scriveno 2.7.2 → 2.8.0

package/docs/configuration.md

@@ -57,7 +57,7 @@ When a writer runs `/scr:new-work`, Scriveno creates `.manuscript/config.json`.
 
 ```json
 {
-  "scriveno_version": "2.7.2",
+  "scriveno_version": "2.8.0",
   "work_type": "<chosen>",
   "group": "<group>",
   "command_unit": "<unit>",

package/docs/development.md

@@ -159,7 +159,7 @@ For release-oriented documentation surfaces, the main files are:
 - `docs/runtime-support.md`
 - `docs/route-graph.md`
 - `templates/*/README.md` when shipped profiles or templates change
-- `.planning/` milestone summaries when you are still using the GSD planning layer
+- `.planning/` milestone summaries when you are still using an external planning layer
 
 ## Before shipping
 

package/docs/release-notes.md

@@ -2,6 +2,20 @@
 
 This document is the public-facing summary of what changed between package releases. For package history, see the root [CHANGELOG](../CHANGELOG.md).
 
+## 2.8.0 - 2026-05-30
+
+### What changed
+
+- Scriveno can now install focused command profiles: `core`, `writing`, `publishing`, `translation`, `specialist`, or `full`. The new `/scr:surface` command and `scriveno surface` CLI helpers let writers inspect, dry-run, and switch profiles.
+- Added `/scr:proof-unit`, a one-unit proof path that checks voice context, plans, drafts, reviews, context health, and optional export-tool readiness.
+- Added context-health estimation to `scriveno status`, `/scr:next`, and `/scr:health --context`, with watch, tight, and critical thresholds.
+- Added `/scr:export --check` and `/scr:publish --preflight` so tool readiness and publishing prerequisites can be verified before writing deliverables.
+- Updated the public command inventory to 115 commands and added regression tests for profiles, dry-run installs, context health, proof-unit, and preflight surfaces.
+
+### Why it matters
+
+Writers can keep Scriveno small when they only need the active workflow, prove the product on one real unit before trusting a larger run, and check export or publishing readiness before generating packages.
+
 ## 2.7.2 - 2026-05-30
 
 ### What changed
@@ -76,7 +90,7 @@ This release closes the gap between what Scriveno documented and what it shipped
 - The public CLI now supports `scriveno first-run --project .`, giving terminal users the same proof path without relying on host-specific slash-command behavior.
 - First-run guidance is connected to `/scr:help`, `/scr:demo`, Quick Proof, Starter Sets, Runtime Support, Shipped Assets, Command Reference, README launch copy, and architecture docs.
 - Scriveno now includes committed first-run and runtime-parity proof bundles under `data/proof/`.
-- Runtime smoke now validates the 113-command installed surface across Claude Code, Codex, Cursor, Gemini CLI, OpenCode, GitHub Copilot, Windsurf, Antigravity, Manus, Perplexity Desktop, and the generic fallback.
+- Runtime smoke now validates the 115-command installed surface across Claude Code, Codex, Cursor, Gemini CLI, OpenCode, GitHub Copilot, Windsurf, Antigravity, Manus, Perplexity Desktop, and the generic fallback.
 - README badges, package metadata, constraints metadata, generated config metadata, changelog, release notes, configuration docs, route graph docs, architecture docs, proof docs, and release tests are aligned on `2.5.0`.
