codebyplan 1.10.3 → 1.11.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "codebyplan",
-  "version": "1.10.3",
+  "version": "1.11.1",
   "description": "CLI for CodeByPlan — AI-powered development planning and tracking",
   "type": "module",
   "bin": {

package/templates/agents/cbp-round-executor.md

@@ -436,7 +436,7 @@ If none match, skip — proceed directly to Step 4.
    - Aggregate `summary` totals into `round.context.frontend_self_review.summary` (combined critical / warning / suggestion / auto_fixed / out_of_scope_fixes).
 
 4. **Surface non-mechanical findings** to the round summary:
-   - `baseline_regression` and `rendered_visual` findings from `cbp-frontend-ui` are NOT auto-fixed (root cause is typically in app state/data, not styling) — surface for `cbp-testing-qa-agent` Phase 4b to convert into mandatory user QA items.
+   - `baseline_regression` and `rendered_visual` findings from `cbp-frontend-ui` are NOT auto-fixed (root cause is typically in app state/data, not styling) — surface in `round.context.frontend_ui_review` findings; `/cbp-round-end` Step 7 surfaces baseline-regression findings as a blocking accept-or-fix gate (baselines never auto-accepted).
    - `out_of_scope_fixes` from either skill (findings whose target file is outside `files_changed`) — surface in `improvements_noted[]` for follow-up rounds; the scope gate prevented silent absorption.
 
 **Why inline (not a separate spawn)**: the post-implementation review consumes the same files the executor just touched. Spawning a separate agent doubles token cost (re-reading the files) and serialises wall time; invoking via Skill keeps both review passes inside the executor's working memory and lets fixes apply with the same Edit/Write tools that wrote the original code. The Pre-Edit Scope Gate inside each skill provides the same boundary the standalone agent enforced.

package/templates/agents/cbp-task-check.md

@@ -80,7 +80,6 @@ Compare task work against `checkpoint.goal`:
 
 Review all QA items across all rounds:
 - **Auto items**: Verify all passed (build, lint, types, tests)
-- **User items**: Verify all marked pass/skip
 - **Default items**: Verify all resolved (pass or skipped with reason)
 
 **E2E pass vs skipped distinction**: When reading `auto_qa.items[]` for `check: 'e2e'`, do NOT conflate `status: 'pass'` with `status: 'skipped'`. A spec that ran with `passed === 0 && skipped > 0` for any path touching `files_changed` is a hard fail, not a pass — verdict text MUST explicitly call this out: "E2E spec authored but assertions did not execute (skip-gated)." Do NOT issue a READY verdict on a zero-assertion e2e run; route to a fix round per `rules/spec-skip-vs-execute.md`.

package/templates/agents/cbp-test-e2e-agent.md

@@ -289,7 +289,7 @@ For each failed test, classify into exactly one category:
 | `auth` | Login-page redirect after credential submit, 401 on authenticated request, `invalid_grant`, `email_not_confirmed` | AskUserQuestion as in Step 6.5.3 |
 | `access` | 403, 404 on a route the user should have access to, RLS policy denial text, missing seed data | AskUserQuestion: "Test failed with access error: `{error}`. Seed data or RLS policy may be missing. Options: (1) reply with steps you took to fix, (2) abort." |
 | `flake` | Timeout on first run, passes on immediate retry, network jitter | Retry up to 3 times before reclassifying to `real` |
-| `visual_regression` | `toHaveScreenshot` pixel-diff exceeded threshold | Do NOT retry. Include baseline + actual paths in `screenshots[]` with `baseline_diff_pct`. Do NOT auto-accept baseline — leave for `frontend-ui` (`/cbp-round-execute` Step 5b under `phase: 'screenshot_review'`) and user QA. |
+| `visual_regression` | `toHaveScreenshot` pixel-diff exceeded threshold | Do NOT retry. Include baseline + actual paths in `screenshots[]` with `baseline_diff_pct`. Do NOT auto-accept baseline — leave for `frontend-ui` (`/cbp-round-execute` Step 5b under `phase: 'screenshot_review'`); baseline regressions surface at `/cbp-round-end` Step 7 as a blocking gate. |
 | `real` | Assertion failure on app behavior (text missing, wrong state, navigation broken) | Attempt fix (see Step 8), then report to executor |
 
 Failures with `category` of `env`, `auth`, or `access` MUST NOT be counted as test failures in `test_results.failed` until pre-flight passes — they block the run instead.
@@ -355,7 +355,7 @@ Populate all output contract fields. Include test file paths in `tests_written`,
 ## Integration
 
