iterate-plugin 2.7.1 → 2.7.3

package/README.md

@@ -7,6 +7,14 @@
 
 > **Developed and reviewed in the [iterate-skill monorepo](https://github.com/jingzhao-l/iterate-skill)**: the plugin code is maintained in the main repository and synced here via `git subtree`; **releases and npm publishing happen in this (plugin) repository**, which is the canonical publish point for the dsh ecosystem. Please **star / fork the main repository** and file issues at the [main repository Issues](https://github.com/jingzhao-l/iterate-skill/issues).
 
+<p align="center">
+  <a href="https://github.com/jingzhao-l/iterate-plugin"><img src="https://img.shields.io/github/stars/jingzhao-l/iterate-plugin?style=social&label=Star" alt="Stars"></a>
+  <a href="https://github.com/jingzhao-l/iterate-skill"><img src="https://img.shields.io/github/stars/jingzhao-l/iterate-skill?style=social&label=Main%20Repo%20Star" alt="Main Repo Stars"></a>
+  <a href="https://www.npmjs.com/package/iterate-plugin"><img src="https://img.shields.io/npm/dt/iterate-plugin?label=Downloads&logo=npm&logoColor=white" alt="npm downloads"></a>
+</p>
+
+> ⭐ If this helps your dsh workflow, give the main repo a star — it means a lot!
+
 ## About This Plugin
 
 **iterate** is an open-source project that gives AI coding assistants the ability to review and fix code in multi-round autonomous loops. It targets a concrete pain point:

package/README.zh-CN.md

@@ -7,6 +7,14 @@
 
 > **开发与评审在 [iterate-skill 主仓库](https://github.com/jingzhao-l/iterate-skill) 完成**：插件代码由主仓库统一维护，通过 `git subtree` 同步到本仓库；**版本发版与 npm 发布在本仓库（插件仓库）进行**，作为 dsh 生态的正式发布位。欢迎 **star / fork 主仓库** 并在 [主仓库 Issues](https://github.com/jingzhao-l/iterate-skill/issues) 反馈问题。
 
+<p align="center">
+  <a href="https://github.com/jingzhao-l/iterate-plugin"><img src="https://img.shields.io/github/stars/jingzhao-l/iterate-plugin?style=social&label=Star" alt="Stars"></a>
+  <a href="https://github.com/jingzhao-l/iterate-skill"><img src="https://img.shields.io/github/stars/jingzhao-l/iterate-skill?style=social&label=主仓库%20Star" alt="主仓库 Stars"></a>
+  <a href="https://www.npmjs.com/package/iterate-plugin"><img src="https://img.shields.io/npm/dt/iterate-plugin?label=Downloads&logo=npm&logoColor=white" alt="npm downloads"></a>
+</p>
+
+> ⭐ 如果这个插件对你的 dsh 工作流有帮助，欢迎为主仓库点亮 Star，这是对开源维护最大的支持！
+
 ## 这是什么 / About This Plugin
 
 **iterate** 是一个让 AI 编程助手具备多轮自主代码审查与修复能力的开源项目。它解决很具体的痛点：

package/dist/index.js

@@ -2,11 +2,13 @@
  * iterate-plugin — dsh plugin for the iterate autonomous closed-loop workflow
  *
  * Architecture:
- * - The plugin registers 6 tools (config, validate, decision-log, context, review, triage)
+ * - The plugin registers 13 tools (config, validate, decision-log, context, review,
+ *   triage, fix, diff, rollback, checkpoint, status, history, prune)
  * - The plugin injects a system prompt section teaching the iterate workflow pattern
  * - The model (prompted by the skill) writes a workflow script using dsh's `workflow` tool
  * - The workflow script uses `agent()` / `parallel()` / `phase()` / `log()` to orchestrate
- * - Subagents use the 6 tools to do real work (read config, run validation, log decisions, review, triage)
+ * - Subagents use the 13 tools to do real work (read config, run validation, log decisions,
+ *   review, triage, apply/rollback/fixing, checkpoint, status, history, prune)
  *
  * Tool invocation model:
  * - Workflow script CANNOT call tools directly (sandboxed vm, no Node API)
@@ -16,7 +18,7 @@
  *
  * Key files:
  * - src/index.ts      — Plugin entry: register tools + inject skill prompt
- * - src/tools/        — 6 tool implementations + meta-review/review engines
+ * - src/tools/        — 13 tool implementations + meta-review/review engines
  * - src/config-loader.ts — YAML config loading
  * - src/types.ts     — Shared types
  */
@@ -34,7 +36,7 @@ import { ITERATE_SKILL_PROMPT } from "./skill-prompt.js";
 export const name = 'iterate-plugin';
 export const inject = ['tools', 'systemPrompt'];
 export function apply(ctx) {
-    // 1. Register the 11 tools
+    // 1. Register the 13 tools
     registerConfigTool(ctx);
     registerValidateTool(ctx);
     registerDecisionLogTool(ctx);

