zames_pro 2.58.0 → 2.59.0

package/CHANGELOG.md

@@ -7,6 +7,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [2.59.0]
+
+### Added
+
+- `/improve [id]` — a backlog-driven self-improvement loop. It picks the
+  next open item from `BACKLOG.md` (highest priority, or an explicit id),
+  runs the standard task loop on it (implement, typecheck/lint/test, mark
+  the item done, add a CHANGELOG entry) and leaves the changes uncommitted
+  for review. This is the reproducible hand-off path for a fresh agent.
+
 ## [2.58.0]
 
 ### Added
@@ -198,7 +208,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Session banner warns when no saved DeepSeek session exists.
 - `--no-color` flag (explicit `NO_COLOR`).
 
-[Unreleased]: https://github.com/Viqto0r/zames_pro/compare/v2.58.0...HEAD
+[Unreleased]: https://github.com/Viqto0r/zames_pro/compare/v2.59.0...HEAD
+[2.59.0]: https://github.com/Viqto0r/zames_pro/compare/v2.58.0...v2.59.0
 [2.58.0]: https://github.com/Viqto0r/zames_pro/compare/v2.57.1...v2.58.0
 [2.57.1]: https://github.com/Viqto0r/zames_pro/compare/v2.57.0...v2.57.1
 [2.57.0]: https://github.com/Viqto0r/zames_pro/compare/v2.56.0...v2.57.0

package/README.md

@@ -247,6 +247,10 @@ Codex CLI:
   instead of the whole list.
 - /review [focus] [--staged] — ask the agent to review uncommitted changes
   and report findings (no code changes).
+- /improve [id] — self-improvement loop: take the next open item from
+  `BACKLOG.md` (or a specific id, e.g. `/improve B3`), implement it, run the
+  typecheck/lint/tests, mark it done and add a CHANGELOG entry. Nothing is
+  committed — the changes stay in the working tree for review.
 - /plan [on|off] — plan (read-only) mode. While it is on, the mutating tools
   (Write/Edit/MultiEdit/ApplyPatch/Bash, GitAdd/GitCommit/GitPush) are removed
   from the tool set, so the agent can investigate without touching the tree.

package/dist/commands.js

@@ -707,6 +707,79 @@ export function mergeMessages(msgs) {
     const text = header + NL + NL + parts.join(NL + NL + '---' + NL + NL);
     return { text, attachments };
 }
+// Parse BACKLOG.md into actionable items. Recognizes headings of the form
+// `### A1. ...`, `### D7. ...` and marks an item done when its heading carries
+// a `[x]` marker. Pure; unit-tested. We deliberately do NOT parse the whole
+// markdown structure — only the headings the file contract promises.
+export function parseBacklogItems(text) {
+    const out = [];
+    let priority = '';
+    for (const raw of String(text ?? '').split(NL)) {
+        const line = raw.trimEnd();
+        const p = /^##\s+(P[0-3])\b/.exec(line);
+        if (p) {
+            priority = p[1];
+            continue;
+        }
+        const m = /^###\s+([A-Z]\d+)\.\s+(.*)$/.exec(line);
+        if (!m)
+            continue;
+        const id = m[1];
+        const rest = m[2];
+        // The `[x]` rewrite in BACKLOG keeps the ORIGINAL heading under a
+        // <details> block wrapped in `~~`. That archived copy must not be counted
+        // as a second, open item — skip a heading whose text starts with `~~`.
+        if (rest.trim().startsWith('~~'))
+            continue;
+        const done = /^\[x\]/i.test(rest.trim());
+        // The title is the heading text with the [x] marker and the `~~` strike
+        // wrappers removed, so a done item still has a clean label.
+        const title = rest
+            .replace(/^\[x\]\s*/i, '')
+            .replace(/~~/g, '')
+            .trim();
+        out.push({ id, title, status: done ? 'done' : 'open', priority });
+    }
+    return out;
+}
+// The next item to work on: the highest-priority OPEN item, in file order.
+// P0 first, then P1..P3. An explicit id overrides the priority search.
+export function nextBacklogItem(items, wanted) {
+    const open = items.filter((i) => i.status === 'open');
+    if (wanted) {
+        const w = wanted.trim().toUpperCase();
+        return items.find((i) => i.id.toUpperCase() === w) || null;
+    }
+    if (!open.length)
+        return null;
+    const rank = (p) => {
+        const m = /P(\d)/.exec(p || '');
+        return m ? Number(m[1]) : 9;
+    };
+    return open.slice().sort((a, b) => rank(a.priority) - rank(b.priority))[0];
+}
+// The task text sent to the agent for a chosen item. Agent-facing English,
+// like the rest of the loop. Keeps the working rules explicit so a fresh agent
+// does not need any external context.
+export function buildImprovePrompt(item) {
+    return ('Implement BACKLOG item ' +
+        item.id +
+        ' (priority ' +
+        (item.priority || '?') +
+        '): ' +
+        item.title +
+        NL +
+        NL +
+        'Read the full item text in BACKLOG.md for the details and the rationale. ' +
+        'Then: (1) implement it with the smallest reasonable change; ' +
+        '(2) run `npm run typecheck`, `npm run lint`, `npm run format:check` and ' +
+        '`npm test` and fix any failure; (3) mark the item done in BACKLOG.md by ' +
+        'prefixing its heading with `[x]` and wrapping the original heading text ' +
+        'in `~~ ~~`; (4) add a CHANGELOG entry if the change is user-visible; ' +
+        '(5) do NOT commit or push — leave the changes staged in the working tree ' +
+        'for the operator to review. When done, call respond with a short report ' +
+        '(files changed, tests run, whether BACKLOG/CHANGELOG were updated).');
+}
 // ---------- /review ----------
 export function buildReviewPrompt(focus, hasStaged = false) {
     const scope = hasStaged ? 'staged' : 'uncommitted';