 - **Spawned by**: `/cbp-round-execute` Step 5 (parallel sibling of `testing-qa-agent`); also invoked by `/cbp-checkpoint-check` (TASK-2 deliverable) with `whole_checkpoint_mode: true`
-- **Parallel sibling**: `cbp-testing-qa-agent` (owns build/lint/types/unit/audit + single-source visual-QA items). **Fully independent — no cross-read.** This agent's screenshots are consumed by `/cbp-round-execute` Step 5b (`frontend-ui` skill, `phase: 'screenshot_review'`) which writes `round.context.frontend_ui_review.findings`; downstream user_qa items from those findings are aggregated at `/cbp-round-end` Step 3b.
+- **Parallel sibling**: `cbp-testing-qa-agent` (owns build/lint/types/unit/audit). **Fully independent — no cross-read.** This agent's screenshots are consumed by `/cbp-round-execute` Step 5b (`frontend-ui` skill, `phase: 'screenshot_review'`) which writes `round.context.frontend_ui_review.findings`; baseline-regression findings surface as a BLOCKING gate at `/cbp-round-end` Step 7 (baselines never auto-accepted).
 - **Returns to**: `/cbp-round-execute` which persists output to `round.context.e2e_output`. Step 5b then invokes the `frontend-ui` skill with `phase: 'screenshot_review'` and the screenshots; Step 6 considers `e2e_output.test_results.failed > 0` and `status === 'failed'` as hard-fail signals.
 - **Reads**: `.claude/context/testing/e2e.md`, page/screen source files, existing specs, `.env.local`, `.codebyplan/server.json` `port_allocations`, MCP `get_repos` (for `tech_stack` reconciliation at Step 1.5)
 - **May modify source**: Only to add testID/data-testid attributes

package/templates/agents/cbp-testing-qa-agent.md

@@ -1,7 +1,7 @@
 ---
 scope: org-shared
 name: cbp-testing-qa-agent
-description: Combined testing, QA generation, and default checklists. Runs build/lint/types/unit-tests/audit, generates auto and single-source user QA items (design-source comparison + mechanical-sweep spot-check), applies default production checklists. Does NOT consume e2e screenshots or frontend-ui findings — cross-source visual-QA items are built downstream at /cbp-round-end Step 3.
+description: Combined testing, QA generation, and default checklists. Runs build/lint/types/unit-tests/audit, generates auto QA items, applies default production checklists. Does NOT consume e2e screenshots or frontend-ui findings.
 tools: Read, Glob, Grep, Bash, AskUserQuestion
 model: sonnet
 effort: xhigh
@@ -16,11 +16,11 @@ Combined testing, QA generation, and default production checklists in a single a
 Single agent that handles non-e2e quality validation in the per-wave validation phase of `/cbp-round-execute` Step 5:
 - Run all 18 automated checks (work + quality verification)
 - **EXECUTE** automated testing commands (build, lint, types, unit tests, visual checks, audit)
-- Generate auto and user QA items
+- Generate auto QA items
 - Apply default production checklist items
 - Detect unrelated issues and missing tests
 
-E2E execution (Playwright / Maestro / WebDriverIO / XCUITest / vscode-test) is owned by `cbp-test-e2e-agent`, spawned in parallel with this agent by `/cbp-round-execute` Step 5. **The two agents are fully independent — this agent does NOT read `round.context.e2e_output` or `round.context.frontend_ui_review`.** Cross-source visual-QA items (baseline regressions, rendered-visual critical findings) are constructed downstream at `/cbp-round-end` Step 3 from `frontend_ui_review.findings`. This agent emits only single-source visual-QA items (Phase 4b.1 design-source comparison + Phase 4b.2 mechanical-sweep spot-check).
+E2E execution (Playwright / Maestro / WebDriverIO / XCUITest / vscode-test) is owned by `cbp-test-e2e-agent`, spawned in parallel with this agent by `/cbp-round-execute` Step 5. **The two agents are fully independent — this agent does NOT read `round.context.e2e_output` or `round.context.frontend_ui_review`.** This agent emits auto QA items and default checklist items. Baseline-regression findings surface as a BLOCKING gate at `/cbp-round-end` Step 7 (an explicit accept-or-fix user decision; baselines are NEVER auto-accepted).
 
 ## Input Contract
 
@@ -63,13 +63,6 @@ output:
         stdout: string        # captured command output
         stderr: string        # captured error output
         screenshots: [{page, viewport, status, file}]  # visual check only
-  user_qa:
-    items:
-      - type: 'user'
-        check: string
-        status: 'pending'
-        instructions: string
-        round_number: number
   default_checklist:
     items:
       - type: 'default'
@@ -256,7 +249,7 @@ Report findings in `build_analysis` even if the build succeeded.
 
 When `files_changed` includes a new route file under any `apps/*/src/app/api/` or `apps/*/src/app/mcp/` directory:
 - If dev server is running: curl the endpoint without credentials, assert response is 401/403 (not 200). Log as auto QA item `auth_enforcement`.
-- If dev server is not running: generate a user QA item with the exact curl command and expected 401 status.
+- If dev server is not running: log a skipped auto QA item with the exact curl command noted in `notes` for reference.
 
 ### Phase 3.58: Missing Unit Tests for New API Routes
 
@@ -331,22 +324,7 @@ This aligns with `immediate-issue-capture.md` (resolve-in-current-scope by defau
 
