issuewatcher-mcp 0.2.3 → 0.2.5

package/README.md

@@ -1,6 +1,6 @@
 # IssueWatcher for your AI assistant
 
-**Ask your AI assistant "What should I work on today?" and get back the GitHub issues that are actually worth your time, with the reason for each.**
+**Ask your AI assistant "What GitHub issues should I work on today?" and get back the GitHub issues that are actually worth your time, with the reason for each.**
 
 IssueWatcher is an [MCP](https://modelcontextprotocol.io) server. It watches the repositories you starred and the open-source libraries your own projects depend on, ranks their newest issues, and explains every score. It works inside Claude, Cursor, VS Code and other apps that support MCP.
 
@@ -133,20 +133,22 @@ You should see:
   [ok]   API budget: 4994 of 5000 requests left (resets ...).
   [ok]   Watching 51 repos: 16 starred, 35 from libraries your projects use (7.2s).
 
-All good. Add this server to your AI app, then ask: "What should I work on today?"
+All good. Add this server to your AI app, then ask: "What GitHub issues should I work on today?"
 ```
 
 ### 4. Ask
 
 Restart your AI app, then try:
 
-- *"What should I work on today?"*
+- *"What GitHub issues should I work on today?"*
 - *"Show me good first issues from the last 24 hours."*
 - *"What broke in my dependencies this week?"*
 - *"Why did you rank the first one so high?"*
 - *"Only show issues in nodejs/node and pydantic/pydantic."*
 - *"What repos are you watching for me?"*
 
+**If your AI answers with general advice instead of using IssueWatcher**, nudge it: add "use IssueWatcher" to the question (*"What GitHub issues should I work on today? Use IssueWatcher."*), or pick **IssueWatcher** from the tools or prompts menu of the chat box. Some apps decide on their own whether a question needs a connected tool, and a vague one like "what should I work on today?" can sound like a request for life advice. Mentioning GitHub or issues usually removes the doubt.
+
 IssueWatcher starts loading your repositories as soon as your AI app starts it, so by the time you type your first question the answer is usually instant. If you ask within the first few seconds it may take 10 to 20 seconds (longer on a slow connection); follow-up questions are instant for the next thirty minutes. It looks at the 20 newest issues per repository in the time window.
 
 ## What the assistant can do (the tools)
@@ -164,7 +166,7 @@ There is also a prompt, `issue_radar`, that some apps show as a shortcut.
 Every issue gets a score from 0 to 100 from transparent rules, each with a reason you can read:
 
 - **Why it is on your radar:** a repo you starred, or a library one of your projects depends on (runtime counts more than dev tools).
-- **Could you pick it up?** `good first issue` or `help wanted` labels, unassigned, opened recently, few comments, reproduction steps. Issues already assigned, claimed by a team, or where the reporter says they are opening a PR are scored down.
+- **Could you pick it up?** `good first issue` or `help wanted` labels, unassigned, opened recently, few comments, reproduction steps. Issues already assigned, claimed by a team, or where the reporter says they are opening a PR are scored down. Newer issues rank higher, and an issue with no reply and no taker after two weeks, or a feature request nobody has answered, is scored down.
 - **Could it break you?** the issue mentions a version in your range, or words like crash, regression, CVE.
 - **Noise is scored down:** bots, questions, duplicates, vague or throwaway titles.
 

package/build/deps/discovery.js

@@ -75,16 +75,16 @@ export async function discoverDependencies(source, registry, opts, now = Date.no
         .slice(0, opts.maxDependencies);
     let lookupFailures = 0;
     const lookupsEnd = Date.now() + (opts.registryBudgetMs ?? 8_000);
-    const resolved = await inPool(ranked, 12, async (dep) => {
+    const lookup = async (dep) => {
         let timer;
         try {
             const remaining = Math.max(0, lookupsEnd - Date.now());
             const budget = new Promise((_, reject) => {
                 timer = setTimeout(() => reject(new Error("registry lookups ran out of time")), remaining);
             });
-            const lookup = registry.resolve(dep.ecosystem, dep.pkg);
-            lookup.catch(() => undefined); // the race may already be lost; a late failure is not news
-            return await Promise.race([lookup, budget]);
+            const pending = registry.resolve(dep.ecosystem, dep.pkg);
+            pending.catch(() => undefined); // the race may already be lost; a late failure is not news
+            return await Promise.race([pending, budget]);
         }
         catch (err) {
             lookupFailures++;
@@ -94,7 +94,18 @@ export async function discoverDependencies(source, registry, opts, now = Date.no
         finally {
             clearTimeout(timer);
         }
+    };