package/dist/i18n.js

@@ -239,6 +239,26 @@ export const CATALOG = {
         ru: '/review [focus] ревью незакоммиченных изменений',
         en: '/review [focus] review uncommitted changes',
     },
+    'help.cmd.improve': {
+        ru: '/improve [id] взять следующий пункт BACKLOG и довести до тестов',
+        en: '/improve [id] take the next BACKLOG item and drive it to green tests',
+    },
+    'improve.no_backlog': {
+        ru: 'BACKLOG.md не найден в рабочей директории.',
+        en: 'BACKLOG.md was not found in the working directory.',
+    },
+    'improve.all_done': {
+        ru: 'Открытых пунктов в BACKLOG нет.',
+        en: 'There are no open BACKLOG items.',
+    },
+    'improve.not_found': {
+        ru: 'Пункт {v} не найден в BACKLOG.',
+        en: 'Item {v} was not found in BACKLOG.',
+    },
+    'improve.start': {
+        ru: 'Улучшение {id}: {title}',
+        en: 'Improving {id}: {title}',
+    },
     'help.cmd.compact': {
         ru: '/compact сжать историю и открыть новый чат с резюме',
         en: '/compact compact the history and open a new chat with the summary',

package/dist/index.js

@@ -18,7 +18,7 @@ import { translate, normalizeLocale, localeDisplayName, isLocale, } from './i18n
 import { Transcript } from './transcript.js';
 import { UndoStore } from './undo.js';
 import { selfReview, selfDiff, selfApply, selfList } from './self-review.js';
-import { formatDiff, formatDiffStat, formatContextSources, diffGitArgs, parseTranscript, summarizeTranscript, renderCost, formatExport, defaultExportPath, renderDoctor, resolveExtraDir, buildReviewPrompt, formatDuration, formatRelativeTime, trimRestoredMessages, RESTORED_HISTORY_LIMIT, mergeMessages, hasQueuedJob, isSlashCommand, parseQueueCommand, parseLiveToggle, parseGoalCommand, isLiveConfigCommand, withGoal, formatQueueList, ctrlCEscalation, } from './commands.js';
+import { formatDiff, formatDiffStat, formatContextSources, diffGitArgs, parseTranscript, summarizeTranscript, renderCost, formatExport, defaultExportPath, renderDoctor, resolveExtraDir, buildReviewPrompt, parseBacklogItems, nextBacklogItem, buildImprovePrompt, formatDuration, formatRelativeTime, trimRestoredMessages, RESTORED_HISTORY_LIMIT, mergeMessages, hasQueuedJob, isSlashCommand, parseQueueCommand, parseLiveToggle, parseGoalCommand, isLiveConfigCommand, withGoal, formatQueueList, ctrlCEscalation, } from './commands.js';
 import { performCompact } from './compact.js';
 import { Scheduler, parseInterval, formatInterval, formatJobLine, parseCron, } from './scheduler.js';
 import { renderMarkdown, setAnswerWidth } from './markdown.js';
@@ -388,6 +388,7 @@ ${theme.bold(t('help.sec.files'))}
   ${t('help.cmd.doctor')}
   ${t('help.cmd.add_dir')}
   ${t('help.cmd.review')}
+  ${t('help.cmd.improve')}
   ${t('help.cmd.debug_dom')}
   ${t('help.cmd.help')}
   ${t('help.cmd.exit')}
@@ -448,6 +449,7 @@ const SLASH_COMMANDS = [
     { name: '/doctor', key: 'help.cmd.doctor' },
     { name: '/add-dir', key: 'help.cmd.add_dir' },
     { name: '/review', key: 'help.cmd.review' },