 **4a. Auto QA items**: Generate from Phase 3 results. One item per test category. Include stdout/stderr.
 
-**4b. User QA items**: Targeted verification items only a human can check.
-
-**4b.0. Connection smoke test suppression**: Before emitting any connection smoke test user QA item (MCP connection, server health, service wiring), check whether the governing config file is unchanged. Governing config map: MCP (Claude Code) → `.mcp.json`; Dev server → `.env.local`, `.codebyplan/server.json` port_allocations; API integrations → `.env.local`. **Suppression rule**: if the governing config is NOT in `files_changed` AND `git diff HEAD -- <config>` is empty, log `{type:"user", check:"<name>", status:"skipped", notes:"Governing config <file> unchanged in this round; connection behavior is unaffected."}` — do NOT emit a pending user QA item.
-
-**4b.1. Design source comparison** (mandatory when `has_ui_work` is true): Search the project's design-sources directory (e.g., `docs/design/`, `docs/development/product/sources/design/`) for PNG files matching the page or component being changed. If design PNGs exist, add a mandatory user QA item with check: "Design source fidelity" and instructions: "Compare rendered output against design source PNG. Verify: column layout matches, control shapes match (flat vs pill vs toggle), background colors match, row structure and dividers match, action controls are in the correct column."
-
-**4b.2. Volume-gated mechanical-sweep spot-check** (volume-triggered, runs regardless of `has_ui_work`): when `files_changed.length > 100` AND the round is mechanical (`work_type == 'mechanical'` OR round requirements match `/sweep|auto.?fix|batch|backlog/i`), emit a mandatory user QA item:
-
-- `check`: `"High-volume mechanical round spot-check"`
-- `status`: `"pending"`
-- `instructions`: "This round modified {N} files mechanically. Open 3–5 changed files in the running app and verify behavior is unchanged. Prioritize files with business logic (services, hooks, reducers) over pure presentation. Spot-check at least one file from each touched module."
-- `round_number`: current
-
-Volume gating exists because automated checks (build/lint/types/unit) verify shape but not behaviour preservation; large mechanical sweeps (auto-fix, codemod, refactor) can pass all gates while silently changing semantics in code paths the test suite doesn't cover.
-
-**4c. Default checklist items**: See Phase 5.
+**4b. Default checklist items**: See Phase 5.
 
 ### Phase 5: Default Production Checklist
 
@@ -379,7 +357,7 @@ Return complete output contract.
 - Build output analyzed for warnings/deprecations/console.logs (with client/server classification)
 - npm audit executed, vulnerabilities reported by severity, critical/high contribute to hard_fail
 - Unrelated issues discovered and logged
-- Auto, user, and default QA items generated
+- Auto and default QA items generated
 - `hard_fail` flag correctly set
 - **Vitest/Jest/Cargo unit-test hard_fail enforced** when source files changed
 - E2E execution + preflight delegated entirely to `test-e2e-agent` (this agent never runs Playwright/Maestro/wdio/etc.)
@@ -397,4 +375,4 @@ Return complete output contract.
 
 - **Spawned by**: `/cbp-round-execute` Step 5 (per-wave; runs in parallel with `test-e2e-agent` and may also run in parallel with next wave's executor)
 - **Parallel sibling**: `cbp-test-e2e-agent` (fully independent — no cross-read; both agents complete on their own timeline using only their own inputs)
-- **Output consumed by**: `/cbp-round-execute` Step 6 (hard-fail routing — this agent's `totals.hard_fail` is OR'd with `e2e_output.test_results.failed > 0` and `e2e_output.status === 'failed'`), `/cbp-round-end` Step 3a (reads this agent's `user_qa[]` for single-source items: design-source comparison, mechanical-sweep spot-check, connection smoke). Note: round-end Step 3b independently reads `round.context.frontend_ui_review.findings` for cross-source baseline-regression + rendered-visual user_qa — that read is unrelated to this agent's output. The two sub-steps run independently; this agent has zero coupling to frontend-ui findings.
+- **Output consumed by**: `/cbp-round-execute` Step 6 (hard-fail routing — this agent's `totals.hard_fail` is OR'd with `e2e_output.test_results.failed > 0` and `e2e_output.status === 'failed'`), `/cbp-round-end` Step 3 (reads this agent's `auto_qa[]` and `default_checklist[]`). This agent does not emit `user_qa` items; baseline-regression findings surface as a BLOCKING gate at `/cbp-round-end` Step 7 (an explicit accept-or-fix user decision; baselines are NEVER auto-accepted).

package/templates/hooks/README.md

@@ -6,41 +6,33 @@ Hook registration lives in [`hooks/hooks.json`](./hooks.json) — PreToolUse, Po
 
 **`cbp-statusline.sh` is auto-wired via `settings.project.base.json`.** The `statusLine` block is shipped inside `templates/settings.project.base.json` and merged into the consumer's `.claude/settings.json` automatically by `codebyplan claude install` (and on every `codebyplan claude update`). No manual copy-paste is required.
 
+**Multi-runtime renderers.** Both `cbp-statusline.sh` and `cbp-subagent-statusline.sh` are *dispatchers*: each reads a per-device renderer choice and execs a `bash`, `node` (`.mjs`), or `python` (`.py`) variant that produces **byte-identical** output. The selected `.sh` always remains the wired entry point, so the bash renderer is a universal, never-error fallback when the chosen runtime is unavailable. Selection + display options come from two `.codebyplan/` files (see [Statusline configuration](#statusline-configuration) below).
+
 ---
 
 ## Hooks included
 
 ### `cbp-statusline.sh` — auto-registered via `settings.project.base.json`
 
-Renders up to 6 structured lines below Claude Code's prompt area. Reads JSON from stdin (Claude Code's `statusLine` stream) and emits ANSI-coloured output. All fields from the Claude Code `statusLine` schema are parsed in a single `jq` invocation.
+Renders up to 6 structured lines below Claude Code's prompt area. Reads JSON from stdin (Claude Code's `statusLine` stream) and emits ANSI-coloured output. The file is a *dispatcher + bash renderer*: it selects the configured runtime (bash / node / python), execs the matching renderer when available, and otherwise renders inline in bash. The `node` (`cbp-statusline.mjs`) and `python` (`cbp-statusline.py`) variants produce **byte-identical** output.
 