+    // One pool per registry: a slow PyPI must not hold the slots that npm lookups need (D-053).
+    const resolved = new Array(ranked.length).fill(null);
+    const byEcosystem = new Map();
+    ranked.forEach((dep, index) => {
+        const group = byEcosystem.get(dep.ecosystem) ?? [];
+        group.push({ dep, index });
+        byEcosystem.set(dep.ecosystem, group);
     });
+    await Promise.all([...byEcosystem.entries()].map(([ecosystem, group]) => inPool(group, ecosystem === "npm" ? 10 : 4, async ({ dep, index }) => {
+        resolved[index] = await lookup(dep);
+    })));
     const map = {};
     ranked.forEach((dep, i) => {
         const repo = resolved[i];

package/build/mcp/diagnose.js

@@ -65,6 +65,6 @@ export async function runCheck(settings, problems, version, write = (l) => conso
         return 1;
     }
     write(`\nMode: ${settings.mode}. Cache folder: ${settings.cacheDir}`);
-    write(failed ? "\nSetup needs attention (see above)." : "\nAll good. Add this server to your AI app, then ask: \"What should I work on today?\"");
+    write(failed ? "\nSetup needs attention (see above)." : "\nAll good. Add this server to your AI app, then ask: \"What GitHub issues should I work on today?\"");
     return failed ? 1 : 0;
 }

package/build/scoring/score.js

@@ -20,6 +20,13 @@ const LABEL_NOISE = /\b(question|support|docs?|documentation|stale|discussion)\b
 const LABEL_NOISE_CONTRIBUTOR = /\b(question|support|stale|discussion)\b/i;
 const LABEL_EASY = /(good[ -]first[ -]issue|beginner|starter|easy|first[ -]timers?)/i;
 const LABEL_HELP = /(help[ -]wanted|hacktoberfest|contributions?[ -]welcome)/i;
+/** A request for new behaviour ("[Feature]: ...", "Feature Request: ..."), as opposed to a report of something broken. */
+const PROPOSAL_TITLE = /^\s*\[?\s*(?:feature|proposal|rfc|enhancement)\b[^\]:]*\]?\s*[:-]|\bfeature request\b/i;
+const DAY_H = 24;
+/** Work for the maintainers (CI, releases, bots), not a problem for users and not a task for an outside contributor. */
+const MAINTENANCE_TITLE = /^\s*(?:chore|ci|build)(?:\([^)]*\))?\s*:|\b(?:trusted publishing|release workflow|github actions?|dependabot|renovate)\b/i;
+/** "docs: ..." and "docs(scope): ..." conventional-commit style titles. */
+const DOCS_TITLE = /^\s*docs?(?:\([^)]*\))?\s*:/i;
 const REPRO = /(steps to reproduce|expected (?:behaviou?r|result)|actual (?:behaviou?r|result)|traceback|stack ?trace|minimal reproduc|reproduction)/i;
 const HOUR_MS = 3_600_000;
 const TEST_WORK = /\b(tests?|testing|suite)\b/i;
@@ -196,6 +203,12 @@ export function scoreIssueDetailed(issue, target, opts = {}) {
     if (severity > severityCap) {
         add(severityCap - severity, "severity-cap", undefined, `severity capped at ${severityCap}${devOnly ? " (dev dependency)" : ""}`);
     }
+    if (MAINTENANCE_TITLE.test(issue.title)) {
+        add(-15, "maintenance", "maintenance task for the maintainers");
+    }
+    else if (consumer && !contributor && DOCS_TITLE.test(issue.title)) {
+        add(-10, "docs-title", "documentation issue");
+    }
     // Dismissals and noise.
     if (LABEL_DISMISSED.test(labels)) {
         add(-25, "dismissed-label", "marked duplicate/invalid");
@@ -241,9 +254,22 @@ export function scoreIssueDetailed(issue, target, opts = {}) {
         else {
             add(10, "unassigned", "unassigned");
         }
+        // Newer is better to pick up; an issue nobody has answered or taken for two weeks is probably not wanted (D-051).
         const ageH = (now - Date.parse(issue.createdAt)) / HOUR_MS;
-        if (Number.isFinite(ageH) && ageH >= 0 && ageH <= 48) {
-            add(10, "fresh", ageH < 1 ? "opened just now" : `opened ${Math.floor(ageH)}h ago`);
+        if (Number.isFinite(ageH) && ageH >= 0) {
+            if (ageH <= 48) {
+                add(10, "fresh", ageH < 1 ? "opened just now" : `opened ${Math.floor(ageH)}h ago`);
+            }
+            else if (ageH <= 7 * DAY_H) {
+                add(5, "recent", "opened this week");
+            }
+            else if (ageH > 14 * DAY_H && issue.comments === 0 && issue.assignees === 0) {
+                add(-10, "stale", `open ${Math.floor(ageH / DAY_H)} days with no replies`);
+            }
+        }
+        // A proposal nobody has answered yet needs a maintainer's yes before it is worth starting.
+        if (PROPOSAL_TITLE.test(issue.title) && issue.comments === 0 && !LABEL_EASY.test(labels) && !LABEL_HELP.test(labels)) {
+            add(-10, "unanswered-proposal", "feature request nobody has answered yet");
         }
         // Work that is already taken is not something to pick up.
         if (LABEL_CLAIMED.test(labels)) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "issuewatcher-mcp",
-  "version": "0.2.3",
+  "version": "0.2.5",
   "description": "MCP server that ranks new GitHub issues for your AI assistant: what to pick up, and what may break your projects.",
   "mcpName": "io.github.mac146/issuewatcher",
   "license": "MIT",