@mechanai/deepreview 2.1.2 → 2.1.4

package/.opencode/commands/deepreview-pr-review.md

@@ -18,16 +18,55 @@ Check if input.txt is empty (0 bytes). If empty, tell the user "Nothing to revie
 Get and store the PR head SHA:
 Run `gh pr view $ARGUMENTS --json headRefOid --jq .headRefOid` and save the output as PR_HEAD_SHA.
 
-## Stage 1-3: Shared Pipeline
+STEP 3: DISPATCH STAGE 1 — INITIAL REVIEW (5 parallel tasks)
+Dispatch ALL FIVE of these Task tool calls simultaneously in a single message:
 
-Follow the shared pipeline at `commands/_deepreview-pipeline.md` with:
+Task 1 — Use the Task tool with subagent_type="deepreview-correctness":
+"You are reviewing a PR diff (code changes). Read the content at $SESSION_DIR/input.txt. Write your review to $SESSION_DIR/review-correctness.md."
 
-- INPUT: `$SESSION_DIR/input.txt`
-- OUTPUT: `$SESSION_DIR/synthesis.md`
+Task 2 — Use the Task tool with subagent_type="deepreview-security":
+"You are reviewing a PR diff (code changes). Read the content at $SESSION_DIR/input.txt. Write your review to $SESSION_DIR/review-security.md."
+
+Task 3 — Use the Task tool with subagent_type="deepreview-architecture":
+"You are reviewing a PR diff (code changes). Read the content at $SESSION_DIR/input.txt. Write your review to $SESSION_DIR/review-architecture.md."
+
+Task 4 — Use the Task tool with subagent_type="deepreview-docs":
+"You are reviewing a PR diff (code changes). Read the content at $SESSION_DIR/input.txt. Write your review to $SESSION_DIR/review-docs.md."
+
+Task 5 — Use the Task tool with subagent_type="deepreview-compatibility":
+"You are reviewing a PR diff (code changes). Read the content at $SESSION_DIR/input.txt. Write your review to $SESSION_DIR/review-compatibility.md."
+
+Wait for all 5 to return. Record which succeeded and which failed.
+
+STEP 4: DISPATCH STAGE 2 — CROSS-VALIDATION (5 parallel tasks)
+Only proceed with reviews that exist. Dispatch ALL FIVE simultaneously:
+
+Task 6 — Use the Task tool with subagent_type="deepreview-validator":
+"Your perspective: correctness. Read all review files at: $SESSION_DIR/review-correctness.md, $SESSION_DIR/review-security.md, $SESSION_DIR/review-architecture.md, $SESSION_DIR/review-docs.md, $SESSION_DIR/review-compatibility.md. Also read the original input at $SESSION_DIR/input.txt for context. Write your validated review to $SESSION_DIR/validated-correctness.md."
+
+Task 7 — Use the Task tool with subagent_type="deepreview-validator":
+"Your perspective: security. Read all review files at: $SESSION_DIR/review-correctness.md, $SESSION_DIR/review-security.md, $SESSION_DIR/review-architecture.md, $SESSION_DIR/review-docs.md, $SESSION_DIR/review-compatibility.md. Also read the original input at $SESSION_DIR/input.txt for context. Write your validated review to $SESSION_DIR/validated-security.md."
+
+Task 8 — Use the Task tool with subagent_type="deepreview-validator":
+"Your perspective: architecture. Read all review files at: $SESSION_DIR/review-correctness.md, $SESSION_DIR/review-security.md, $SESSION_DIR/review-architecture.md, $SESSION_DIR/review-docs.md, $SESSION_DIR/review-compatibility.md. Also read the original input at $SESSION_DIR/input.txt for context. Write your validated review to $SESSION_DIR/validated-architecture.md."
+
+Task 9 — Use the Task tool with subagent_type="deepreview-validator":
+"Your perspective: docs. Read all review files at: $SESSION_DIR/review-correctness.md, $SESSION_DIR/review-security.md, $SESSION_DIR/review-architecture.md, $SESSION_DIR/review-docs.md, $SESSION_DIR/review-compatibility.md. Also read the original input at $SESSION_DIR/input.txt for context. Write your validated review to $SESSION_DIR/validated-docs.md."
+
+Task 10 — Use the Task tool with subagent_type="deepreview-validator":
+"Your perspective: compatibility. Read all review files at: $SESSION_DIR/review-correctness.md, $SESSION_DIR/review-security.md, $SESSION_DIR/review-architecture.md, $SESSION_DIR/review-docs.md, $SESSION_DIR/review-compatibility.md. Also read the original input at $SESSION_DIR/input.txt for context. Write your validated review to $SESSION_DIR/validated-compatibility.md."
+
+Wait for all 5 to return.
+
+STEP 5: DISPATCH STAGE 3 — SYNTHESIS (1 task)
+Task 11 — Use the Task tool with subagent_type="deepreview-synthesizer":
+"Read the validated reviews at: $SESSION_DIR/validated-correctness.md, $SESSION_DIR/validated-security.md, $SESSION_DIR/validated-architecture.md, $SESSION_DIR/validated-docs.md, $SESSION_DIR/validated-compatibility.md (skip any that don't exist). Write the synthesis to $SESSION_DIR/synthesis.md."
+
+Record the stats line from its return.
 
