pi-gsd 1.12.3 → 2.0.0

package/.gsd/harnesses/pi/get-shit-done/workflows/do.md

@@ -1,3 +1,32 @@
+<gsd-version v="1.12.4" />
+
+<gsd-arguments>
+  <settings><keep-extra-args /></settings>
+  <arg name="request" type="string" optional />
+</gsd-arguments>
+
+<gsd-execute>
+  <shell command="pi-gsd-tools">
+    <args>
+      <arg string="pi-gsd-tools" />
+      <arg string="state" />
+      <arg string="load" />
+      <arg string="--raw" />
+    </args>
+    <outs>
+      <suppress-errors />
+      <out type="string" name="state" />
+    </outs>
+  </shell>
+</gsd-execute>
+
+## Context (pre-injected)
+
+**Request:** <gsd-paste name="request" />
+
+**State:**
+<gsd-paste name="state" />
+
 <purpose>
 Analyze freeform text from the user and route to the most appropriate GSD command. This is a dispatcher - it never does the work itself. Match user intent to the best command, confirm the routing, and hand off.
 </purpose>
@@ -23,9 +52,7 @@ Wait for response before continuing.
 <step name="check_project">
 **Check if project exists.**
 
-```bash
-INIT=$(pi-gsd-tools state load 2>/dev/null)
-```
+<!-- Context pre-injected above via WXP — variables available via <gsd-paste name="..."> -->
 
 Track whether `.planning/` exists - some routes require it, others don't.
 </step>

package/.gsd/harnesses/pi/get-shit-done/workflows/execute-milestone.md

@@ -1,3 +1,67 @@
+<gsd-version v="1.12.4" />
+
+<gsd-arguments>
+  <settings><keep-extra-args /></settings>
+  <arg name="from" type="number" optional />
+  <arg name="uat-threshold" type="number" optional />
+</gsd-arguments>
+
+<gsd-execute>
+  <shell command="pi-gsd-tools">
+    <args>
+      <arg string="pi-gsd-tools" />
+      <arg string="roadmap" />
+      <arg string="analyze" />
+      <arg string="--raw" />
+    </args>
+    <outs>
+      <out type="string" name="roadmap" />
+    </outs>
+  </shell>
+  <shell command="pi-gsd-tools">
+    <args>
+      <arg string="pi-gsd-tools" />
+      <arg string="state" />
+      <arg string="json" />
+      <arg string="--raw" />
+    </args>
+    <outs>
+      <out type="string" name="state" />
+    </outs>
+  </shell>
+  <shell command="pi-gsd-tools">
+    <args>
+      <arg string="pi-gsd-tools" />
+      <arg string="progress" />
+      <arg string="json" />
+      <arg string="--raw" />
+    </args>
+    <outs>
+      <out type="string" name="progress" />
+    </outs>
+  </shell>
+  <!-- SET _auto_chain_active when milestone execution chain starts -->
+  <shell command="pi-gsd-tools">
+    <args>
+      <arg string="config-set" />
+      <arg string="workflow._auto_chain_active" />
+      <arg string="true" />
+    </args>
+    <outs><suppress-errors /></outs>
+  </shell>
+</gsd-execute>
+
+## Execution Context (pre-injected)
+
+**Roadmap:**
+<gsd-paste name="roadmap" />
+
+**State:**
+<gsd-paste name="state" />
+
+**Progress:**
+<gsd-paste name="progress" />
+
 # execute-milestone workflow
 
 Execute all planned phases in the current milestone with scope guardian, UAT gates, and configurable recovery.