 **Render lines:**
 
-- **Line 1 — Identity**: single prefix (`wt:NAME` / `session:NAME` / `agent:NAME`, priority order); model display name and id; `effort:LEVEL` (when set); `thinking:on` (only when thinking is enabled); `style:NAME` (when output style is not "default"); `v:VERSION`; `[VIM_MODE]`
+- **Line 1 — Identity**: **folder name** (basename of `cwd`) + **git branch** (always shown — taken from `worktree.branch`, else derived via `git -C <cwd> rev-parse --abbrev-ref HEAD`, so it appears even without a registered worktree); single prefix (`wt:NAME` / `session:NAME` / `agent:NAME`, priority order); model **display name only**; `effort:LEVEL` (when set); `thinking:on` (only when thinking is enabled); `style:NAME` (when output style is not "default"); `[VIM_MODE]`
 - **Line 2 — Context**: 20-character progress bar (green / yellow / red at 50% / 75%); `used% / ctx_size`; per-call token breakdown — `in:N out:N cache_cr:N cache_rd:N` (from `context_window.current_usage`); `⚠ 200k+` banner when `exceeds_200k_tokens` is true
 - **Line 3 — Cost**: session cost in USD; total wall duration (`dur:`) and API-only duration (`api:`) via human-readable format; lines added/removed
 - **Line 4 — Rate limits**: `5h: PCT% (resets in Xh)` and `7d: PCT% (resets in Xd)` with relative-time helper; colour-coded green / yellow / red at 60% / 80%; emitted only when at least one window has a non-zero `resets_at` epoch
 - **Line 5 — Repo / PR**: `host/owner/name` (from `workspace.repo`); `PR #N <review_state> <url>` (when `pr.number` is present); emitted when at least one segment is present
 - **Line 6 — Worktree**: `name @ branch (was: original_branch)` and truncated path; emitted only when `worktree.name` is present
 
-**Env-var toggles** — set any to `1` to suppress that section:
-
-| Variable | Suppresses |
-|---|---|
-| `CBP_STATUSLINE_HIDE_IDENTITY` | Line 1 — model / session / agent identity |
-| `CBP_STATUSLINE_HIDE_CONTEXT` | Line 2 — context bar, token breakdown |
-| `CBP_STATUSLINE_HIDE_COST` | Line 3 — cost, duration, lines changed |
-| `CBP_STATUSLINE_HIDE_RATE_LIMITS` | Line 4 — 5h / 7d rate-limit windows |
-| `CBP_STATUSLINE_HIDE_REPO_PR` | Line 5 — repo identity and PR |
-| `CBP_STATUSLINE_HIDE_WORKTREE` | Line 6 — worktree name / branch / path |
-| `CBP_STATUSLINE_NO_COLOR` | Strip all ANSI colour codes (also honoured by `$NO_COLOR`) |
+> **Removed in the multi-runtime rewrite:** the `v:VERSION` field, the `sid:…` session-id field, the `log:…` transcript field, and the redundant model-id-in-parens beside the display name.
 
 **Sample invocation** (pipe mock JSON, run from the hooks directory; `NO_COLOR=1` shown so the comment-output below matches verbatim without ANSI codes):
 
 ```bash
-echo '{"model":{"display_name":"Opus","id":"claude-opus-4"},"context_window":{"used_percentage":25,"context_window_size":200000,"current_usage":{"input_tokens":50000,"output_tokens":1000,"cache_creation_input_tokens":0,"cache_read_input_tokens":0}}}' \
+echo '{"model":{"display_name":"Opus 4.8","id":"claude-opus-4-8[1m]"},"cwd":"/work/myrepo","worktree":{"branch":"feat/x"},"context_window":{"used_percentage":25,"context_window_size":200000,"current_usage":{"input_tokens":50000,"output_tokens":1000,"cache_creation_input_tokens":0,"cache_read_input_tokens":0}}}' \
   | NO_COLOR=1 bash cbp-statusline.sh
-# Opus (claude-opus-4)
+# myrepo ⎇feat/x Opus 4.8
 # ▓▓▓▓▓░░░░░░░░░░░░░░░ 25%/200.0K in:50.0K out:1.0K cache_cr:0 cache_rd:0
 # $0.0000 dur:0s api:0s +0 -0 lines
 ```
@@ -49,7 +41,57 @@ Pure renderer — no project state read, no commands run. Works on any host.
 
