pi update

pi/.pi/agent/prompts/implement-critical.md

@@ -1,5 +1,5 @@
 ---
-description: "Maximum quality pipeline — deep scout, Max planning, Opus plan review, approval gate, Sonnet coding, Opus code review"
+description: "Maximum quality pipeline — deep scout, thorough planning, plan review, approval gate, coding, code review"
 ---
 
 Use the subagent tool to implement with maximum quality. This is for high-risk or architecturally significant changes.
@@ -30,7 +30,7 @@ If the user requests changes, revise the plan (re-run planner with the feedback)
 - For each coder run, include the approved plan verbatim: "Implement the following plan step(s). Do NOT deviate.\n\n<plan>\n{the approved plan steps}\n</plan>"
 - For multiple independent steps, run them in parallel using separate coder-claude tasks, each assigned to specific files/plan steps to avoid conflicts
 
-## Step 4: Opus review
+## Step 4: Code review
 Run the "reviewer" agent on all changes with this task: "Review all changes made for: $@\n\nCheck for correctness, edge cases, error handling, type safety, and consistency with the approved plan."
 
 ## Step 5: Fix

pi/.pi/agent/prompts/implement.md

@@ -29,7 +29,7 @@ If the user requests changes to the plan, revise and present again before implem
 ## Step 3: Implement
 
 Once approved:
-- Execute the plan steps using "coder" for sequential steps, or "coder-parallel" with parallel tasks if the plan identified parallelizable steps
+- Execute the plan steps using the "coder" agent
 - When running coder, always wrap the plan step(s) in the task: "Implement the following plan step(s). Do NOT deviate.\n\n<plan>\n{the approved plan steps}\n</plan>"
 - Run the "reviewer" agent on all changes
 - If NEEDS_FIXES, run the "fixer" agent with the review output
@@ -43,26 +43,13 @@ After the final step, summarize: what was done, what files changed, what was rev
 - **NEVER skip the approval gate**. Always present the plan and wait.
 - Always pass scout context forward using {previous} in chain mode — this is how the planner and plan-reviewer receive the scout's findings.
 - When running the coder, always include the approved plan verbatim in the task so the coder has full context.
-- For parallel coder tasks, clearly assign each coder to specific files/plan steps to avoid conflicts.
 
 ## Agent Failure and Fallback
 
 When a subagent returns empty output or an error (rate limit, credit exhaustion, connection failure):
 
 1. **Retry once** with the same agent and model — transient failures are common.
-2. **If still failing, retry with the cross-family fallback model** using the `model` override parameter:
-
-| Agent | Primary model | Fallback model |
-|-------|--------------|----------------|
-| scout | zai/glm-4.7-flash | anthropic/claude-haiku-4-5 |
-| deep-scout, coder-parallel | zai/glm-4.7 | anthropic/claude-sonnet-4-6 |
-| planner, coder | zai/glm-5.1 | anthropic/claude-opus-4-6 |
-| reviewer-quick, explorer | anthropic/claude-haiku-4-5 | zai/glm-4.7-flash |
-| coder-claude, fixer | anthropic/claude-sonnet-4-6 | zai/glm-5.1 |
-| plan-reviewer, reviewer | anthropic/claude-opus-4-6 | zai/glm-5.1 |
-
-Example: `subagent({ agent: "scout", task: "...", model: "anthropic/claude-haiku-4-5" })`
-
+2. **If still failing, retry with the cross-family fallback model** using the `model` override parameter. See the fallback table in the `subagent-implement` SKILL.md for the current primary/fallback mapping.
 3. **If the fallback also fails**, do the work yourself (read the relevant files directly and produce the scout/plan/review output inline). Inform the user which agent failed, what error was returned, and what you did instead.
 
 Do NOT silently absorb failures. Always surface them to the user even when working around them.

pi/.pi/agent/prompts/plan.md

@@ -1,5 +1,5 @@
 ---
-description: "Scout + plan + Opus plan review — no implementation"
+description: "Scout + plan + plan review — no implementation"
 ---
 
 Use the subagent tool with a chain to plan (but NOT implement) the following:
@@ -19,8 +19,5 @@ Present the plan and the review to me. Do NOT proceed to implementation.
 If any agent returns empty output or an error (rate limit, credit exhaustion, connection failure):
 
 1. Retry once with the same agent.
-2. If still failing, retry with the cross-family fallback using the `model` override:
-   - scout (zai/glm-4.7-flash fails) → `model: "anthropic/claude-haiku-4-5"`
-   - planner (zai/glm-5.1 fails) → `model: "anthropic/claude-opus-4-6"`
-   - plan-reviewer (anthropic/claude-opus-4-6 fails) → `model: "zai/glm-5.1"`
+2. If still failing, retry with the cross-family fallback using the `model` override. See the fallback table in the `subagent-plan` SKILL.md for the current mapping.
 3. If the fallback also fails, do the work yourself and tell me which agent failed and why.