package/.gsd/harnesses/pi/get-shit-done/workflows/execute-phase.md

@@ -1,3 +1,79 @@
+<gsd-version v="1.12.4" />
+
+<gsd-arguments>
+  <settings>
+    <keep-extra-args />
+    <delimiters>
+      <delimiter type="string" value="\n" />
+    </delimiters>
+  </settings>
+  <arg name="auto-chain-active" type="flag" flag="--auto" optional />
+  <arg name="phase" type="number" />
+  <arg name="user-text" type="string" optional />
+</gsd-arguments>
+
+<gsd-execute>
+  <shell command="pi-gsd-tools">
+    <args>
+      <arg string="init" />
+      <arg string="execute-phase" />
+      <arg name="phase" wrap='"' />
+    </args>
+    <outs>
+      <out type="string" name="init" />
+    </outs>
+  </shell>
+  <if>
+    <condition>
+      <starts-with>
+        <left name="init" />
+        <right type="string" value="@file:" />
+      </starts-with>
+    </condition>
+    <then>
+      <string-op op="split">
+        <args>
+          <arg name="init" />
+          <arg type="string" value="@file:" />
+        </args>
+        <outs>
+          <out type="string" name="init-file" />
+        </outs>
+      </string-op>
+      <shell command="cat">
+        <args>
+          <arg name="init-file" wrap='"' />
+        </args>
+        <outs>
+          <out type="string" name="init" />
+        </outs>
+      </shell>
+    </then>
+  </if>
+  <shell command="pi-gsd-tools">
+    <args>
+      <arg string="agent-skills" />
+      <arg string="gsd-executor" />
+    </args>
+    <outs>
+      <suppress-errors />
+      <out type="string" name="agent-skills" />
+    </outs>
+  </shell>
+</gsd-execute>
+
+## Execution Context (pre-injected)
+
+**Phase:** <gsd-paste name="phase" />
+
+**Phase Init Data:**
+<gsd-paste name="init" />
+
+**Agent Skills:**
+<gsd-paste name="agent-skills" />
+
+---
+
 <purpose>
 Execute all plans in a phase using wave-based parallel execution. Orchestrator stays lean - delegates plan execution to subagents.
 </purpose>
@@ -47,24 +123,11 @@ Always use the exact name from this list - do not fall back to 'general-purpose'
 
 <process>
 
-<step name="parse_args" priority="first">
-Parse `$ARGUMENTS` before loading any context:
-
-- First positional token → `PHASE_ARG`
-- Optional `--wave N` → `WAVE_FILTER`
-- Optional `--gaps-only` keeps its current meaning
-
-If `--wave` is absent, preserve the current behavior of executing all incomplete waves in the phase.
-</step>
 
 <step name="initialize" priority="first">
 Load all context in one call:
 
-```bash
-INIT=$(pi-gsd-tools init execute-phase "${PHASE_ARG}")
-if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
-AGENT_SKILLS=$(pi-gsd-tools agent-skills gsd-executor 2>/dev/null)
-```
+<!-- Init data pre-injected above via WXP: `init`, `agent-skills` variables available -->
 
 Parse JSON for: `executor_model`, `verifier_model`, `commit_docs`, `parallelization`, `branching_strategy`, `branch_name`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `plans`, `incomplete_plans`, `plan_count`, `incomplete_count`, `state_exists`, `roadmap_exists`, `phase_req_ids`.
 
@@ -83,12 +146,7 @@ internally and skip the `execute_waves` step in favor of `check_interactive_mode
 inline path for each plan.
 
 **REQUIRED - Sync chain flag with intent.** If user invoked manually (no `--auto`), clear the ephemeral chain flag from any previous interrupted `--auto` chain. This prevents stale `_auto_chain_active: true` from causing unwanted auto-advance. This does NOT touch `workflow.auto_advance` (the user's persistent settings preference). You MUST execute this bash block before any config reads:
-```bash
-# REQUIRED: prevents stale auto-chain from previous --auto runs
-if [[ ! "$ARGUMENTS" =~ --auto ]]; then
-  pi-gsd-tools config-set workflow._auto_chain_active false 2>/dev/null
-fi
-```
+<!-- auto-chain-active sync handled above via WXP -->
 </step>
 
 <step name="check_interactive_mode">