 If stats show 0 critical, 0 warnings, 0 suggestions, tell the user "No findings to post. PR looks good!" and STOP.
 
-STEP 3: FORMAT THREADS (1 task)
+STEP 6: FORMAT THREADS (1 task)
 
 Get the repo owner/name:
 Run `gh repo view --json owner,name --jq '.owner.login + "/" + .name'` and save as OWNER_REPO.
@@ -37,18 +76,18 @@ Task — Use the Task tool with subagent_type="deepreview-review-formatter":
 
 Wait for it to return.
 
-STEP 4: POST REVIEW
+STEP 7: POST REVIEW
 Use the `deepreview-post-review` tool:
 
 - `threads_path`: The absolute path to `$SESSION_DIR/threads.md`
 - `pr_number`: $ARGUMENTS (the PR number)
 
-STEP 5: PRESENT RESULTS
+STEP 8: PRESENT RESULTS
 Show the user:
 
 - Session directory: $SESSION_DIR/
 - Which reviewers completed (and any that failed)
-- Stats from synthesis (the stats line from Stage 3)
+- Stats from synthesis (the stats line from Step 5)
 - Output from the posting script (how many threads posted, any demotions)
 - Remind: "The review is PENDING. Submit it via the GitHub UI when ready."
 

package/dist/setup.mjs

@@ -0,0 +1,115 @@
+#!/usr/bin/env node
+
+// src/setup.ts
+import {
+  existsSync,
+  lstatSync,
+  mkdirSync,
+  readdirSync,
+  symlinkSync,
+  unlinkSync,
+  readFileSync,
+  writeFileSync
+} from "node:fs";
+import path from "node:path";
+import os from "node:os";
+import { applyEdits, modify, parse as parseJsonc } from "jsonc-parser";
+var PACKAGE_NAME = "@mechanai/deepreview";
+var local = process.argv.includes("--local");
+var cwd = process.cwd();
+var globalConfigDir = path.join(process.env.XDG_CONFIG_HOME ?? path.join(os.homedir(), ".config"), "opencode");
+var targetDir = local ? path.join(cwd, ".opencode") : globalConfigDir;
+var packageDir = path.resolve(import.meta.dirname, "..");
+var packageOpencode = path.join(packageDir, ".opencode");
+function ensurePluginInConfig() {
+  const configFiles = ["opencode.jsonc", "opencode.json"];
+  const searchDir = local ? cwd : globalConfigDir;
+  let configPath;
+  for (const file of configFiles) {
+    const candidate = path.join(searchDir, file);
+    if (existsSync(candidate)) {
+      configPath = candidate;
+      break;
+    }
+  }
+  if (configPath === undefined) {
+    configPath = path.join(searchDir, "opencode.json");
+    mkdirSync(searchDir, { recursive: true });
+    writeFileSync(configPath, JSON.stringify({ plugin: [PACKAGE_NAME] }, null, 2) + `
+`);
+    console.log(`Created ${configPath} with plugin entry.`);
+    return;
+  }
+  const raw = readFileSync(configPath, "utf-8");
+  let config;
+  try {
+    const parsed = parseJsonc(raw);
+    if (parsed === null || typeof parsed !== "object" || Array.isArray(parsed)) {
+      throw new Error("not an object");
+    }
+    config = parsed;
+  } catch {
+    console.error(`Could not parse ${configPath}. Add the plugin manually:`);
+    console.error(`  "plugin": ["${PACKAGE_NAME}"]`);