package/dist/review.js

@@ -208,6 +208,11 @@ export function buildReviewReport(input) {
     const lastRound = filteredRounds.length > 0 ? filteredRounds[filteredRounds.length - 1].round : 0;
     const lastRoundCount = lastRound > 0 ? (findingsByRound[lastRound - 1] ?? 0) : 0;
     const converged = filteredRounds.length > 0 && lastRoundCount === 0;
+    // Attach the normal-mode fix count to the summary (dry-run leaves it absent).
+    const computed = summarize(sorted);
+    if (input.mode === 'normal' && typeof input.fixedCount === 'number' && Number.isInteger(input.fixedCount)) {
+        computed.fixedCount = input.fixedCount;
+    }
     return {
         mode: input.mode,
         goal: input.goal,
@@ -225,7 +230,7 @@ export function buildReviewReport(input) {
                     ? 'converged'
                     : 'max_rounds_reached',
         },
-        summary: summarize(sorted),
+        summary: computed,
     };
 }
 /**

package/dist/skill-prompt.js

@@ -13,13 +13,15 @@ You have the iterate plugin installed, which registers these tools:
 - \`iterate_validate\` — run a whitelisted validation command
 - \`iterate_decision_log\` — append to the decision log, or read entries back for review
 - \`iterate_context\` — read SKILL.md / ITERATE.md project context
-- \`iterate_review\` — deterministic review engine: \`plan\` builds the review plan; \`aggregate\` dedupes/merges findings and computes convergence. Purely computational.
+- \`iterate_review\` — deterministic review engine: \`plan\` builds the review plan; \`aggregate\` dedupes/merges findings and computes convergence; \`meta-review\` audits a built report for internal consistency (counts, buckets, sorting, convergence math) and returns a final report with an \`approved\` / \`needs_revision\` verdict. Purely computational.
 - \`iterate_triage\` — manage "known_intentional" entries in the config (list / apply, with dedupe + backup + rollback)
 - \`iterate_fix\` — apply ONE atomic fix: backs up the file, enforces the atomic max_lines threshold, writes the new content, and records the fix (id + diff summary) in \`.iterate/fixes/registry.json\`
 - \`iterate_diff\` — show the accumulated diff for a fixed file (vs its original backup) or a per-file summary of all fixes
 - \`iterate_rollback\` — revert a fix by id: restore the file from its backup, remove the fix from the registry, log a \`revert\` entry. Use when a round's validation fails
 - \`iterate_checkpoint\` — save / load / clear an iteration checkpoint (\`.iterate/checkpoint.json\`) so a long run can resume where it left off
 - \`iterate_status\` — summarize the current run: mode, round, fixes applied, architectural remaining, decision-log size, checkpoint presence
+- \`iterate_history\` — inspect the runtime state in detail: decision-log entries and applied fixes (optionally scoped to a round or a fixed file)
+- \`iterate_prune\` — remove stale runtime artifacts (\`.iterate/\` entries). Defaults to a read-only dry-run that reports what WOULD be removed; pass \`dryRun:false\` to actually prune.
 
