connect them into a process, add gates where decisions matter, and let the workflow move forward, branch, loop back, or stop based on explicit results. Instead of one giant prompt, you get a reusable structure for how agents collaborate: steps, feedback loops, stop rules, and saved evidence.
8
6
 
9
7
  ## Why loopflows
10
8
 
@@ -65,32 +63,6 @@ loopflow_run({
65
63
  - `build-review` — small generic build → review → fix loop for scoped implementation tasks.
66
64
  - `plan-review` — planning loop that lets a reviewer reject vague or unsafe plans before implementation.
67
65
 
68
- ## Built-in: Launch Control
69
-
70
- Launch Control is bundled because it is the clearest example of why loopflows exist. It turns a plan into a controlled implementation process:
71
-
72
- ```text
73
- context-builder
74
- → planner
75
- → loop max 3:
76
- worker
77
- reviewer gate
78
- approved -> continue
79
- changes_requested -> repeat
80
- blocked -> stop
81
- → final audit
82
- ```
83
-
84
- Use it when drift, skipped validation, PR correctness, or multi-step delivery risk matter.
85
-
86
- Example:
87
-
88
- ```text
89
- /loopflow launch-control -- Implement the auth migration plan in docs/auth-plan.md
90
- ```
91
-
92
- Launch Control is not hard-coded. It is just a `.loopflow.json` file. You can copy it, change the agents, change the prompts, adjust max iterations, add stricter gates, or create a project-specific version in `.pi/loopflows/`.
93
-
94
66
  ## Loopflows as a constructor
95
67
 
96
68
  Think of loopflows as LEGO for agent processes. A loopflow can use any available Pi subagent role:
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "pi-loopflows",
3
- "version": "0.1.1",
3
+ "version": "0.1.2",
4
4
  "description": "Deterministic loop workflows for Pi subagents: steps, gates, feedback loops, and artifacts.",
5
5
  "license": "MIT",
6
6
  "author": "Nikita Nosov <20nik.nosov21@gmail.com>",