pi-herdsman 0.5.1 → 0.6.0

package/README.md

@@ -1,17 +1,16 @@
 # Pi Herdsman 🐏
 
-![Pi Herdsman: asynchronous subagents and multi-agent orchestration for Pi](docs/assets/banner.webp)
+![Pi Herdsman: asynchronous Pi subagents and agent fleet orchestration](docs/assets/banner.webp)
 
-**Asynchronous subagents and multi-agent orchestration for [Pi](https://github.com/earendil-works/pi) in [herdr](https://github.com/herdrdev/herdr).**
+**Asynchronous [Pi](https://github.com/earendil-works/pi) subagents and agent fleet orchestration with nested delegation, parallel execution, and supervision in [herdr](https://github.com/herdrdev/herdr).**
 
 Keep the conversation. Delegate the work.
 
-Pi Herdsman is a Pi extension for asynchronous subagents (sub-agents).
-Delegate coding tasks to managed background agents running in independent Pi
-sessions while the lead conversation stays interactive. Run agents in
-parallel, nest delegation, steer active agents, route questions and results
-back to their owning agent, and supervise multiple leads through one
-coordinated hierarchy.
+Pi Herdsman is a Pi extension for asynchronous subagents. Delegate coding
+tasks to managed background agents running in independent Pi sessions while
+the lead conversation stays interactive. Run agents in parallel, nest
+delegation, steer active agents, route questions and results back to their
+owning agent, and supervise multiple leads through one coordinated hierarchy.
 
 Pi Herdsman calls its managed subagents **agents**.
 
@@ -22,6 +21,9 @@ You ↔ lead
       └─ agent
 ```
 
+A lead and its nested agent hierarchy form a herd, Herdsman's model of an
+agent fleet.
+
 Pi Herdsman is opinionated about coordination, not workflow. A lead owns its
 agents, and a delegation-enabled agent may own permitted agents of its own.
 Agent definitions, models, tools, extensions, and development process remain up
@@ -45,20 +47,29 @@ chief
 
 ```sh
 pi install npm:pi-herdsman
+herdr integration install pi
 ```
 
-The lead Pi session must run inside herdr.
+Start Herdr in your project:
+
+```sh
+herdr
+```
 
-## Try it
+Then run Pi in the Herdr pane:
+
+```sh
+pi
+```
 
 Ask Pi normally:
 
 ```text
-Use an implementer agent to implement the approved change.
+Use scout to inspect this repository.
 ```
 
-That is enough. The implementer runs asynchronously while the lead conversation
-remains available.
+That's enough. The agent runs asynchronously while the lead conversation remains
+available.
 
 Other useful requests look the same:
 
@@ -137,9 +148,11 @@ tools, extensions, skills, and instructions.
 ## Requirements
 
 - [herdr](https://github.com/herdrdev/herdr) `>=0.9.0`
-- Pi `>=0.84.2 <0.86.0` (the version range tested for this release)
+- Pi `>=0.84.2 <0.86.0` (supported)
 - Node `>=22.19.0`
 
+CI validates Node 22.19.0 with the locked dependency set.
+
 Install or refresh the herdr Pi integration:
 
 ```sh

package/dist/agent-definitions/generalist.md

@@ -1,8 +1,6 @@
 ---
 name: generalist
 description: General-purpose execution agent for scoped tasks that do not fit scout, researcher, implementer, or reviewer
-model: openai-codex/gpt-5.6-luna
-thinking: medium
 agents: ["scout", "researcher"]
 systemPromptMode: replace
 inheritProjectContext: true

package/dist/agent-definitions/implementer.md

@@ -1,8 +1,6 @@
 ---
 name: implementer
 description: Focused implementation agent for a resolved change; use when the required behavior is already decided and the task is to edit, test, and report
-model: openai-codex/gpt-5.6-luna
-thinking: high
 agents: ["scout"]
 systemPromptMode: replace
 inheritProjectContext: true

package/dist/agent-definitions/researcher.md

@@ -1,8 +1,6 @@
 ---
 name: researcher
 description: External research specialist for questions that require web, documentation, standards, vendor, or other authoritative evidence beyond the repository; use for current facts, API behavior, comparisons, and source-backed recommendations
-model: openai-codex/gpt-5.6-luna
-thinking: medium
 systemPromptMode: replace
 inheritProjectContext: true
 inheritGlobalContext: false

package/dist/agent-definitions/reviewer.md

@@ -1,8 +1,6 @@
 ---
 name: reviewer
 description: Independent read-only reviewer for plans, diffs, implementations, and codebase health; use when work needs verification, missing-case analysis, or regression review rather than modification
-model: openai-codex/gpt-5.6-luna
-thinking: medium
 agents: ["scout", "researcher"]
 systemPromptMode: replace
 inheritProjectContext: true

package/dist/agent-definitions/scout.md

@@ -1,8 +1,6 @@
 ---
 name: scout
 description: Read-only codebase reconnaissance for unfamiliar areas; use to find entry points, trace flows, dependencies, constraints, and risks before deciding or editing
-model: openai-codex/gpt-5.6-luna
-thinking: medium
 systemPromptMode: replace
 inheritProjectContext: true
 inheritGlobalContext: false