feat(miner): implement generic ContributionProfile extraction

packages/loopover-miner/lib/contribution-profile-extract.d.ts

@@ -0,0 +1,17 @@
+import type { ContributionProfile } from "./contribution-profile.js";
+
+/**
+ * Extract a best-effort ContributionProfile for a repo from its published label taxonomy and contribution docs.
+ * Never throws: any fetch/parse failure degrades the relevant signal to `absent`/`unknown`. Generic — no
+ * loopover-specific hardcoding.
+ */
+export function extractContributionProfile(
+  repoFullName: string,
+  options?: {
+    fetchImpl?: typeof fetch;
+    githubToken?: string;
+    apiBaseUrl?: string;
+    /** ISO timestamp for the profile's generatedAt; defaults to now. Injected so tests stay deterministic. */
+    generatedAt?: string;
+  },
+): Promise<ContributionProfile>;

packages/loopover-miner/lib/contribution-profile-extract.js

@@ -0,0 +1,246 @@
+// ContributionProfile extraction (#6796). Reads a repo's real, published signals — label taxonomy + contribution
+// docs — and produces a populated ContributionProfile per the #6795 schema. GENERIC by design: it recognizes
+// conventional OSS eligibility/exclusion vocabulary and matches over label name AND description, with NO
+// loopover-specific keyword hardcoding (the #6794 inventory found loopover's own `gittensor:*` labels are the
+// exception, not the shape to generalize from). Never throws: any fetch/parse failure degrades a signal to
+// `absent`/`unknown` rather than erroring, so an unreachable or docs-less repo yields a low-confidence profile.
+import {
+  CONTRIBUTION_PROFILE_SCHEMA_VERSION,
+  emptyContributionProfile,
+  weakestConfidence,
+} from "./contribution-profile.js";
+
+const DEFAULT_API_BASE_URL = "https://api.github.com";
+const GITHUB_API_VERSION = "2022-11-28";
+const REQUEST_TIMEOUT_MS = 10_000;
+/** A CONTRIBUTING.md smaller than this is treated as a signpost (a link to an external guide), not the rules
+ *  themselves — #6794 found react's is 208 B and kubernetes' 525 B, both just pointers. */
+const CONTRIBUTING_SIGNPOST_MAX_BYTES = 600;
+
+/** Canonical eligibility vocabulary — recognized OSS "contributor-workable" conventions. Matched case-insensitively
+ *  as a substring over a label's name AND description. Not loopover-specific. */
+const ELIGIBILITY_TERMS = Object.freeze([
+  "good first issue",
+  "good-first-issue",
+  "help wanted",
+  "help-wanted",
+  "up for grabs",
+  "beginner",
+  "easy",
+  "starter",
+]);
+
+/** Conventional exclusion/off-limits vocabulary. These are UNstated conventions (#6794 found no repo names
+ *  exclusion in a label NAME explicitly), so a match yields `inferred`, never `explicit`. */
+const EXCLUSION_TERMS = Object.freeze([
+  "blocked",
+  "on hold",
+  "on-hold",
+  "do not merge",
+  "wontfix",
+  "invalid",
+  "needs triage",
+  "work in progress",
+  "wip",
+  "maintainer only",
+  "internal",
+]);
+
+/** Closing-keyword / linked-issue language in a CONTRIBUTING.md. */
+const LINKED_ISSUE_TERMS = Object.freeze([
+  "closes #",
+  "fixes #",
+  "resolves #",
+  "linked issue",
+  "reference an issue",
+  "link to an issue",
+]);
+
+/** @param {string} repoFullName @returns {{owner:string,repo:string}|null} */
+function parseRepoFullName(repoFullName) {
+  if (typeof repoFullName !== "string") return null;
+  const [owner, repo, extra] = repoFullName.split("/");
+  if (!owner?.trim() || !repo?.trim() || extra !== undefined) return null;
+  return { owner: owner.trim(), repo: repo.trim() };
+}
+
+/** @param {string|undefined} githubToken */
+function githubHeaders(githubToken) {
+  const headers = {
+    accept: "application/vnd.github+json",
+    "user-agent": "loopover-miner",
+    "x-github-api-version": GITHUB_API_VERSION,
+  };
+  if (githubToken) headers.authorization = `Bearer ${githubToken}`;
+  return headers;
+}
+
+/** Bounded, never-throwing JSON GET. Returns null on any transport/HTTP/parse failure. */
+async function getJson(url, headers, fetchImpl) {
+  let response;
+  try {
+    response = await fetchImpl(url, {
+      method: "GET",
+      headers,
+      signal: AbortSignal.timeout(REQUEST_TIMEOUT_MS),
+    });
+  } catch {
+    return null;
+  }
+  if (!response.ok) return null;
+  return response.json().catch(() => null);
+}
+
+/**
+ * Match one label against a term list, preferring the NAME but falling back to the DESCRIPTION (the rust
+ * `E-easy` finding: a label can carry its eligibility meaning only in the description). Returns the matcher +
+ * a provenance detail, or null when neither field matches.
