baldart 4.49.1 → 4.50.0

package/CHANGELOG.md

@@ -5,6 +5,17 @@ All notable changes to BALDART will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [4.50.0] - 2026-06-17
+
+**BALDART ships a `Terse` Claude Code output style as a latent, opt-in deliverable — installed with every Claude-enabled consumer, activated only by the user.** Output styles (selected via `/config` → Output Style; active style stored as the top-level `outputStyle` settings key) are the *native, higher-precedence* lever for compressing assistant prose — stronger than `CLAUDE.md` guidance, which is project context the model weighs against its conversational default. The new `framework/.claude/output-styles/terse.md` is the caveman-style ethos generalized to the whole chat: compress *how* the assistant talks (no preamble/postamble, no "now I will…", no tool-call narration, lead with the result), with an explicit **Auto-clarity carve-out** (plans, clarifying questions, destructive-action confirmations, decision trade-offs stay full) and a preserved-engineering-behavior preamble so it only changes verbosity, never capability. Distribution reuses the v4.14.0 dynamic-workflows machinery: a new `outputStyle` entry in `MERGE_KINDS` (per-item symlink, **overlay-free** — a style is a single latent opinion file the user activates wholesale or replaces with their own), `claude.js` exposes `outputStylesDir()`, `codex.js` returns `null` (**Claude-only** — Codex has no output styles). Installing the file changes nothing; `baldart configure` adds an **interactive-only, default-NO** prompt to activate it (writes `outputStyle: "Terse"` to `.claude/settings.local.json` — personal, gitignored, never forced on the team). **MINOR** (additive payload type + CLI capability; **no new `baldart.config.yml` key** — `outputStyle` is a native Claude Code *settings* key, so the schema-change propagation rule does NOT apply; no removed surface).
+
+### Added
+
+- **`framework/.claude/output-styles/terse.md`** — the `Terse` output style (frontmatter `name: Terse`): prose-only terseness with an Auto-clarity carve-out, preserving all software-engineering behavior.
+- **`src/utils/symlinks.js`** — `outputStyle` kind in `MERGE_KINDS` + `mergeOutputStyles()` wrapper, wired into `createAllSymlinks()` and the install-validation reconcile loop. `_mergeBulkDir` generalized with an optional `srcDir` field (defaults to `<kind>s`) so the hyphenated `output-styles/` source dir Claude Code requires resolves correctly (the kind name `outputStyle` would otherwise pluralize to the wrong `outputStyles/`).
+- **`src/utils/tool-adapters/{claude,codex}.js`** — `outputStylesDir()` (`.claude/output-styles` for Claude; `null` for Codex).
+- **`src/commands/configure.js`** — `maybeActivateTerseOutputStyle()`: interactive-only, default-NO prompt to activate the style by writing `outputStyle: "Terse"` to `.claude/settings.local.json`; no-ops when the file is absent (Codex-only / older framework) or already active. New NEXT STEPS line pointing to `/config` → Output Style.
+
 ## [4.49.1] - 2026-06-17
 
 **The four `/new` dynamic workflows shed their paragraph-length `meta.description` — the last prose that re-entered the orchestrator context on every workflow completion.** The `Workflow` tool contract specifies `description` as a *one-line* field shown in the permission dialog, but `new-card-review` / `new-final-review` / `new2` / `new2-resolve` each carried a full-paragraph rationale (~150–230 words) that the runtime echoes back into the orchestrator prefix on the completion line — pure prose with zero runtime value (the orchestrator already knows what it invoked). Each is collapsed to a single line; the full semantics were already duplicated in the script's own args-contract comment block (source code, never injected into context) plus the `references/*.md` SSOT, so nothing is lost. Same family as the v4.49.0 prose-leak closures, applied to the workflow layer. **PATCH** (no behaviour change — descriptions are display/permission-dialog text only; **no new `baldart.config.yml` key**).

package/README.md

@@ -358,6 +358,7 @@ your-project/
 │   ├── commands/           # Symlink → .framework/.claude/commands/
 │   ├── skills/             # Per-item merge dir (v2.1.1+): framework symlinks alongside your own skills
 │   ├── workflows/          # Per-item symlinks of framework dynamic workflows (v4.14.0+, Claude-only)
+│   ├── output-styles/      # Per-item symlinks of framework output styles (v4.50.0+, Claude-only; latent — activate via /config)
 │   └── hooks/              # Customizable copies
 ├── baldart.config.yml      # Project context: paths/identity/stack/features (v3.0.0+)
 ├── .baldart/
@@ -447,6 +448,7 @@ Files with symlinks auto-update when framework updates:
 - `.claude/agents/`
 - `.claude/commands/`
 - `.claude/workflows/` (v4.14.0+) — framework dynamic workflows, per-item symlinks (Claude-only; no Codex equivalent)
+- `.claude/output-styles/` (v4.50.0+) — framework output styles, per-item symlinks (Claude-only; latent — installs without activating, toggle via `/config` → Output Style)
 