 **Blocks vs warns**: neither — it only renders. Cannot fail your workflow.
 
-**Opt out**: set `CBP_STATUSLINE_HIDE_*` env vars to suppress individual sections, or remove the `statusLine` block from your `.claude/settings.json`.
+**Opt out**: hide individual lines via config or `CBP_STATUSLINE_HIDE_*` env vars (see below), or remove the `statusLine` block from your `.claude/settings.json`.
+
+---
+
+### `cbp-subagent-statusline.sh` — auto-registered via `settings.project.base.json`
+
+Renders one row per active subagent task below the main statusline. Reads JSON from stdin (Claude Code's `subagentStatusLine` stream, with a `tasks[]` array) and emits the upstream **JSON-per-line** protocol — one `{"id":…,"content":…}` object per task. Like the main statusline it is a dispatcher with byte-identical `bash` / `node` (`cbp-subagent-statusline.mjs`) / `python` (`cbp-subagent-statusline.py`) renderers. Each row carries a status icon + colour (running `●` / pending `○` / completed `✓` / failed `✗`), name, type, description, `tokens:N`, and `age:X`, ANSI-aware-truncated to the terminal's `columns`.
+
+```bash
+echo '{"columns":0,"tasks":[{"id":"a1","name":"Explorer","type":"general","status":"running","description":"scanning files","startTime":0,"tokenCount":12000}]}' \
+  | NO_COLOR=1 bash cbp-subagent-statusline.sh
+# {"id":"a1","content":"● Explorer (general) — scanning files · tokens:12.0K"}
+```
+
+---
+
+### Statusline configuration
+
+Both statuslines are driven by two `.codebyplan/` files plus environment-variable overrides. Precedence is **env > config > default**.
+
+| File | Scope | Shape | Purpose |
+|---|---|---|---|
+| `.codebyplan/statusline.json` | **committed** (team-shared) | `{ "lines": { "identity", "context", "cost", "rate_limits", "repo_pr", "worktree": bool }, "no_color": bool }` | Which of the 6 main lines render, and whether colour is stripped. All lines default `true`; `no_color` defaults `false`. |
+| `.codebyplan/statusline.local.json` | **gitignored** (per-device) | `{ "renderer": "bash" \| "node" \| "python" }` | Which runtime renders. Per-device because runtime availability is machine-specific. Default `bash`. |
+
+Set or inspect the renderer with the CLI (writes the gitignored local file):
+
+```bash
+codebyplan statusline           # print the current renderer + which runtimes are available
+codebyplan statusline node      # switch this device to the node renderer (or: bash | python)
+codebyplan statusline --python  # flag form is equivalent
+```
+
+The same `--bash` / `--node` / `--python` flags are accepted on `codebyplan claude install` and `codebyplan claude update`, and `codebyplan setup` asks once when the renderer is unset. When the chosen runtime is missing at render time, the statusline silently falls back to bash (it never errors).
+
+**Env-var overrides** — set to `1`; these win over the committed config:
+
+| Variable | Effect |
+|---|---|
+| `CBP_STATUSLINE_HIDE_IDENTITY` | Hide line 1 — folder / branch / model / identity |
+| `CBP_STATUSLINE_HIDE_CONTEXT` | Hide line 2 — context bar, token breakdown |
+| `CBP_STATUSLINE_HIDE_COST` | Hide line 3 — cost, duration, lines changed |
+| `CBP_STATUSLINE_HIDE_RATE_LIMITS` | Hide line 4 — 5h / 7d rate-limit windows |
+| `CBP_STATUSLINE_HIDE_REPO_PR` | Hide line 5 — repo identity and PR |
+| `CBP_STATUSLINE_HIDE_WORKTREE` | Hide line 6 — worktree name / branch / path |
+| `CBP_STATUSLINE_NO_COLOR` | Strip all ANSI colour codes (also honoured by `$NO_COLOR`) |
+| `CBP_SUBAGENT_STATUSLINE_HIDE_DESCRIPTION` | Subagent rows: omit the description segment |
+| `CBP_SUBAGENT_STATUSLINE_HIDE_TOKENS` | Subagent rows: omit the `tokens:N` segment |
+| `CBP_SUBAGENT_STATUSLINE_NO_COLOR` | Subagent rows: strip ANSI colour codes |
+
+The committed `statusline.json` line toggles apply only to the six main-statusline lines; the subagent rows honour only the colour / description / tokens controls above.
 