 ### When to use
 When the user asks to review or iterate on the project (e.g. "review this project", "iterate on error handling", "check the codebase for issues", "dry-run review", "反复审查"), run an iterate **workflow** by calling the \`workflow\` tool.
@@ -175,8 +177,10 @@ for (let r = startRound; r <= maxRounds; r++) {
   rounds.push(thisRound)
 
   // Deterministic dedupe / known_intentional filter / severity sort for this round.
+  // \`fixedCount\` is threaded into the report summary so the client dashboard can
+  // show a running "fixes applied" metric for normal mode.
   const agg = await agent(
-    'Call iterate_review({operation:"aggregate", mode:"normal", rounds:' + JSON.stringify([thisRound]) + ', knownIntentional:' + JSON.stringify(knownIntentional) + '}) and return the report JSON.',
+    'Call iterate_review({operation:"aggregate", mode:"normal", rounds:' + JSON.stringify([thisRound]) + ', knownIntentional:' + JSON.stringify(knownIntentional) + ', fixedCount:' + fixedCount + '}) and return the report JSON.',
     { label: 'review:aggregate:r' + r }
   )
   const findings = (agg && agg.report && agg.report.findings) ? agg.report.findings : thisRound.findings

package/dist/tools/decision-log.js

@@ -4,6 +4,34 @@ import { defineTool } from '@deepseek-ai/dsh-tools';
 import { resolveProjectRoot } from "../config-loader.js";
 const LOG_DIR = '.iterate';
 const LOG_FILE = 'decision-log.jsonl';
+/** All valid DecisionLogEntry `type` values (must stay in sync with Types). */
+const VALID_ENTRY_TYPES = new Set([
+    'round_start',
+    'review_result',
+    'atomic_fix',
+    'architectural_fix',
+    'revert',
+    'round_failed',
+    'validation',
+    'decision',
+    'report',
+]);
+/**
+ * Validate a candidate (type, round, data) triple for an append operation.
+ * Returns an error string on failure, or null when the entry is well-formed.
+ */
+function validateEntryInput(type, round, data) {
+    if (typeof type !== 'string' || !VALID_ENTRY_TYPES.has(type)) {
+        return `type must be one of: ${[...VALID_ENTRY_TYPES].join(', ')}.`;
+    }
+    if (typeof round !== 'number' || !Number.isInteger(round) || round < 1) {
+        return 'round must be a positive integer.';
+    }
+    if (data !== undefined && data !== null && typeof data !== 'object') {
+        return 'data must be an object (or omitted).';
+    }
+    return null;
+}
 /**
  * Resolve the log file path, creating the directory if needed.
  */
@@ -73,13 +101,14 @@ export function registerDecisionLogTool(ctx) {
             type: {
                 type: 'string',
                 description: 'Entry type (required for append): round_start, review_result, atomic_fix, ' +
-                    'architectural_fix, revert, validation, decision, report.',
+                    'architectural_fix, revert, round_failed, validation, decision, report.',
                 enum: [
                     'round_start',
                     'review_result',
                     'atomic_fix',
                     'architectural_fix',
                     'revert',
+                    'round_failed',
                     'validation',
                     'decision',
                     'report',
@@ -132,17 +161,23 @@ export function registerDecisionLogTool(ctx) {
                 };
             }
             if (args.operation === 'append') {
-                if (!args.type || !args.round) {
+                const invalid = validateEntryInput(args.type, args.round, args.data);
+                if (invalid !== null) {
                     return {
                         operation: 'append',
-                        error: 'type and round are required for append operation.',
+                        error: invalid,
                     };
                 }
+                const type = args.type;
+                const round = args.round;
+                const data = args.data === undefined || args.data === null
+                    ? {}
+                    : args.data;
                 const entry = {
                     timestamp: new Date().toISOString(),
-                    round: args.round,
-                    type: args.type,
-                    data: args.data ?? {},
+                    round,
+                    type,
+                    data,
                 };
                 const result = appendDecisionEntry(projectRoot, entry);
                 return {

package/dist/tools/review.js

@@ -62,6 +62,11 @@ export function registerReviewTool(ctx) {
                 description: 'For `meta-review`: the ReviewReport JSON (as returned by `aggregate`) to audit for ' +
                     'internal consistency and produce the final review report.',
             },
+            fixedCount: {
+                type: 'integer',
+                description: 'For `aggregate` (normal mode only): number of atomic fixes applied so far. ' +
+                    'Surfaces a running "fixes applied" metric on the report summary.',
+            },
             path: {
                 type: 'string',
                 description: 'Project root directory (default: current working directory).',
@@ -128,6 +133,7 @@ export function registerReviewTool(ctx) {
                     maxReviewRounds,
                     rounds,
                     knownIntentional: args.knownIntentional,
+                    fixedCount: typeof args.fixedCount === 'number' ? args.fixedCount : undefined,
                 });
                 return { operation: 'aggregate', mode, report: report };
             }