 
 ### Why it matters

package/docs/route-graph.md

@@ -13,9 +13,9 @@ The text report summarizes command count, graph edges, agent-capable routes, loc
 
 ## Current Shape
 
-As of `2.7.2`, the route graph contains:
+As of `2.8.0`, the route graph contains:
 
-- 113 commands
+- 115 commands
 - intent-order edges from `command_intents`
 - dependency-chain edges from `dependencies.core_chain`
 - automation lanes from `getCommandAutomationPolicy()`

package/docs/sacred-texts.md

@@ -292,5 +292,5 @@ Here is a quick walkthrough for starting a sacred writing project:
 ## See Also
 
 - [Getting Started](getting-started.md) -- Install Scriveno and create your first project
-- [Command Reference](command-reference.md) -- Full reference for all 113 commands, including the [Sacred Exclusive](command-reference.md#sacred-exclusive) section
+- [Command Reference](command-reference.md) -- Full reference for all 115 commands, including the [Sacred Exclusive](command-reference.md#sacred-exclusive) section
 - [README](../README.md) -- Project overview and feature list

package/docs/voice-dna.md

@@ -293,5 +293,5 @@ See [docs/drafter-quality.md](drafter-quality.md) for the full system, including
 - [Proof Artifacts](proof-artifacts.md) -- inspect the Voice DNA before/after bundle first if you want the fastest concrete evidence
 - [Getting Started](getting-started.md) -- Install Scriveno and write your first draft
 - [Drafter Quality](drafter-quality.md) -- the three rule layers, the `draft` config block, and model-tier recommendations
-- [Command Reference](command-reference.md) -- Full list of all 113 commands with usage and examples
+- [Command Reference](command-reference.md) -- Full list of all 115 commands with usage and examples
 - [Work Types Guide](work-types.md) -- How work types adapt Scriveno's vocabulary and commands

package/docs/work-types.md

@@ -335,5 +335,5 @@ Your work type is stored in `.manuscript/config.json` and can be changed later b
 ## See Also
 
 - [Getting Started](getting-started.md) -- Install Scriveno and write your first draft
-- [Command Reference](command-reference.md) -- Full list of all 113 commands with usage and examples
+- [Command Reference](command-reference.md) -- Full list of all 115 commands with usage and examples
 - [Voice DNA Guide](voice-dna.md) -- How Scriveno profiles and preserves your writing voice

package/lib/auto-invoke-engine.js

@@ -581,6 +581,72 @@ function detectContextSignal(manuscriptDir, draftFiles) {
   return { state: 'fresh', suggest: null };
 }
 
+const CONTEXT_HEALTH_LIMITS = {
+  watch: 45000,
+  tight: 80000,
+  critical: 120000,
+};
+
+function estimateTextTokens(byteCount) {
+  return Math.ceil(byteCount / 4);
+}
+
+function fileByteSize(filePath) {
+  const stat = safeStat(filePath);
+  return stat && stat.isFile() ? stat.size : 0;
+}
+
+function newestFiles(files, limit) {
+  return files
+    .map((file) => ({ file, mtime: safeStat(file)?.mtimeMs || 0 }))
+    .sort((a, b) => b.mtime - a.mtime)
+    .slice(0, limit)
+    .map((entry) => entry.file);
+}
+
+function detectContextHealth(manuscriptDir, draftFiles) {
+  const coreFiles = [
+    'STYLE-GUIDE.md',
+    'CONTEXT.md',
+    'STATE.md',
+    'OUTLINE.md',
+    'RECORD.md',
+    'WORK.md',
+    'config.json',
+  ].map((name) => path.join(manuscriptDir, name));
+  const reviewFiles = newestFiles(listFiles(path.join(manuscriptDir, 'reviews'), { extensions: ['.md', '.txt'], recursive: true }), 3);
+  const planFiles = newestFiles(listFiles(path.join(manuscriptDir, 'plans'), { extensions: ['.md'], recursive: true }), 3);
+  const recentDrafts = newestFiles(draftFiles, 5);
+  const uniqueFiles = [...new Set([...coreFiles, ...planFiles, ...recentDrafts, ...reviewFiles])].filter(pathExists);
+  const files = uniqueFiles.map((file) => ({
+    file: path.relative(manuscriptDir, file),
+    bytes: fileByteSize(file),
+  }));
+  const estimatedBytes = files.reduce((sum, file) => sum + file.bytes, 0);
+  const estimatedTokens = estimateTextTokens(estimatedBytes);
+  let state = 'ok';