+    { name: '/improve', key: 'help.cmd.improve' },
     { name: '/goal', key: 'help.cmd.goal' },
     { name: '/loop', key: 'help.cmd.loop' },
     { name: '/cron', key: 'help.cmd.cron' },
@@ -3336,6 +3338,58 @@ async function main() {
             }
             continue;
         }
+        if (lower === '/improve' || lower.startsWith('/improve ')) {
+            // Backlog-driven self-improvement: pick the next open BACKLOG item (or a
+            // specific id) and run the standard task loop on it. The agent reads
+            // BACKLOG.md itself for the details, so a FRESH agent needs no external
+            // context — this is the reproducible hand-off path.
+            const arg = trimmed.slice('/improve'.length).trim();
+            let backlogText;
+            try {
+                backlogText = await fs.readFile(path.join(currentWorkdir, 'BACKLOG.md'), 'utf-8');
+            }
+            catch {
+                console.error(theme.warn(t('improve.no_backlog')));
+                continue;
+            }
+            const items = parseBacklogItems(backlogText);
+            const item = nextBacklogItem(items, arg || undefined);
+            if (!item) {
+                console.log(theme.dim(arg ? t('improve.not_found', { v: arg }) : t('improve.all_done')));
+                continue;
+            }
+            console.log(theme.system(t('improve.start', { id: item.id, title: item.title })));
+            const improveTools = mod.createTools(currentWorkdir, {
+                undo,
+                todos: todoStore,
+                readOnly: planMode,
+            });
+            if (mcpPool)
+                improveTools.push(...mcpPool.tools);
+            if (editor)
+                editor.busy = true;
+            try {
+                await runTask(browser, improveTools, buildImprovePrompt(item), currentWorkdir, {
+                    transcript,
+                    freshChat: false,
+                    sendSystemPrompt: false,
+                    queue: pendingQueue,
+                    ui: editor || null,
+                    onChatReady: (chatId) => {
+                        if (chatId) {
+                            currentChatId = chatId;
+                            saveLastChat(chatId, currentWorkdir);
+                        }
+                    },
+                    getTokenUsage: () => browser.getLastTokenUsage(),
+                });
+            }
+            finally {
+                if (editor)
+                    editor.busy = false;
+            }
+            continue;
+        }
         if (lower === '/review' || lower.startsWith('/review ')) {
             const rest = trimmed.slice('/review'.length).trim();
             const staged = rest.indexOf('--staged') !== -1;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "zames_pro",
-  "version": "2.58.0",
+  "version": "2.59.0",
   "description": "Terminal coding agent that drives chat.deepseek.com through Playwright: reads and edits files, runs commands, commits to git.",
   "type": "module",
   "bin": {