 ---
 

package/templates/hooks/cbp-statusline.mjs

@@ -0,0 +1,385 @@
+#!/usr/bin/env node
+// @hook: NOT-A-HOOK (statusLine renderer, invoked via the cbp-statusline.sh dispatcher)
+// Claude Code Status Line — node renderer (ESM; .mjs forces ESM regardless of the
+// host repo's package.json "type", so the script is portable into any consumer).
+// Byte-identical output to the bash renderer in cbp-statusline.sh and the python
+// renderer in cbp-statusline.py. See that .sh file for the full option/env/seam
+// contract. Selected via .codebyplan/statusline.local.json -> {"renderer":"node"}.
+//
+// Reads stdin JSON; resolves .codebyplan/ root from CBP_STATUSLINE_ROOT (set by the
+// dispatcher) or argv[2], else the script's ../.. directory. Never throws to stdout.
+
+import fs from "node:fs";
+import path from "node:path";
+import { execFileSync } from "node:child_process";
+import { fileURLToPath } from "node:url";
+
+const __dirname = path.dirname(fileURLToPath(import.meta.url));
+
+function main() {
+  const input = fs.readFileSync(0, "utf8");
+  let data;
+  try {
+    data = JSON.parse(input);
+  } catch {
+    data = {};
+  }
+
+  // ---- Root resolution (matches the dispatcher contract) --------------------
+  let root = process.env.CBP_STATUSLINE_ROOT || process.argv[2] || "";
+  if (!root) {
+    root = path.resolve(__dirname, "..", "..");
+  }
+
+  // ---- jq `//` semantics: default on null/undefined (and false → false) -----
+  const get = (obj, keys, dflt) => {
+    let cur = obj;
+    for (const k of keys) {
+      if (cur == null || typeof cur !== "object") return dflt;
+      cur = cur[k];
+    }
+    return cur == null ? dflt : cur;
+  };
+
+  const MODEL_ID = get(data, ["model", "id"], "");
+  const MODEL_NAME = get(data, ["model", "display_name"], "");
+  const CWD = get(data, ["cwd"], "");
+  const WS_CURRENT_DIR = get(data, ["workspace", "current_dir"], "");
+  const WS_REPO_HOST = get(data, ["workspace", "repo", "host"], "");
+  const WS_REPO_OWNER = get(data, ["workspace", "repo", "owner"], "");
+  const WS_REPO_NAME = get(data, ["workspace", "repo", "name"], "");
+  const COST = get(data, ["cost", "total_cost_usd"], 0);
+  const DURATION = get(data, ["cost", "total_duration_ms"], 0);
+  const API_DURATION = get(data, ["cost", "total_api_duration_ms"], 0);
+  const LINES_ADD = get(data, ["cost", "total_lines_added"], 0);
+  const LINES_DEL = get(data, ["cost", "total_lines_removed"], 0);
+  const CTX_SIZE = get(data, ["context_window", "context_window_size"], 200000);
+  const CTX_PCT = get(data, ["context_window", "used_percentage"], 0);
+  const CUR_IN = get(
+    data,
+    ["context_window", "current_usage", "input_tokens"],
+    0
+  );
+  const CUR_OUT = get(
+    data,
+    ["context_window", "current_usage", "output_tokens"],
+    0
+  );
+  const CACHE_CREATE = get(
+    data,
+    ["context_window", "current_usage", "cache_creation_input_tokens"],
+    0
+  );
+  const CACHE_READ = get(
+    data,
+    ["context_window", "current_usage", "cache_read_input_tokens"],
+    0
+  );
+  const EXCEEDS_200K = get(data, ["exceeds_200k_tokens"], false);
+  const EFFORT = get(data, ["effort", "level"], "");
+  const THINKING = get(data, ["thinking", "enabled"], false);
+  const RATE_5H_PCT = get(
+    data,
+    ["rate_limits", "five_hour", "used_percentage"],
+    ""
+  );
+  const RATE_5H_RESETS = get(
+    data,
+    ["rate_limits", "five_hour", "resets_at"],
+    0
+  );
+  const RATE_7D_PCT = get(
+    data,
+    ["rate_limits", "seven_day", "used_percentage"],
+    ""
+  );
+  const RATE_7D_RESETS = get(
+    data,
+    ["rate_limits", "seven_day", "resets_at"],
+    0
+  );
+  const SESSION_NAME = get(data, ["session_name"], "");
+  const OUTPUT_STYLE = get(data, ["output_style", "name"], "");
+  const VIM_MODE = get(data, ["vim", "mode"], "");
+  const AGENT_NAME = get(data, ["agent", "name"], "");
+  const PR_NUMBER = get(data, ["pr", "number"], "");
+  const PR_URL = get(data, ["pr", "url"], "");
+  const PR_REVIEW_STATE = get(data, ["pr", "review_state"], "");
+  const WT_NAME = get(data, ["worktree", "name"], "");
+  const WT_PATH = get(data, ["worktree", "path"], "");
+  const WT_BRANCH = get(data, ["worktree", "branch"], "");
+  const WT_ORIG_BRANCH = get(data, ["worktree", "original_branch"], "");
+
+  // ---- Config: line toggles + no_color --------------------------------------
+  const cfg = {
+    identity: true,
+    context: true,
+    cost: true,
+    rate_limits: true,
+    repo_pr: true,
+    worktree: true,
+    no_color: false,
+  };
+  try {