+  let suggest = null;
+  if (estimatedTokens >= CONTEXT_HEALTH_LIMITS.critical) {
+    state = 'critical';
+    suggest = '/scr:thread';
+  } else if (estimatedTokens >= CONTEXT_HEALTH_LIMITS.tight) {
+    state = 'tight';
+    suggest = '/scr:save';
+  } else if (estimatedTokens >= CONTEXT_HEALTH_LIMITS.watch) {
+    state = 'watch';
+    suggest = '/scr:health --context';
+  }
+  return {
+    state,
+    estimatedTokens,
+    estimatedBytes,
+    fileCount: files.length,
+    limits: { ...CONTEXT_HEALTH_LIMITS },
+    largestFiles: files.sort((a, b) => b.bytes - a.bytes).slice(0, 5),
+    suggest,
+  };
+}
+
 function detectExportSignal(manuscriptDir, sourceFiles) {
   const newestSource = newestMtime(sourceFiles);
   const newestOutput = findNewestOutput(manuscriptDir);
@@ -757,6 +823,12 @@ function buildAutomationPlan(signals, recommendation) {
   if (signals.context?.state === 'stale') {
     localCandidates.push({ command: signals.context.suggest || '/scr:scan', reason: 'refresh stale context before chaining work' });
   }
+  if (signals.contextHealth?.state === 'tight' || signals.contextHealth?.state === 'critical') {
+    localCandidates.push({
+      command: signals.contextHealth.suggest || '/scr:health --context',
+      reason: `loaded context estimate is ${signals.contextHealth.state}`,
+    });
+  }
   if (signals.notes?.count > 0) {
     localCandidates.push({ command: '/scr:check-notes', reason: 'surface unresolved notes before the next writing route' });
   }
@@ -801,6 +873,7 @@ function analyzeProject(projectRoot = process.cwd(), options = {}) {
       hasProject: false,
       hasState: false,
       context: { state: 'none', suggest: null },
+      contextHealth: { state: 'none', estimatedTokens: 0, estimatedBytes: 0, fileCount: 0, largestFiles: [], suggest: null },
       history: { state: 'none', lastFailed: false },
       reviews: { state: 'none', count: 0, files: [] },
       reviewCoverage: { state: 'none', suggest: null },
@@ -844,6 +917,7 @@ function analyzeProject(projectRoot = process.cwd(), options = {}) {
     hasProject: true,
     hasState: pathExists(statePath),
     context: detectContextSignal(manuscriptDir, draftFiles),
+    contextHealth: detectContextHealth(manuscriptDir, draftFiles),
     history: historySignal,
     readiness: detectProjectReadiness(manuscriptDir),
     plan: detectPlanSignal(manuscriptDir, draftFiles),
@@ -895,6 +969,7 @@ function formatProactiveChecks(analysis) {
     progressLine,
     `  Readiness: ${signals.readiness?.state || 'none'}${signals.readiness?.missing?.length ? `, missing ${signals.readiness.missing.join(', ')}` : ''}`,
     `  Session: ${signals.context.state}${signals.context.suggest ? `, suggest ${signals.context.suggest}` : ''}`,
+    `  Context health: ${signals.contextHealth?.state || 'none'}${signals.contextHealth?.estimatedTokens ? `, about ${signals.contextHealth.estimatedTokens} tokens` : ''}${signals.contextHealth?.suggest ? `, suggest ${signals.contextHealth.suggest}` : ''}`,
     `  Plans: ${signals.plan?.state || 'none'}${signals.plan?.suggest ? `, suggest ${signals.plan.suggest}` : ''}`,
     `  Reviews: ${signals.reviews.count ? `${signals.reviews.count} pending, suggest /scr:editor-review` : 'none'}`,
     `  Review coverage: ${signals.reviewCoverage?.state || 'none'}${signals.reviewCoverage?.suggest ? `, suggest ${signals.reviewCoverage.suggest}` : ''}`,
@@ -1574,4 +1649,6 @@ module.exports = {
   listRuntimeAgentSupport,
   parseCliArgs,
   computeProgressLedger,
+  detectContextHealth,
+  estimateTextTokens,
 };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "scriveno",
-  "version": "2.7.2",
+  "version": "2.8.0",
   "description": "Spec-driven creative writing, publishing, and translation pipeline for AI coding agents. From blank page to published book.",
   "bin": {
     "scriveno": "bin/install.js"

package/templates/config.json

@@ -1,5 +1,5 @@
 {
-  "scriveno_version": "2.7.2",
+  "scriveno_version": "2.8.0",
   "work_type": "",
   "group": "",
   "command_unit": "",