feat(conductor): Add run_subagent script for stable headless skill invocation

MMA_Support/mma_tiered_orchestrator_skill.md

@@ -10,19 +10,23 @@ You are operating as a Tier 1 Product Manager or Tier 2 Tech Lead within the MMA
 
 To accomplish this, you MUST delegate token-heavy or stateless tasks to "Tier 3 Contributors" or "Tier 4 QA Agents" by spawning secondary Gemini CLI instances via `run_shell_command`.
 
+**CRITICAL Prerequisite:**
+To avoid hanging the CLI and ensure proper environment authentication, you MUST NOT call the `gemini` command directly. Instead, you MUST use the wrapper script:
+`.\scripts\run_subagent.ps1 -Prompt "..."`
+
 ## 1. The Tier 3 Worker (Heads-Down Coding)
 When you need to perform a significant code modification (e.g., refactoring a 500-line script, writing a massive class, or implementing a predefined spec):
 1. **DO NOT** attempt to write or use `replace`/`write_file` yourself. Your history will bloat.
 2. **DO** construct a single, highly specific prompt.
 3. **DO** spawn a sub-agent using `run_shell_command` pointing to the target file.
-   *Command:* `gemini ask "Modify [FILE_PATH] to implement [SPECIFIC_INSTRUCTION]. Only write the code, no pleasantries." --model gemini-1.5-flash`
+   *Command:* `.\scripts\run_subagent.ps1 -Prompt "Modify [FILE_PATH] to implement [SPECIFIC_INSTRUCTION]. Only write the code, no pleasantries."`
 4. If you need the sub-agent to automatically apply changes instead of just returning the text, use `gemini run` or pipe the output appropriately. However, the best method is to let the sub-agent modify the code and return "Done."
 
 ## 2. The Tier 4 QA Agent (Error Translation)
 If you run a local test (e.g., `npm test`, `pytest`, `go run`) via `run_shell_command` and it fails with a massive traceback (e.g., 200+ lines of `stderr`):
 1. **DO NOT** analyze the raw `stderr` in your own context window.
 2. **DO** immediately spawn a stateless Tier 4 agent to compress the error.
-3. *Command:* `gemini ask "Summarize this stack trace into a 20-word fix: [PASTE_SNIPPET_OF_STDERR_HERE]" --model gemini-1.5-flash`
+3. *Command:* `.\scripts\run_subagent.ps1 -Prompt "Summarize this stack trace into a 20-word fix: [PASTE_SNIPPET_OF_STDERR_HERE]"`
 4. Use the 20-word fix returned by the Tier 4 agent to inform your next architectural decision or pass it to the Tier 3 worker.
 
 ## 3. Context Amnesia (Phase Checkpoints)
@@ -38,7 +42,7 @@ When you complete a major Phase or Track within the `conductor` workflow:
 **Agent (You):** 
 ```json
 {
-  "command": "gemini ask "Summarize this stack trace into a 20-word fix: [snip first 30 lines...]" --model gemini-1.5-flash",
+  "command": ".\\scripts\\run_subagent.ps1 -Prompt \"Summarize this stack trace into a 20-word fix: [snip first 30 lines...]\"",
   "description": "Spawning Tier 4 QA to compress error trace statelessly."
 }
 ```
@@ -48,7 +52,7 @@ When you complete a major Phase or Track within the `conductor` workflow:
 **Agent (You):**
 ```json
 {
-  "command": "gemini ask "Read file_cache.py and implement the ASTParser class using tree-sitter. Ensure you preserve docstrings but strip function bodies. Output the updated code or edit the file directly." --model gemini-1.5-flash",
+  "command": ".\\scripts\\run_subagent.ps1 -Prompt \"Read file_cache.py and implement the ASTParser class using tree-sitter. Ensure you preserve docstrings but strip function bodies. Output the updated code or edit the file directly.\"",
   "description": "Delegating implementation to a Tier 3 Worker."
 }
 ```

conductor/workflow.md

@@ -364,9 +364,10 @@ A task is complete when:
 To emulate the 4-Tier MMA Architecture within the standard Conductor extension without requiring a custom fork, adhere to these strict workflow policies:
 
 ### 1. Active Model Switching (Simulating the 4 Tiers)
-- **Phase Planning & Macro Merges (Tier 1):** Use high-reasoning models (e.g., Gemini 1.5 Pro or Claude 3.5 Sonnet) when running \/conductor:setup\ or when reviewing a major phase checkpoint.
-- **Track Delegation & Implementation (Tier 2/3):** Switch your CLI to a mid-tier model (e.g., Gemini 1.5 Flash) before invoking \/conductor:implement\. This reserves the expensive model for architecture decisions while letting Flash handle the heads-down coding.
-- **QA/Fixing (Tier 4):** If a test fails with a massive traceback, **DO NOT** paste the traceback into the main conductor thread. Instead, switch to a fast/cheap model in a separate, isolated CLI instance, ask for the fix, and then manually apply the fix or provide the 20-word solution to the Conductor thread.
+- **Activate MMA Orchestrator Skill:** To enforce the 4-Tier token firewall explicitly, invoke `/activate_skill mma-orchestrator` (or use the `activate_skill` tool) when planning or executing new tracks.
+- **Phase Planning & Macro Merges (Tier 1):** Use high-reasoning models (e.g., Gemini 1.5 Pro or Claude 3.5 Sonnet) when running `/conductor:setup` or when reviewing a major phase checkpoint.
+- **Track Delegation & Implementation (Tier 2/3):** The MMA Orchestrator skill autonomously dispatches Tier 3 (Heads-Down Coding) tasks to secondary stateless instances of Gemini CLI (via `.\scripts\run_subagent.ps1 -Prompt "..."`) rather than performing heavy coding directly in the main thread.
+- **QA/Fixing (Tier 4):** If a test fails with a massive traceback, **DO NOT** paste the traceback into the main conductor thread. Instead, the MMA Orchestrator skill instructs you to spawn a fast/cheap model sub-agent (via a shell command) to compress the error trace into a 20-word fix, keeping the main context clean.
 
 ### 2. Context Checkpoints (The Token Firewall)
 - The **Phase Completion Verification and Checkpointing Protocol** is the project's primary defense against token bloat.

scripts/run_subagent.ps1

@@ -0,0 +1,12 @@
+param(
+    [Parameter(Mandatory=$true)]
+    [string]$Prompt,
+    
+    [string]$Model = "gemini-3-flash-preview"
+)
+
+# Ensure the session has the API key loaded
+. C:\projects\misc\setup_gemini.ps1
+
+# Piping an empty string ensures stdin is closed, forcing the Gemini CLI to terminate naturally after answering.
+echo "" | gemini $Prompt --model $Model