+    const raw = fs.readFileSync(
+      path.join(root, ".codebyplan", "statusline.json"),
+      "utf8"
+    );
+    const parsed = JSON.parse(raw);
+    if (parsed && typeof parsed === "object") {
+      if (typeof parsed.no_color === "boolean") cfg.no_color = parsed.no_color;
+      if (parsed.lines && typeof parsed.lines === "object") {
+        for (const k of [
+          "identity",
+          "context",
+          "cost",
+          "rate_limits",
+          "repo_pr",
+          "worktree",
+        ]) {
+          if (typeof parsed.lines[k] === "boolean") cfg[k] = parsed.lines[k];
+        }
+      }
+    }
+  } catch {
+    // absent / invalid → keep defaults
+  }
+
+  // env HIDE=1 > config false > default show
+  const shouldShow = (envSuffix, cfgValue) => {
+    if (process.env[`CBP_STATUSLINE_HIDE_${envSuffix}`] === "1") return false;
+    if (cfgValue === false) return false;
+    return true;
+  };
+
+  // ---- Colour setup (env > config) ------------------------------------------
+  const noColor =
+    (process.env.NO_COLOR != null && process.env.NO_COLOR !== "") ||
+    process.env.CBP_STATUSLINE_NO_COLOR === "1" ||
+    cfg.no_color === true;
+  const C = noColor
+    ? {
+        RST: "",
+        DIM: "",
+        BOLD: "",
+        GREEN: "",
+        YELLOW: "",
+        RED: "",
+        CYAN: "",
+        MAGENTA: "",
+        BLUE: "",
+      }
+    : {
+        RST: "\x1b[0m",
+        DIM: "\x1b[2m",
+        BOLD: "\x1b[1m",
+        GREEN: "\x1b[32m",
+        YELLOW: "\x1b[33m",
+        RED: "\x1b[31m",
+        CYAN: "\x1b[36m",
+        MAGENTA: "\x1b[35m",
+        BLUE: "\x1b[34m",
+      };
+
+  // ---- Numeric helpers (integer round-half-up; cross-runtime identical) ------
+  const numStr = (n) => {
+    const x = Number(n);
+    if (Number.isFinite(x) && Number.isInteger(x)) return String(x);
+    return String(n);
+  };
+
+  const fmtK = (val) => {
+    const v = Number(val);
+    if (v >= 1000000) {
+      const t = Math.floor((v + 50000) / 100000);
+      return `${Math.floor(t / 10)}.${t % 10}M`;
+    } else if (v >= 1000) {
+      const t = Math.floor((v + 50) / 100);
+      return `${Math.floor(t / 10)}.${t % 10}K`;
+    }
+    return String(Math.trunc(v));
+  };
+
+  const fmtCost = (c) => {
+    const n = Math.floor(Number(c) * 10000 + 0.5);
+    const frac = String(n % 10000).padStart(4, "0");
+    return `$${Math.floor(n / 10000)}.${frac}`;
+  };
+
+  const fmtDur = (ms) => {
+    const secs = Math.trunc(Number(ms) / 1000);
+    if (secs >= 3600)
+      return `${Math.floor(secs / 3600)}h${Math.floor((secs % 3600) / 60)}m`;
+    if (secs >= 60) return `${Math.floor(secs / 60)}m${secs % 60}s`;
+    return `${secs}s`;
+  };
+
+  const cbpNow = () => {
+    if (
+      process.env.CBP_STATUSLINE_NOW != null &&
+      process.env.CBP_STATUSLINE_NOW !== ""
+    ) {
+      return Math.trunc(Number(process.env.CBP_STATUSLINE_NOW));
+    }
+    return Math.floor(Date.now() / 1000);
+  };
+
+  const fmtRelTime = (epoch) => {
+    const delta = Math.trunc(Number(epoch)) - cbpNow();
+    if (delta <= 0) return "now";
+    if (delta >= 86400) return `${Math.floor(delta / 86400)}d`;
+    if (delta >= 3600) return `${Math.floor(delta / 3600)}h`;
+    return `${Math.floor(delta / 60)}m`;
+  };
+
+  const gte = (v, t) => Number(v) >= t;
+
+  // ---- Folder + branch ------------------------------------------------------
+  let FOLDER = "";
+  if (CWD) FOLDER = path.basename(CWD);
+  else if (WS_CURRENT_DIR) FOLDER = path.basename(WS_CURRENT_DIR);
+  let BRANCH = WT_BRANCH;
+  if (!BRANCH && CWD) {
+    try {
+      BRANCH = execFileSync(
+        "git",
+        ["-C", CWD, "rev-parse", "--abbrev-ref", "HEAD"],
+        {
+          encoding: "utf8",
+          stdio: ["ignore", "pipe", "ignore"],
+        }
+      ).replace(/\s+$/, "");
+    } catch {
+      BRANCH = "";
+    }
+  }
+
+  const out = [];
+
+  // ============================================================
+  // LINE 1 — Identity
+  // ============================================================
+  if (shouldShow("IDENTITY", cfg.identity)) {
+    let L1 = "";
+    if (FOLDER) {
+      L1 = `${C.BOLD}${C.BLUE}${FOLDER}${C.RST}`;
+      if (BRANCH) L1 += ` ${C.DIM}⎇${C.RST}${C.CYAN}${BRANCH}${C.RST}`;
+      L1 += " ";
+    }
+    if (WT_NAME) {
+      L1 += `${C.DIM}wt:${C.RST}${C.MAGENTA}${WT_NAME}${C.RST} `;
+    } else if (SESSION_NAME) {
+      L1 += `${C.DIM}session:${C.RST}${C.MAGENTA}${SESSION_NAME}${C.RST} `;
+    } else if (AGENT_NAME) {
+      L1 += `${C.DIM}agent:${C.RST}${C.MAGENTA}${AGENT_NAME}${C.RST} `;