+ */
+function matchLabel(label, terms) {
+  const rawName = typeof label?.name === "string" ? label.name : "";
+  const name = rawName.toLowerCase();
+  const description =
+    typeof label?.description === "string"
+      ? label.description.toLowerCase()
+      : "";
+  const detail = rawName || "(unnamed label)";
+  const nameTerm = terms.find((term) => name.includes(term));
+  if (nameTerm !== undefined)
+    return { matcher: { field: "name", contains: nameTerm }, detail };
+  const descriptionTerm = terms.find((term) => description.includes(term));
+  if (descriptionTerm !== undefined)
+    return {
+      matcher: { field: "description", contains: descriptionTerm },
+      detail,
+    };
+  return null;
+}
+
+/** Classify labels into a SignalRule of the given confidence. Recognized labels build an OR-list of matchers;
+ *  no match ⇒ `absent`. Eligibility passes `explicit` (a recognized convention IS an explicit statement);
+ *  exclusion passes `inferred` (conventional but unstated). */
+function classifyLabels(labels, terms, matchedConfidence) {
+  const matchers = [];
+  const provenance = [];
+  for (const label of labels) {
+    const hit = matchLabel(label, terms);
+    if (hit === null) continue;
+    matchers.push(hit.matcher);
+    provenance.push({ source: "labels", detail: hit.detail });
+  }
+  if (matchers.length === 0)
+    return { value: null, confidence: "absent", provenance: [] };
+  return { value: matchers, confidence: matchedConfidence, provenance };
+}
+
+/** Decode a GitHub contents API response body to text. Returns null when absent or not base64. Buffer.from over
+ *  a string never throws, so no error path is needed here. */
+function decodeContents(payload) {
+  if (
+    !payload ||
+    typeof payload.content !== "string" ||
+    payload.encoding !== "base64"
+  )
+    return null;
+  return Buffer.from(payload.content, "base64").toString("utf8");
+}
+
+/** Fetch CONTRIBUTING.md, probing the repo root then `.github/` (#6794: 6/10 at root, 2/10 under `.github/`). */
+async function fetchContributing(base, target, headers, fetchImpl) {
+  for (const path of ["CONTRIBUTING.md", ".github/CONTRIBUTING.md"]) {
+    const payload = await getJson(
+      `${base}/repos/${target.owner}/${target.repo}/contents/${path}`,
+      headers,
+      fetchImpl,
+    );
+    const text = decodeContents(payload);
+    if (text !== null) return text;
+  }
+  return null;
+}
+
+/** Extract the PR-body linked-issue requirement from CONTRIBUTING.md. A very small file is a signpost, not the
+ *  rules, so it yields `absent` rather than a false negative dressed as a real one. */
+function extractPrBody(contributing) {
+  if (contributing === null)
+    return { value: null, confidence: "absent", provenance: [] };
+  if (contributing.length < CONTRIBUTING_SIGNPOST_MAX_BYTES)
+    return { value: null, confidence: "unknown", provenance: [] };
+  const lower = contributing.toLowerCase();
+  const requiresLinkedIssue = LINKED_ISSUE_TERMS.some((term) =>
+    lower.includes(term),
+  );
+  // A real, sufficiently-sized CONTRIBUTING.md is an explicit source either way: present-with-keyword is an
+  // explicit requirement, present-without is an explicit "no such rule".
+  return {
+    value: { requiresLinkedIssue },
+    confidence: "explicit",
+    provenance: [{ source: "contributing_md", detail: "CONTRIBUTING.md" }],
+  };
+}
+
+/**
+ * Extract a best-effort ContributionProfile for a repo from what it actually publishes.
+ *
+ * @param {string} repoFullName owner/repo
+ * @param {{ fetchImpl?: typeof fetch, githubToken?: string, apiBaseUrl?: string, generatedAt?: string }} [options]
+ * @returns {Promise<import("./contribution-profile.js").ContributionProfile>}
+ */
+export async function extractContributionProfile(repoFullName, options = {}) {
+  const generatedAt =
+    typeof options.generatedAt === "string"
+      ? options.generatedAt
+      : new Date().toISOString();
+  const target = parseRepoFullName(repoFullName);
+  // A malformed name can't be fetched — return the safe, fully-absent default rather than throwing.