 Files managed by the CLI:
 

package/VERSION

@@ -1 +1 @@
-4.49.1
+4.50.0

package/framework/.claude/output-styles/terse.md

@@ -0,0 +1,27 @@
+---
+name: Terse
+description: Caveman-style terseness — compress how the assistant talks (prose only), leaving reasoning and engineering behavior untouched, with an Auto-clarity carve-out for decision-grade content.
+---
+
+You are an interactive CLI tool that helps users with software engineering tasks. Keep ALL of your software-engineering capabilities, tool use, and safety behavior exactly as in the default — this style changes ONLY how much prose you emit to the user, never what you do.
+
+## Communication style — terse
+
+Compress *how* you talk, never *what* you do. Reasoning and work stay full; only the user-facing prose is lean.
+
+- No preamble or postamble. Do not open with "Sure!"/"Great question" or close with "Let me know if…"/"Hope this helps"/"In summary". Answer directly.
+- No narration of intent ("now I will…", "let me…") and no recap of what a tool just did or what an agent is doing. When you have enough to act, act.
+- Lead with the result; add context only if asked or if it changes the decision. Don't survey options you won't pursue — give a recommendation.
+- Report outcomes faithfully and compactly: `path:line`, error strings verbatim, exit codes — no prose wrapped around them.
+- Default to a few words or a short sentence over a paragraph; use a list only when the user needs several discrete items.
+
+## Auto-clarity (carve-out — do NOT compress)
+
+Content a human reads in order to *decide* stays full and clear:
+
+- clarifying questions, plans / plan-mode output,
+- confirmations of irreversible or destructive actions,
+- explanations the user explicitly asked for,
+- any trade-off where you expect the user to choose.
+
+Terseness removes noise, never decision-grade substance. When in doubt about whether something is decision-grade, keep it clear.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "baldart",
-  "version": "4.49.1",
+  "version": "4.50.0",
   "description": "Claude Agent Framework - Reusable framework for coordinating AI agents and humans in software projects",
   "bin": {
     "baldart": "./bin/baldart.js"

package/src/commands/configure.js

@@ -1118,6 +1118,51 @@ function serialize(config) {
   return header + yaml.dump(clean, { lineWidth: 100, noRefs: true });
 }
 
+/**
+ * Offer to activate the framework-shipped `Terse` output style (v4.50.0+).
+ *
+ * The style FILE is installed latently by the symlink layer (`.claude/output-styles/terse.md`)
+ * with every install — installing it changes nothing on its own. ACTIVATION, by contrast,
+ * changes how every chat in the repo is phrased, so it is strictly opt-in: interactive only,
+ * default NO, and written to `.claude/settings.local.json` (personal, gitignored — never forced
+ * on the team via the committed `.claude/settings.json`). The active style is the top-level
+ * `outputStyle` string key Claude Code reads (defaulting to "default").
+ *
+ * No-ops silently when the style file is absent (older framework / Codex-only install) or when
+ * the style is already active.
+ */
+async function maybeActivateTerseOutputStyle(cwd) {
+  const styleFile = path.join(cwd, '.claude', 'output-styles', 'terse.md');
+  if (!fs.existsSync(styleFile)) return; // not shipped / not linked — nothing to offer
+
+  const localPath = path.join(cwd, '.claude', 'settings.local.json');
+  const sharedPath = path.join(cwd, '.claude', 'settings.json');
+  const readJson = (p) => {
+    try { return JSON.parse(fs.readFileSync(p, 'utf8')); } catch { return null; }
+  };
+  const local = readJson(localPath) || {};
+  const shared = readJson(sharedPath) || {};
+  const active = local.outputStyle || shared.outputStyle || 'default';
+  if (active === 'Terse') {
+    UI.info('Output style "Terse" is already active.');
+    return;
+  }
+
+  const enable = await UI.confirm(
+    'Activate the "Terse" output style now? (compresses assistant prose only — reasoning/work unchanged; toggle later via /config)',
+    false
+  );
+  if (!enable) {
+    UI.info('Left output style as-is. The "Terse" style stays available — activate it any time via /config → Output Style.');
+    return;
+  }
+
+  local.outputStyle = 'Terse';
+  fs.mkdirSync(path.dirname(localPath), { recursive: true });
+  fs.writeFileSync(localPath, `${JSON.stringify(local, null, 2)}\n`, 'utf8');
+  UI.success('Activated "Terse" output style (.claude/settings.local.json). Restart Claude Code or /clear to apply.');
+}
+
 async function configure(opts = {}) {
   const cwd = process.cwd();
   UI.header('BALDART CONFIGURE — project context');
@@ -1211,10 +1256,16 @@ async function configure(opts = {}) {
     UI.success(`Created ${OVERLAYS_DIR}/`);
   }
 
