fix: use coder model for pi agents

.pi/teams/agents/critic.md

@@ -1,8 +1,8 @@
 ---
 name: critic
 description: Challenges plans and implementations before expensive work continues.
-model: bong-llm/Qwen3.6
-fallbackModels: bong-llm/general-big, bong-llm/coder
+model: bong-llm/coder
+fallbackModels: bong-llm/coder
 thinking: high
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/devops.md

@@ -2,7 +2,7 @@
 name: devops
 description: Reviews local services, Docker, CI, deployment, secrets, and operational runbooks.
 model: bong-llm/coder
-fallbackModels: bong-llm/general-big
+fallbackModels: bong-llm/coder
 thinking: high
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/docs-specialist.md

@@ -1,8 +1,8 @@
 ---
 name: docs-specialist
 description: Technical writer for READMEs, guides, architecture notes, changelogs, specs, and parity reports.
-model: bong-llm/general
-fallbackModels: bong-llm/general-big
+model: bong-llm/coder
+fallbackModels: bong-llm/coder
 thinking: medium
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/e2e-tester.md

@@ -2,7 +2,7 @@
 name: e2e-tester
 description: Browser E2E tester using Playwright MCP and the project's Playwright suites.
 model: bong-llm/coder
-fallbackModels: bong-llm/general-big
+fallbackModels: bong-llm/coder
 thinking: high
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/executor.md

@@ -2,7 +2,7 @@
 name: executor
 description: Implements approved, scoped code changes and runs focused verification.
 model: bong-llm/coder
-fallbackModels: bong-llm/general-big, bong-llm/Qwen3.6
+fallbackModels: bong-llm/coder
 thinking: high
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/explorer.md

@@ -2,7 +2,7 @@
 name: explorer
 description: Maps relevant files, symbols, constraints, tests, and docs without editing.
 model: bong-llm/coder
-fallbackModels: bong-llm/general-big, bong-llm/Qwen3.6
+fallbackModels: bong-llm/coder
 thinking: medium
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/gitops.md

@@ -1,7 +1,7 @@
 ---
 name: gitops
 description: Handles git status, branch hygiene, diff review, commits, and feature-branch pushes.
-model: bong-llm/general
+model: bong-llm/coder
 fallbackModels: bong-llm/coder
 thinking: medium
 systemPromptMode: replace

.pi/teams/agents/memory-curator.md

@@ -1,8 +1,8 @@
 ---
 name: memory-curator
 description: Curates manual prompts, errors, fixes, decisions, and lessons into reviewed project memory without storing secrets or noisy transcripts.
-model: bong-llm/general
-fallbackModels: bong-llm/Qwen3.6, bong-llm/coder
+model: bong-llm/coder
+fallbackModels: bong-llm/coder
 thinking: high
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/planner.md

@@ -2,7 +2,7 @@
 name: planner
 description: Converts approved specs into concise implementation plans with files, tests, risks, and handoffs.
 model: bong-llm/coder
-fallbackModels: bong-llm/general-big, bong-llm/Qwen3.6
+fallbackModels: bong-llm/coder
 thinking: high
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/prompt-evolution-analyst.md

@@ -1,8 +1,8 @@
 ---
 name: prompt-evolution-analyst
 description: Proposes guarded improvements to agents, workflows, and Pi prompt shortcuts from memory, self-evaluations, errors, and manual prompt patterns.
-model: bong-llm/general-big
-fallbackModels: bong-llm/Qwen3.6, bong-llm/coder
+model: bong-llm/coder
+fallbackModels: bong-llm/coder
 thinking: high
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/reviewer.md

@@ -1,13 +1,13 @@
 ---
 name: reviewer
 description: Reviews diffs for bugs, regressions, missing tests, and project-rule violations.
-model: bong-llm/Qwen3.6
-fallbackModels: bong-llm/general-big, bong-llm/coder
-thinking: high
+model: bong-llm/coder
+fallbackModels: bong-llm/coder
+thinking: medium
 systemPromptMode: replace
 inheritProjectContext: true
 inheritSkills: false
-tools: read, grep, find, ls, bash
+tools: bash
 triggers: review, code review, diff review, pre-commit
 useWhen: after implementation or before commit
 avoidWhen: no diff or artifact exists to review
@@ -19,6 +19,21 @@ You review changes with a bug-finding mindset.
 