+    process.exitCode = 1;
+    return;
+  }
+  const pluginArray = Array.isArray(config.plugin) ? config.plugin : [];
+  const plugins = pluginArray.filter((p) => typeof p === "string");
+  if (plugins.includes(PACKAGE_NAME)) {
+    console.log(`Plugin already registered in ${configPath}.`);
+    return;
+  }
+  const formatting = { formattingOptions: { insertSpaces: true, tabSize: 2 } };
+  const edits = Array.isArray(config.plugin) ? modify(raw, ["plugin", pluginArray.length], PACKAGE_NAME, formatting) : modify(raw, ["plugin"], [PACKAGE_NAME], formatting);
+  writeFileSync(configPath, applyEdits(raw, edits));
+  console.log(`Added "${PACKAGE_NAME}" to plugin array in ${configPath}.`);
+}
+function symlinkDirectory(kind) {
+  const sourceDir = path.join(packageOpencode, kind);
+  if (!existsSync(sourceDir))
+    return;
+  const destDir = path.join(targetDir, kind);
+  mkdirSync(destDir, { recursive: true });
+  const sourceFiles = new Set(readdirSync(sourceDir).filter((f) => f.endsWith(".md")));
+  let created = 0;
+  for (const file of readdirSync(destDir)) {
+    if (!file.startsWith("deepreview-") && !file.startsWith("_deepreview-"))
+      continue;
+    const dest = path.join(destDir, file);
+    try {
+      if (lstatSync(dest).isSymbolicLink() && !sourceFiles.has(file)) {
+        unlinkSync(dest);
+      }
+    } catch (err) {
+      if (err instanceof Error && !(("code" in err) && err.code === "ENOENT")) {
+        console.warn(`Could not check ${dest}: ${err.message}`);
+      }
+    }
+  }
+  for (const file of sourceFiles) {
+    const dest = path.join(destDir, file);
+    const source = path.relative(destDir, path.join(sourceDir, file));
+    try {
+      const stat = lstatSync(dest);
+      if (!stat.isSymbolicLink()) {
+        console.warn(`Skipping ${dest}: not a symlink (would overwrite regular file)`);
+        continue;
+      }
+      unlinkSync(dest);
+    } catch (err) {
+      if (err instanceof Error && "code" in err && err.code !== "ENOENT") {
+        throw err;
+      }
+    }
+    symlinkSync(source, dest);
+    created++;
+  }
+  const label = local ? `.opencode/${kind}/` : path.join(targetDir, kind) + "/";
+  console.log(`Linked ${created} ${kind} into ${label}`);
+}
+ensurePluginInConfig();
+symlinkDirectory("agents");
+symlinkDirectory("commands");
+var scope = local ? "project" : "global";
+console.log(`Done (${scope}). Run opencode to use /deepreview commands.`);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mechanai/deepreview",
-  "version": "2.1.2",
+  "version": "2.1.4",
   "description": "Multi-agent parallel code/spec review for OpenCode",
   "license": "MIT",
   "repository": {
@@ -25,6 +25,9 @@
   "publishConfig": {
     "access": "public"
   },
+  "scripts": {
+    "prepare": "mise run build"
+  },
   "dependencies": {
     "gray-matter": "4.0.3",
     "js-yaml": "4.1.0",