+  // v4.50.0+: offer to turn on the latent "Terse" output style (interactive only).
+  if (!opts.nonInteractive) {
+    await maybeActivateTerseOutputStyle(cwd);
+  }
+
   UI.box('NEXT STEPS', [
     '• Review baldart.config.yml — values are committed to your repo',
     '• Author skill overlays in .baldart/overlays/<skill-name>.md',
     '  Examples: framework/templates/overlays/',
+    '• Output style "Terse" available — toggle via /config → Output Style',
     '• Re-run `npx baldart configure` any time to refresh',
   ]);
 }

package/src/commands/update.js

@@ -1181,6 +1181,7 @@ async function update(options = {}, unknownArgs = []) {
       symlinks.mergeAgents({ tools: enabledTools });
       symlinks.mergeCommands({ tools: enabledTools });
       symlinks.mergeWorkflows({ tools: enabledTools });
+      symlinks.mergeOutputStyles({ tools: enabledTools });
     }
 
     // Routines wizard (since v2.1.0) — surfaces routines added in the new framework version

package/src/utils/symlinks.js

@@ -19,13 +19,21 @@ const CONFLICT_LOG = path.join('.baldart', 'skill-conflicts.json');
 //   - ext:       the file extension of the source items.
 //   - overlay:   whether the base+overlay generation path applies. Overlays
 //     are a markdown construct (`## [OVERRIDE]` sections + HTML-comment
-//     marker), so they only make sense for `.md` kinds. Workflows are `.js`
-//     and are distributed as plain per-item symlinks — no overlay.
+//     marker). Workflows are `.js` so they can't carry overlays. Output styles
+//     ARE `.md` but are still distributed overlay-free (`overlay: false`): a
+//     style is a single latent opinion file the user activates wholesale via
+//     `/config` or replaces by dropping their own file in the same dir — there
+//     is no per-section merge to do.
 //   - exclude:   filenames in the source dir that are NOT installable items.
+//   - srcDir:    framework source subdir under `.framework/framework/.claude/`.
+//     Defaults to `<kind>s` (agents/commands/workflows). Set explicitly when the
+//     kind name doesn't pluralize to the on-disk dir — e.g. `outputStyle` lives in
+//     the hyphenated `output-styles/` dir Claude Code requires, not `outputStyles/`.
 const MERGE_KINDS = {
-  agent:    { dirGetter: 'agentsDir',    ext: '.md', overlay: true,  exclude: new Set(['REGISTRY.md']) },
-  command:  { dirGetter: 'commandsDir',  ext: '.md', overlay: true,  exclude: new Set(['REGISTRY.md']) },
-  workflow: { dirGetter: 'workflowsDir', ext: '.js', overlay: false, exclude: new Set() },
+  agent:       { dirGetter: 'agentsDir',       ext: '.md', overlay: true,  exclude: new Set(['REGISTRY.md']) },
+  command:     { dirGetter: 'commandsDir',     ext: '.md', overlay: true,  exclude: new Set(['REGISTRY.md']) },
+  workflow:    { dirGetter: 'workflowsDir',    ext: '.js', overlay: false, exclude: new Set() },
+  outputStyle: { dirGetter: 'outputStylesDir', ext: '.md', overlay: false, exclude: new Set(), srcDir: 'output-styles' },
 };
 
 /**
@@ -345,6 +353,10 @@ class SymlinkUtils {
     UI.section('Merging Framework Workflows');
     this.mergeWorkflows({ tools: opts.tools });
 
+    UI.newline();
+    UI.section('Merging Framework Output Styles');
+    this.mergeOutputStyles({ tools: opts.tools });
+
     UI.newline();
   }
 