 Respect `AGENTS.md`. Prioritize correctness, regressions, missing tests, SSR hazards, Module Federation constraints, accessibility, SEO, and Angular/React parity drift.
 
+## Stall Prevention
+
+- First response must call `bash` once with a cheap heartbeat and diff overview:
+  `printf 'reviewer-start\n'; git status --short; git diff --stat; git diff --check`.
+- Do not use direct `read`, `grep`, `find`, or `ls` tools. Use `bash` only.
+- Do not read whole files unless a diff hunk or finding requires exact line evidence.
+- Inspect diffs in bounded chunks. Prefer:
+  - `git diff --name-only`
+  - `git diff --unified=80 -- <path> | sed -n '1,220p'`
+  - `nl -ba <path> | sed -n '<start>,<end>p'`
+  - `rg -n "debug\\(|console\\.|TODO|FIXME" <changed files>`
+- After each tool result, write at least one short sentence with current findings, even if it is only "No finding yet; continuing with <next file>." This keeps the task heartbeat alive.
+- If a tool returns more than about 250 lines, stop broad reading and narrow to file:line evidence.
+- If you cannot continue after a tool result, return a partial review with residual risk instead of starting another broad tool call.
+
 ## Tool Policy
 
 - Do not call an abstract tool named `glob`.

.pi/teams/agents/spec-analyst.md

@@ -1,8 +1,8 @@
 ---
 name: spec-analyst
 description: Turns product requests, PRDs, and existing docs into precise implementation constraints.
-model: bong-llm/general-big
-fallbackModels: bong-llm/Qwen3.6, bong-llm/coder
+model: bong-llm/coder
+fallbackModels: bong-llm/coder
 thinking: high
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/tdd-tester.md

@@ -2,7 +2,7 @@
 name: tdd-tester
 description: Designs tests before implementation and enforces red-green-refactor discipline.
 model: bong-llm/coder
-fallbackModels: bong-llm/general-big
+fallbackModels: bong-llm/coder
 thinking: high
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/tech-debt-auditor.md

@@ -1,8 +1,8 @@
 ---
 name: tech-debt-auditor
 description: Produces whole-repo, file-cited technical debt audits with ranked remediation priorities.
-model: bong-llm/general-big
-fallbackModels: bong-llm/Qwen3.6, bong-llm/coder
+model: bong-llm/coder
+fallbackModels: bong-llm/coder
 thinking: high
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/unit-tester.md

@@ -2,7 +2,7 @@
 name: unit-tester
 description: Adds and reviews unit tests and fast integration tests.
 model: bong-llm/coder
-fallbackModels: bong-llm/general-big
+fallbackModels: bong-llm/coder
 thinking: high
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/agents/version-parity-analyst.md

@@ -1,8 +1,8 @@
 ---
 name: version-parity-analyst
 description: Compares legacy Angular behavior against the React implementation, extracts business logic, writes specs, and verifies implementation parity.
-model: bong-llm/general-big
-fallbackModels: bong-llm/Qwen3.6, bong-llm/coder
+model: bong-llm/coder
+fallbackModels: bong-llm/coder
 thinking: high
 systemPromptMode: replace
 inheritProjectContext: true

.pi/teams/workflows/review-only.workflow.md

@@ -19,7 +19,7 @@ dependsOn: explore
 parallelGroup: review
 reads: review-context.md
 
-Review correctness, maintainability, regressions, tests, project-rule compliance, SSR safety, and Module Federation constraints.
+Review correctness, maintainability, regressions, tests, project-rule compliance, SSR safety, and Module Federation constraints. Start with the reviewer heartbeat command from the reviewer agent instructions, then inspect changed files in bounded diff chunks. Do not use direct `read`; use `bash` only. If the review cannot finish, return a partial review with residual risk instead of waiting silently.
 
 ## critical-review
 role: critic

.pi/teams/workflows/spec-driven-implementation.workflow.md

@@ -74,7 +74,7 @@ role: reviewer
 dependsOn: unit-verify, e2e-verify
 verify: true
 
-Review the final diff against the spec, plan, tests, and project rules. Return prioritized findings and whether any fix is required before commit.
+Review the final diff against the spec, plan, tests, and project rules. Start with the reviewer heartbeat command from the reviewer agent instructions, then inspect changed files in bounded diff chunks. Do not use direct `read`; use `bash` only. Return prioritized findings and whether any fix is required before commit. If the review cannot finish, return a partial review with residual risk instead of waiting silently.
 
 ## docs
 role: docs