package/.opencode/commands/_deepreview-pipeline.md

@@ -1,57 +0,0 @@
----
-internal: true
-description: "Shared pipeline stages for deepreview commands (review → validate → synthesize)"
----
-
-# Shared Pipeline: Review → Validate → Synthesize
-
-This template defines 3 stages used by deepreview orchestrator commands. The orchestrator must set SESSION_DIR and INPUT_DESCRIPTION before invoking these stages.
-
-## STAGE 1: INITIAL REVIEW (one task per review perspective)
-
-Dispatch ALL of these Task tool calls simultaneously in a single message:
-
-Task — Use the Task tool with subagent_type="deepreview-correctness":
-"You are reviewing $INPUT_DESCRIPTION. Read the content at $SESSION_DIR/input.txt. Write your review to $SESSION_DIR/review-correctness.md."
-
-Task — Use the Task tool with subagent_type="deepreview-security":
-"You are reviewing $INPUT_DESCRIPTION. Read the content at $SESSION_DIR/input.txt. Write your review to $SESSION_DIR/review-security.md."
-
-Task — Use the Task tool with subagent_type="deepreview-architecture":
-"You are reviewing $INPUT_DESCRIPTION. Read the content at $SESSION_DIR/input.txt. Write your review to $SESSION_DIR/review-architecture.md."
-
-Task — Use the Task tool with subagent_type="deepreview-docs":
-"You are reviewing $INPUT_DESCRIPTION. Read the content at $SESSION_DIR/input.txt. Write your review to $SESSION_DIR/review-docs.md."
-
-Task — Use the Task tool with subagent_type="deepreview-compatibility":
-"You are reviewing $INPUT_DESCRIPTION. Read the content at $SESSION_DIR/input.txt. Write your review to $SESSION_DIR/review-compatibility.md."
-
-Wait for all 5 to return. Record which succeeded and which failed.
-
-## STAGE 2: CROSS-VALIDATION (5 parallel tasks)
-
-Only proceed with reviews that exist. For each validator below, replace $REVIEW_FILE_LIST with ONLY the review files that were successfully created in Stage 1. If a review file failed, omit it from the list entirely. Dispatch validators simultaneously:
-
-Task — Use the Task tool with subagent_type="deepreview-validator":
-"Your perspective: correctness. Read all available review files at: $REVIEW_FILE_LIST. Also read the original input at $SESSION_DIR/input.txt for context. Write your validated review to $SESSION_DIR/validated-correctness.md."
-
-Task — Use the Task tool with subagent_type="deepreview-validator":
-"Your perspective: security. Read all available review files at: $REVIEW_FILE_LIST. Also read the original input at $SESSION_DIR/input.txt for context. Write your validated review to $SESSION_DIR/validated-security.md."
-
-Task — Use the Task tool with subagent_type="deepreview-validator":
-"Your perspective: architecture. Read all available review files at: $REVIEW_FILE_LIST. Also read the original input at $SESSION_DIR/input.txt for context. Write your validated review to $SESSION_DIR/validated-architecture.md."
-
-Task — Use the Task tool with subagent_type="deepreview-validator":
-"Your perspective: docs. Read all available review files at: $REVIEW_FILE_LIST. Also read the original input at $SESSION_DIR/input.txt for context. Write your validated review to $SESSION_DIR/validated-docs.md."
-
-Task — Use the Task tool with subagent_type="deepreview-validator":
-"Your perspective: compatibility. Read all available review files at: $REVIEW_FILE_LIST. Also read the original input at $SESSION_DIR/input.txt for context. Write your validated review to $SESSION_DIR/validated-compatibility.md."
-
-Wait for all 5 to return.
-
-## STAGE 3: SYNTHESIS (1 task)
-
-Task — Use the Task tool with subagent_type="deepreview-synthesizer":
-"Read the validated reviews at: $SESSION_DIR/validated-correctness.md, $SESSION_DIR/validated-security.md, $SESSION_DIR/validated-architecture.md, $SESSION_DIR/validated-docs.md, $SESSION_DIR/validated-compatibility.md (skip any that don't exist). Write the synthesis to $SESSION_DIR/synthesis.md."
-
-Record the stats line from its return.