@haposoft/cafekit 0.16.7 → 0.18.1

package/README.md

@@ -2,7 +2,7 @@
 
 > Native spec-driven workflow and runtime bundle for Claude Code and Codex CLI.
 
-[![Version](https://img.shields.io/badge/version-0.16.7-blue.svg)](https://github.com/haposoft/cafekit)
+[![Version](https://img.shields.io/badge/version-0.18.1-blue.svg)](https://github.com/haposoft/cafekit)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 [![Claude%20Code](https://img.shields.io/badge/Claude%20Code-Native-orange.svg)](https://claude.ai/code)
 [![Codex%20CLI](https://img.shields.io/badge/Codex%20CLI-Native-111111.svg)](https://developers.openai.com/codex)
@@ -147,6 +147,13 @@ cat .codex/cafekit.json
 The Claude statusline reads three keys from `.claude/runtime.json`:
 
 - `"statusline"`: render mode — `full` (default), `compact`, `minimal`, or `none`.
+  The default is one line, `◆ model (effort) ϟ✱  ◔ context%  ⧗ 5h quota% reset  ◷ weekly%  ⎇ branch ●changed ↑↓ #PR✓ ⊟  ± +added/-removed  ⏱ session  ↻ cache hit%`
+  (`ϟ` fast mode, `✱` thinking, `#PR` with ✓ approved / ✗ changes requested, `⊟` inside a git worktree;
+  each appears only when present), which drops cache, session time, changes, weekly, quota, then the
+  branch as the terminal narrows. Quota comes only from the `rate_limits` Claude Code sends (Pro/Max,
+  after a session's first API response); without it the quota segments are hidden. `full` adds
+  agent and todo lines only while they exist, `compact` is the line alone, and `minimal`
+  keeps model, context and branch.
 - `statuslineColors`: set `false` to disable ANSI colors (`NO_COLOR` also wins).
 - `statuslineLayout`: optional custom layout. Global shape
   `{ "lines": [["model", "context"], ["directory", "git"]] }` — each inner
@@ -156,8 +163,8 @@ The Claude statusline reads three keys from `.claude/runtime.json`:
   ids are ignored; an empty or invalid layout falls back to the default
   renderers, and leaving the key out keeps the default output unchanged. The
   `cost` section renders only when enabled here, billing mode is API, and cost
-  data exists. Quota shows five-hour and weekly windows only while the usage
-  cache is fresh.
+  data exists. Quota shows five-hour and weekly windows only while Claude Code
+  sends `rate_limits`. The `usage` key is deprecated and has no effect.
 
 ## Core Skills
 
@@ -167,8 +174,6 @@ CafeKit ships many skills, but the main release surface is:
 - `/cf:scout <search-target>`: discover relevant files locally first, delegating only for permitted broad independent scopes
 - `/cf:brainstorm <idea-or-problem>`: scout the repo, clarify exact requirements, compare approaches, and hand off to specs
 - `/cf:research <decision>`: choose proportional depth and return traceable evidence for an uncertain technical decision
-- `/cf:route <material-request>`: classify ambiguous, multi-step, multi-domain, or elevated-risk work and compose the shortest valid installed chain
-- `/cf:loop <bounded-experiment>`: run explicit-only numeric optimization in an isolated worktree and return a base-bound patch handoff
 - `/cf:orca <orca-request>`: inside an Orca (onorca.dev) pane, route a request to read, wait on, or send to another agent pane, or spawn one into a worktree
 - `/cf:specs <feature-description>`: create or resume a structured spec workflow
 - `/cf:develop <feature-name>`: implement from approved spec artifacts
@@ -194,7 +199,7 @@ completes work. Chat is the default output. A durable file needs explicit user
 authority, and no Brainstorm output is live proof or Specs/Develop approval or
 execution authority.
 
-### Adaptive Research and bounded Loop
+### Adaptive Research
 
 Use `/cf:research` when the result is a decision: Quick, Standard, or Deep
 research binds material claims to a URL or repository anchor, authority,
@@ -202,18 +207,9 @@ date/version, applicability, and `confirmed`, `inferred`, or `unresolved`
 state. Research returns evidence and tradeoffs; it does not implement the
 recommendation or guarantee correctness.
 
-Use `/cf:loop` only by explicit request and only after its preflight freezes
-Goal, isolated Scope, finite numeric Metric and Direction, reproducible
-Baseline, distinct Guard, noise policy and minimum delta, budget, and stop
-conditions. Each iteration stays in a detached worktree. The result is a
-base-bound isolated patch handoff, never an automatic apply, commit, push, or
-guarantee of improvement.
-
 ```text
 /cf:research Compare current local-first search libraries for this repository
-/cf:loop Goal="reduce parser latency" Scope="packages/parser" Metric="median ms, lower" Baseline="pinned base" Guard="npm test" Noise="MAD; minimum delta 2%" Budget="10 iterations" Stop="budget, drift, or failed guard"
 $cf-research Compare current local-first search libraries for this repository
-$cf-loop Goal="reduce parser latency" Scope="packages/parser" Metric="median ms, lower" Baseline="pinned base" Guard="npm test" Noise="MAD; minimum delta 2%" Budget="10 iterations" Stop="budget, drift, or failed guard"
 ```
 
 Optional document skills are `docs`, `docx`, `pdf`, `pptx`, `xlsx`, and
@@ -244,7 +240,7 @@ node .claude/scripts/generate-skill-catalog.cjs --skills
 Routing uses progressive disclosure: live catalog metadata selects a candidate,
 the selected `SKILL.md` supplies its contract, and only relevant references are
 loaded. Invoke an installed skill directly for explicit or obvious low-risk
-work; use `cf:route` only when classification or chaining is material. When a
+work; compose a short chain only when classification or chaining is material. When a
 capability or agent is absent, continue inline when safe or name the gap.
 Hooks are not a skill router and never grant capability presence or authority. Source
 and installed projections are verified; live-model adherence remains
@@ -310,17 +306,13 @@ specs/<feature-name>/
 ```
 
 The process-first workflow has three human decision gates. `cf:specs` opens
-C1 to fix scope before authoring and C2 to resolve adversarial findings, then
+GATE-SCOPE to fix scope before authoring and GATE-REVIEW to resolve adversarial findings, then
 stops. A later explicit `cf:develop` invocation executes the tasks and
-presents C3 for closeout only after real execution proof. Each task has one
+presents GATE-DONE for closeout only after real execution proof. Each task has one
 `Status:` field and keeps its canonical `## Receipt` inline, including the
 exact Verification Plan command, `Exit: 0`, `Verification: PASS`,
 runtime-derived Base and Head, and current command output.
 
-Existing packets with `spec.json`, nested `tasks/task-R*.md`, or separate
-receipts remain supported through the legacy compatibility adapter. New Specs
-work does not author those legacy artifacts.
-
 ## Development
 
 Run package self-tests:

package/bin/__tests__/codex-hooks-ownership.test.js

@@ -136,8 +136,8 @@ test('repeated installs never duplicate a CafeKit hook', () => {
     const config = readHooks(root);
     assert.equal(allHandlers(config).length, afterFirst, 'a reinstall added handlers that were already registered');
 
-    // Uniqueness is per event, not global: state.cjs and completion-authority.cjs each
-    // register under several events by design.
+    // Uniqueness is per event, not global: state.cjs registers under several events by
+    // design.
     for (const [eventName, groups] of Object.entries(config.hooks)) {
       const scripts = groups
         .flatMap((group) => group.hooks || [])