@@ -360,6 +372,7 @@ class SymlinkUtils {
   mergeAgents(opts = {}) { return this._mergeBulkDir('agent', opts); }
   mergeCommands(opts = {}) { return this._mergeBulkDir('command', opts); }
   mergeWorkflows(opts = {}) { return this._mergeBulkDir('workflow', opts); }
+  mergeOutputStyles(opts = {}) { return this._mergeBulkDir('outputStyle', opts); }
 
   /**
    * Generic per-item merge for kinds whose framework source is a directory
@@ -377,7 +390,8 @@ class SymlinkUtils {
     const aggregate = { linked: [], generated: [], skipped: [], conflicts: [], warnings: [] };
     const { getAdapter } = require('./tool-adapters');
 
-    const fwSourceDir = path.join(this.cwd, FRAMEWORK_PAYLOAD, '.claude', `${kind}s`);
+    const srcDirName = cfg.srcDir || `${kind}s`;
+    const fwSourceDir = path.join(this.cwd, FRAMEWORK_PAYLOAD, '.claude', srcDirName);
     if (!fs.existsSync(fwSourceDir)) {
       UI.warning(`No framework ${kind}s found at ${path.relative(this.cwd, fwSourceDir)}. Skipping ${kind} merge.`);
       return aggregate;
@@ -405,7 +419,7 @@ class SymlinkUtils {
         // portable if the project gets moved.
         const linkDepth = targetRel.split(path.sep).filter(Boolean).length;
         const upPath = path.join(...Array(linkDepth).fill('..'));
-        const target = path.join(upPath, FRAMEWORK_PAYLOAD, '.claude', `${kind}s`, filename);
+        const target = path.join(upPath, FRAMEWORK_PAYLOAD, '.claude', srcDirName, filename);
 
         const overlayRel = path.join('.baldart', 'overlays', `${kind}s`, filename);
         const overlayAbs = path.join(this.cwd, overlayRel);
@@ -676,7 +690,8 @@ class SymlinkUtils {
 
       // v3.8.0+: agents and commands also use per-item merge with overlay support.
       // v4.14.0+: workflows (.js) use the same per-item merge, overlay-free.
-      for (const [kindGetter, kindLabel] of [['agentsDir', 'agents'], ['commandsDir', 'commands'], ['workflowsDir', 'workflows']]) {
+      // v4.50.0+: output styles (.md) use the same per-item merge, overlay-free.
+      for (const [kindGetter, kindLabel] of [['agentsDir', 'agents'], ['commandsDir', 'commands'], ['workflowsDir', 'workflows'], ['outputStylesDir', 'output styles']]) {
         if (typeof adapter[kindGetter] !== 'function') continue;
         const rel = adapter[kindGetter]();
         if (!rel) continue;

package/src/utils/tool-adapters/claude.js

@@ -6,6 +6,7 @@
  *   - `.claude/agents/<agent>.md`                 (subagents, bulk symlink)
  *   - `.claude/commands/<command>.md`             (slash commands, bulk symlink)
  *   - `.claude/workflows/<workflow>.js`           (dynamic workflows, per-item symlinks)
+ *   - `.claude/output-styles/<name>.md`           (output styles, per-item symlinks)
  *   - `.claude/settings.json`                     (hooks, ide config)
  *   - `AGENTS.md`                                 (root coordination protocol)
  *
@@ -31,6 +32,9 @@ class ClaudeAdapter {
   /** Where this tool reads dynamic workflow scripts from (null if unsupported). */
   workflowsDir() { return '.claude/workflows'; }
 
+  /** Where this tool reads output-style definitions from (null if unsupported). */
+  outputStylesDir() { return '.claude/output-styles'; }
+
   /** Whether this tool consumes subagent definitions (`.claude/agents/`). */
   supportsSubagents() { return true; }
 

package/src/utils/tool-adapters/codex.js

@@ -46,6 +46,11 @@ class CodexAdapter {
   // simply never linked into a Codex tree.
   workflowsDir() { return null; }
 
+  // Output styles are a Claude Code concept (selected via `/config`); Codex has
+  // no equivalent. Returning null disables the per-item output-style merge for
+  // Codex — the source style files are simply never linked into a Codex tree.
+  outputStylesDir() { return null; }
+
   supportsSubagents() { return false; }
   supportsSlashCommands() { return false; }
   supportsHooks() { return false; }