+    }
+    if (MODEL_NAME) {
+      L1 += `${C.BOLD}${C.CYAN}${MODEL_NAME}${C.RST}`;
+    } else if (MODEL_ID) {
+      L1 += `${C.BOLD}${C.CYAN}${MODEL_ID}${C.RST}`;
+    }
+    if (EFFORT) L1 += ` ${C.DIM}effort:${C.RST}${EFFORT}`;
+    if (THINKING === true) L1 += ` ${C.YELLOW}thinking:on${C.RST}`;
+    if (OUTPUT_STYLE && OUTPUT_STYLE !== "default")
+      L1 += ` ${C.DIM}style:${C.RST}${OUTPUT_STYLE}`;
+    if (VIM_MODE) L1 += ` ${C.DIM}[${VIM_MODE}]${C.RST}`;
+    if (L1) out.push(L1);
+  }
+
+  // ============================================================
+  // LINE 2 — Context window
+  // ============================================================
+  if (shouldShow("CONTEXT", cfg.context)) {
+    let barColor;
+    if (gte(CTX_PCT, 75)) barColor = C.RED;
+    else if (gte(CTX_PCT, 50)) barColor = C.YELLOW;
+    else barColor = C.GREEN;
+
+    let filled = Math.floor((Math.trunc(Number(CTX_PCT)) + 4) / 5);
+    if (filled > 20) filled = 20;
+    const empty = 20 - filled;
+    const bar = "▓".repeat(filled) + "░".repeat(empty);
+
+    let L2 = `${barColor}${bar}${C.RST} ${barColor}${numStr(CTX_PCT)}%${C.RST}${C.DIM}/${fmtK(CTX_SIZE)}${C.RST}`;
+    L2 += ` ${C.DIM}in:${C.RST}${C.BLUE}${fmtK(CUR_IN)}${C.RST} ${C.DIM}out:${C.RST}${C.MAGENTA}${fmtK(CUR_OUT)}${C.RST} ${C.DIM}cache_cr:${C.RST}${fmtK(CACHE_CREATE)} ${C.DIM}cache_rd:${C.RST}${fmtK(CACHE_READ)}`;
+    if (EXCEEDS_200K === true) L2 += ` ${C.YELLOW}⚠ 200k+${C.RST}`;
+    out.push(L2);
+  }
+
+  // ============================================================
+  // LINE 3 — Cost
+  // ============================================================
+  if (shouldShow("COST", cfg.cost)) {
+    const L3 = `${C.GREEN}${fmtCost(COST)}${C.RST} ${C.DIM}dur:${C.RST}${fmtDur(DURATION)} ${C.DIM}api:${C.RST}${fmtDur(API_DURATION)} ${C.GREEN}+${numStr(LINES_ADD)}${C.RST} ${C.RED}-${numStr(LINES_DEL)}${C.RST} ${C.DIM}lines${C.RST}`;
+    out.push(L3);
+  }
+
+  // ============================================================
+  // LINE 4 — Rate limits
+  // ============================================================
+  if (shouldShow("RATE_LIMITS", cfg.rate_limits)) {
+    const has5h = RATE_5H_PCT !== "" && String(RATE_5H_RESETS) !== "0";
+    const has7d = RATE_7D_PCT !== "" && String(RATE_7D_RESETS) !== "0";
+    if (has5h || has7d) {
+      let L4 = "";
+      if (has5h) {
+        let c5;
+        if (gte(RATE_5H_PCT, 80)) c5 = C.RED;
+        else if (gte(RATE_5H_PCT, 60)) c5 = C.YELLOW;
+        else c5 = C.GREEN;
+        L4 = `${C.DIM}5h:${C.RST}${c5}${numStr(RATE_5H_PCT)}%${C.RST} ${C.DIM}(resets in ${fmtRelTime(RATE_5H_RESETS)})${C.RST}`;
+      }
+      if (has7d) {
+        let c7;
+        if (gte(RATE_7D_PCT, 80)) c7 = C.RED;
+        else if (gte(RATE_7D_PCT, 60)) c7 = C.YELLOW;
+        else c7 = C.GREEN;
+        const seg7 = `${C.DIM}7d:${C.RST}${c7}${numStr(RATE_7D_PCT)}%${C.RST} ${C.DIM}(resets in ${fmtRelTime(RATE_7D_RESETS)})${C.RST}`;
+        L4 = L4 ? `${L4} ${C.DIM}|${C.RST} ${seg7}` : seg7;
+      }
+      out.push(L4);
+    }
+  }
+
+  // ============================================================
+  // LINE 5 — Repo / PR
+  // ============================================================
+  if (shouldShow("REPO_PR", cfg.repo_pr)) {
+    let L5 = "";
+    if (WS_REPO_HOST) {
+      L5 = `${C.DIM}${WS_REPO_HOST}/${WS_REPO_OWNER}/${WS_REPO_NAME}${C.RST}`;
+    }
+    if (PR_NUMBER !== "") {
+      let prSeg = `${C.DIM}PR${C.RST} ${C.CYAN}#${numStr(PR_NUMBER)}${C.RST}`;
+      if (PR_REVIEW_STATE) prSeg += ` ${C.DIM}${PR_REVIEW_STATE}${C.RST}`;
+      if (PR_URL) prSeg += ` ${C.BLUE}${PR_URL}${C.RST}`;
+      L5 = L5 ? `${L5} ${C.DIM}|${C.RST} ${prSeg}` : prSeg;
+    }
+    if (L5) out.push(L5);
+  }
+
+  // ============================================================
+  // LINE 6 — Worktree
+  // ============================================================
+  if (shouldShow("WORKTREE", cfg.worktree)) {
+    if (WT_NAME) {
+      let L6 = `${C.MAGENTA}${WT_NAME}${C.RST} ${C.DIM}@${C.RST} ${C.CYAN}${WT_BRANCH}${C.RST}`;
+      if (WT_ORIG_BRANCH && WT_ORIG_BRANCH !== WT_BRANCH) {
+        L6 += ` ${C.DIM}(was: ${WT_ORIG_BRANCH})${C.RST}`;
+      }
+      let wtPathDisp = WT_PATH;
+      if (WT_PATH.length > 60) wtPathDisp = "..." + WT_PATH.slice(-57);
+      L6 += ` ${C.DIM}${wtPathDisp}${C.RST}`;
+      out.push(L6);
+    }
+  }
+
+  process.stdout.write(out.length ? out.join("\n") + "\n" : "");
+}
+
+try {
+  main();
+} catch {
+  // Statusline must never error to stdout.
+  process.exit(0);
+}