+  if (target === null)
+    return emptyContributionProfile(
+      typeof repoFullName === "string" ? repoFullName : "",
+      generatedAt,
+    );
+
+  /* v8 ignore next -- the global-fetch default is the production path; every test injects fetchImpl. */
+  const fetchImpl = options.fetchImpl ?? fetch;
+  const base =
+    typeof options.apiBaseUrl === "string" && options.apiBaseUrl.trim()
+      ? options.apiBaseUrl.replace(/\/+$/, "")
+      : DEFAULT_API_BASE_URL;
+  const headers = githubHeaders(
+    options.githubToken ?? process.env.GITHUB_TOKEN,
+  );
+
+  const labelsPayload = await getJson(
+    `${base}/repos/${target.owner}/${target.repo}/labels?per_page=100`,
+    headers,
+    fetchImpl,
+  );
+  const labels = Array.isArray(labelsPayload) ? labelsPayload : [];
+  const contributing = await fetchContributing(
+    base,
+    target,
+    headers,
+    fetchImpl,
+  );
+
+  const eligibilityLabels = classifyLabels(
+    labels,
+    ELIGIBILITY_TERMS,
+    "explicit",
+  );
+  const exclusionLabels = classifyLabels(labels, EXCLUSION_TERMS, "inferred");
+  const prBody = extractPrBody(contributing);
+
+  return {
+    repoFullName: `${target.owner}/${target.repo}`,
+    schemaVersion: CONTRIBUTION_PROFILE_SCHEMA_VERSION,
+    generatedAt,
+    eligibilityLabels,
+    exclusionLabels,
+    prBody,
+    completeness: weakestConfidence([
+      eligibilityLabels.confidence,
+      exclusionLabels.confidence,
+      prBody.confidence,
+    ]),
+  };
+}

packages/loopover-miner/package.json

@@ -38,7 +38,7 @@
   "scripts": {
     "benchmark": "node scripts/benchmark.mjs",
     "cross-repo-eval": "node scripts/cross-repo-evaluation.mjs",
-    "build": "node --check bin/loopover-miner.js && node --check bin/loopover-miner-mcp.js && node --check lib/ams-policy.js && node --check lib/attempt-cli.js && node --check lib/attempt-input-builder.js && node --check lib/attempt-log.js && node --check lib/attempt-runner.js && node --check lib/attempt-worktree.js && node --check lib/calibration-run.js && node --check lib/calibration-types.js && node --check lib/calibration.js && node --check lib/chat-action-dispatch.js && node --check lib/chat-action-registry.js && node --check lib/chat-discover-attempt-actions.js && node --check lib/chat-governor-actions.js && node --check lib/chat-portfolio-actions.js && node --check lib/ci-poller.js && node --check lib/claim-adjudication.js && node --check lib/claim-conflict-resolver.js && node --check lib/claim-ledger-cli.js && node --check lib/claim-ledger-expiry.js && node --check lib/claim-ledger.js && node --check lib/cli.js && node --check lib/coding-agent-construction.js && node --check lib/coding-agent-house-rules.js && node --check lib/coding-task-spec.js && node --check lib/contribution-profile.js && node --check lib/cross-repo-evaluation.js && node --check lib/deny-check.js && node --check lib/deny-hook-synthesis.js && node --check lib/deny-hooks.js && node --check lib/deployment-docs-audit.js && node --check lib/discover-cli.js && node --check lib/event-ledger-cli.js && node --check lib/event-ledger.js && node --check lib/execute-local-write.js && node --check lib/feasibility-cli.js && node --check lib/governor-chokepoint-persisted.js && node --check lib/governor-chokepoint.js && node --check lib/governor-kill-switch.js && node --check lib/governor-ledger-cli.js && node --check lib/governor-ledger.js && node --check lib/governor-metrics-cli.js && node --check lib/governor-pause-cli.js && node --check lib/governor-run-halt.js && node --check lib/governor-state.js && node --check lib/harness-submission-trigger.js && node --check lib/init-wizard.js && node --check lib/laptop-init.js && node --check lib/live-issue-snapshot.js && node --check lib/local-store.js && node --check lib/logger.js && node --check lib/loop-cli.js && node --check lib/loop-closure.js && node --check lib/loop-reentry.js && node --check lib/manage-poll.js && node --check lib/manage-status.js && node --check lib/metrics-cli.js && node --check lib/miner-goal-spec.js && node --check lib/opportunity-fanout.js && node --check lib/opportunity-ranker.js && node --check lib/orb-export.js && node --check lib/plan-store-cli.js && node --check lib/plan-store.js && node --check lib/policy-doc-cache.js && node --check lib/policy-verdict-cache.js && node --check lib/portfolio-dashboard.js && node --check lib/portfolio-discovery.js && node --check lib/portfolio-queue-cli.js && node --check lib/portfolio-queue-manager.js && node --check lib/portfolio-queue.js && node --check lib/portfolio-queue-expiry.js && node --check lib/pr-disposition-poller.js && node --check lib/pr-number-parse.js && node --check lib/pr-outcome.js && node --check lib/prediction-ledger.js && node --check lib/pretooluse-hook.js && node --check lib/purge-cli.js && node --check lib/ranked-candidates.js && node --check lib/rejection-signal.js && node --check lib/rejection-state-machine.js && node --check lib/rejection-templates.js && node --check lib/replay-objective-anchor.js && node --check lib/replay-snapshot.js && node --check lib/replay-task-bridge.js && node --check lib/replay-task-generation.js && node --check lib/repo-clone.js && node --check lib/run-state-cli.js && node --check lib/run-state.js && node --check lib/self-review-context.js && node --check lib/sentry.js && node --check lib/slop-assessment.js && node --check lib/stack-detection.js && node --check lib/status.js && node --check lib/submission-freshness-check.js && node --check lib/update-check.js && node --check lib/version.js && node --check lib/worktree-allocator.js"
+    "build": "node --check bin/loopover-miner.js && node --check bin/loopover-miner-mcp.js && node --check lib/ams-policy.js && node --check lib/attempt-cli.js && node --check lib/attempt-input-builder.js && node --check lib/attempt-log.js && node --check lib/attempt-runner.js && node --check lib/attempt-worktree.js && node --check lib/calibration-run.js && node --check lib/calibration-types.js && node --check lib/calibration.js && node --check lib/chat-action-dispatch.js && node --check lib/chat-action-registry.js && node --check lib/chat-discover-attempt-actions.js && node --check lib/chat-governor-actions.js && node --check lib/chat-portfolio-actions.js && node --check lib/ci-poller.js && node --check lib/claim-adjudication.js && node --check lib/claim-conflict-resolver.js && node --check lib/claim-ledger-cli.js && node --check lib/claim-ledger-expiry.js && node --check lib/claim-ledger.js && node --check lib/cli.js && node --check lib/coding-agent-construction.js && node --check lib/coding-agent-house-rules.js && node --check lib/coding-task-spec.js && node --check lib/contribution-profile.js && node --check lib/contribution-profile-extract.js && node --check lib/cross-repo-evaluation.js && node --check lib/deny-check.js && node --check lib/deny-hook-synthesis.js && node --check lib/deny-hooks.js && node --check lib/deployment-docs-audit.js && node --check lib/discover-cli.js && node --check lib/event-ledger-cli.js && node --check lib/event-ledger.js && node --check lib/execute-local-write.js && node --check lib/feasibility-cli.js && node --check lib/governor-chokepoint-persisted.js && node --check lib/governor-chokepoint.js && node --check lib/governor-kill-switch.js && node --check lib/governor-ledger-cli.js && node --check lib/governor-ledger.js && node --check lib/governor-metrics-cli.js && node --check lib/governor-pause-cli.js && node --check lib/governor-run-halt.js && node --check lib/governor-state.js && node --check lib/harness-submission-trigger.js && node --check lib/init-wizard.js && node --check lib/laptop-init.js && node --check lib/live-issue-snapshot.js && node --check lib/local-store.js && node --check lib/logger.js && node --check lib/loop-cli.js && node --check lib/loop-closure.js && node --check lib/loop-reentry.js && node --check lib/manage-poll.js && node --check lib/manage-status.js && node --check lib/metrics-cli.js && node --check lib/miner-goal-spec.js && node --check lib/opportunity-fanout.js && node --check lib/opportunity-ranker.js && node --check lib/orb-export.js && node --check lib/plan-store-cli.js && node --check lib/plan-store.js && node --check lib/policy-doc-cache.js && node --check lib/policy-verdict-cache.js && node --check lib/portfolio-dashboard.js && node --check lib/portfolio-discovery.js && node --check lib/portfolio-queue-cli.js && node --check lib/portfolio-queue-manager.js && node --check lib/portfolio-queue.js && node --check lib/portfolio-queue-expiry.js && node --check lib/pr-disposition-poller.js && node --check lib/pr-number-parse.js && node --check lib/pr-outcome.js && node --check lib/prediction-ledger.js && node --check lib/pretooluse-hook.js && node --check lib/purge-cli.js && node --check lib/ranked-candidates.js && node --check lib/rejection-signal.js && node --check lib/rejection-state-machine.js && node --check lib/rejection-templates.js && node --check lib/replay-objective-anchor.js && node --check lib/replay-snapshot.js && node --check lib/replay-task-bridge.js && node --check lib/replay-task-generation.js && node --check lib/repo-clone.js && node --check lib/run-state-cli.js && node --check lib/run-state.js && node --check lib/self-review-context.js && node --check lib/sentry.js && node --check lib/slop-assessment.js && node --check lib/stack-detection.js && node --check lib/status.js && node --check lib/submission-freshness-check.js && node --check lib/update-check.js && node --check lib/version.js && node --check lib/worktree-allocator.js"
   },
   "dependencies": {
     "@loopover/engine": "^3.0.0",