Convert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research into a persistent, searchable wiki that builds on itself. Hosted API + MCP: hyperresearch.ai
Python agentsagentskillscitationsclaude-codecodexcodex-plugincodex-skilldeep-researchdeep-research-agentdeepresearchmcp-serverresearchresearch-agentresearch-tools
ruff: clean lint failures in v0.5.0 changeset
Jordan8d870ce52252
diff --git a/src/hyperresearch/cli/fetch.py b/src/hyperresearch/cli/fetch.pyindex 9ec78f0..6e0e91d 100644--- a/src/hyperresearch/cli/fetch.py+++ b/src/hyperresearch/cli/fetch.py@@ -145,7 +145,6 @@ def _detect_content_type(url: str, raw_content_type: str | None = None) -> str:"""if raw_content_type and "pdf" in raw_content_type.lower():return "paper"- u = url.lower()domain = urlparse(url).netloc.lower()path = urlparse(url).path.lower()@@ -160,7 +159,7 @@ def _detect_content_type(url: str, raw_content_type: str | None = None) -> str:return "code"# Dataset portals that happen to live on .gov domains must win first- if domain in ("data.gov", "data.gov.uk") or domain.startswith("data.") and (domain.endswith(".gov") or domain.endswith(".gov.uk") or domain.endswith(".europa.eu")):+ if domain in ("data.gov", "data.gov.uk") or (domain.startswith("data.") and (domain.endswith(".gov") or domain.endswith(".gov.uk") or domain.endswith(".europa.eu"))):return "dataset"# Policy: gov domains, EU, regulator sitesdiff --git a/src/hyperresearch/cli/lint.py b/src/hyperresearch/cli/lint.pyindex 4ebcd88..f278204 100644--- a/src/hyperresearch/cli/lint.py+++ b/src/hyperresearch/cli/lint.py@@ -185,8 +185,8 @@ def lint("severity": "error","note_id": "<vault>","message": (- f"Most recent conformance audit returned status=failed. "- f"Investigate the findings and re-run the auditor."+ "Most recent conformance audit returned status=failed. "+ "Investigate the findings and re-run the auditor."),})@@ -230,7 +230,7 @@ def lint(# broad — false matches are fine (they cause a re-check# which passes harmlessly); missing a match is the failure# mode we're guarding against.- _KW_TO_RULE = [+ kw_to_rule = [# scaffold-prompt (verbatim prompt gospel rule)("scaffold-prompt", "scaffold-prompt"),("scaffold_prompt", "scaffold-prompt"),@@ -305,7 +305,7 @@ def lint(desc = (str(c.get("description", "")) + " " +str(c.get("id", ""))).lower()matched = None- for kw, rule_name in _KW_TO_RULE:+ for kw, rule_name in kw_to_rule:if kw in desc:matched = rule_namebreakdiff --git a/src/hyperresearch/cli/note.py b/src/hyperresearch/cli/note.pyindex 9f668f8..a3d8ba9 100644--- a/src/hyperresearch/cli/note.py+++ b/src/hyperresearch/cli/note.py@@ -178,8 +178,8 @@ def note_show(data = {"id": row["id"], "title": row["title"], "path": row["path"],"status": row["status"], "type": row["type"], "tags": tags,- "tier": row["tier"] if "tier" in row.keys() else None,- "content_type": row["content_type"] if "content_type" in row.keys() else None,+ "tier": row["tier"] if "tier" in row else None, # noqa: SIM401 (sqlite3.Row has no .get())+ "content_type": row["content_type"] if "content_type" in row else None, # noqa: SIM401"created": row["created"], "updated": row["updated"],"word_count": row["word_count"], "source": row["source"],"parent": row["parent"], "summary": row["summary"],@@ -343,8 +343,8 @@ def note_list("path": row["path"],"status": row["status"],"type": row["type"],- "tier": row["tier"] if "tier" in row.keys() else None,- "content_type": row["content_type"] if "content_type" in row.keys() else None,+ "tier": row["tier"] if "tier" in row else None, # noqa: SIM401 (sqlite3.Row has no .get())+ "content_type": row["content_type"] if "content_type" in row else None, # noqa: SIM401"tags": tag_list,"word_count": row["word_count"],"summary": row["summary"],@@ -548,6 +548,7 @@ def note_rm(- any entries in the `assets` table and their files on disk"""import shutil+from hyperresearch.core.vault import Vaultvault = Vault.discover()diff --git a/src/hyperresearch/core/patterns.py b/src/hyperresearch/core/patterns.pyindex 174b660..926ccd4 100644--- a/src/hyperresearch/core/patterns.py+++ b/src/hyperresearch/core/patterns.py@@ -88,6 +88,4 @@ def is_valid_wiki_link_target(ref: str) -> bool:return Falseif _SYMBOL_FOOTNOTE_RE.match(ref):return False- if _DOC_REF_PREFIX_RE.match(ref):- return False- return True+ return not _DOC_REF_PREFIX_RE.match(ref)diff --git a/src/hyperresearch/search/fts.py b/src/hyperresearch/search/fts.pyindex c5602a9..a696f08 100644--- a/src/hyperresearch/search/fts.py+++ b/src/hyperresearch/search/fts.py@@ -113,8 +113,8 @@ def search_fts("path": row["path"],"status": row["status"],"type": row["type"],- "tier": row["tier"] if "tier" in row.keys() else None,- "content_type": row["content_type"] if "content_type" in row.keys() else None,+ "tier": row["tier"] if "tier" in row else None, # noqa: SIM401 (sqlite3.Row has no .get())+ "content_type": row["content_type"] if "content_type" in row else None, # noqa: SIM401"tags": tag_list,"created": row["created"],"updated": row["updated"],diff --git a/src/hyperresearch/web/crawl4ai_provider.py b/src/hyperresearch/web/crawl4ai_provider.pyindex fca0fe2..6ee3623 100644--- a/src/hyperresearch/web/crawl4ai_provider.py+++ b/src/hyperresearch/web/crawl4ai_provider.py@@ -33,7 +33,7 @@ if sys.platform == "win32":def _is_pdf_url(url: str) -> bool:"""Check if URL likely points to a PDF."""- from urllib.parse import urlparse, parse_qs+ from urllib.parse import urlparseparsed = urlparse(url.lower())path = parsed.path@@ -44,9 +44,7 @@ def _is_pdf_url(url: str) -> bool:if "/pdf/" in path or "/pdfs/" in path:return True# arXiv PDF links- if "arxiv.org" in parsed.netloc and ("/pdf/" in path or "/abs/" in path):- return True- return False+ return "arxiv.org" in parsed.netloc and ("/pdf/" in path or "/abs/" in path)def _looks_like_binary(text: str) -> bool:@@ -58,10 +56,10 @@ def _looks_like_binary(text: str) -> bool:pdf_markers = ("endstream", "endobj", "/Filter", "/FlateDecode", "stream\nx", "%PDF-")if any(m in sample for m in pdf_markers):return True- # High ratio of actual binary/control chars — do NOT flag ord(c) > 127, as that would+ # High ratio of actual binary/control chars - do NOT flag ord(c) > 127, as that would# falsely reject valid CJK, Arabic, Cyrillic, and other non-ASCII text.# Only flag: true control chars (< 0x20, excluding normal whitespace), the Unicode- # replacement character (U+FFFD from bad decoding), and C1 controls (0x80–0x9F).+ # replacement character (U+FFFD from bad decoding), and C1 controls (0x80-0x9F).def _is_garbage(c: str) -> bool:o = ord(c)return (o < 0x20 and c not in '\t\n\r\f\v') or c == '\ufffd' or (0x80 <= o <= 0x9F)diff --git a/tests/test_cli/test_lint.py b/tests/test_cli/test_lint.pyindex dace659..1d1d94a 100644--- a/tests/test_cli/test_lint.py+++ b/tests/test_cli/test_lint.py@@ -2,7 +2,6 @@from __future__ import annotations-import pytestfrom typer.testing import CliRunnerfrom hyperresearch.cli.lint import app as lint_app@@ -68,7 +67,7 @@ def test_scaffold_prompt_fails_when_header_missing(tmp_vault):"1. Cosmology\n"),)- code, out = _run_lint(tmp_vault, rule="scaffold-prompt")+ _, out = _run_lint(tmp_vault, rule="scaffold-prompt")import jsondata = json.loads(out)issues = data.get("data", {}).get("issues", [])@@ -88,7 +87,7 @@ def test_scaffold_prompt_warns_when_quote_too_short(tmp_vault):"- thing\n"),)- code, out = _run_lint(tmp_vault, rule="scaffold-prompt")+ _, out = _run_lint(tmp_vault, rule="scaffold-prompt")import jsondata = json.loads(out)issues = data.get("data", {}).get("issues", [])@@ -131,7 +130,7 @@ def test_provenance_rooted_tree_passes_with_valid_chain(tmp_vault):_write_source(tmp_vault, "Child C", "child-c", body="*Suggested by [[seed-two]] — reply*\n\nCritical response.")tmp_vault.auto_sync()- code, out = _run_lint(tmp_vault, rule="provenance")+ _, out = _run_lint(tmp_vault, rule="provenance")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "provenance"]@@ -144,7 +143,7 @@ def test_provenance_fails_when_all_sources_are_seeds(tmp_vault):_write_source(tmp_vault, f"Source {i}", f"source-{i}")tmp_vault.auto_sync()- code, out = _run_lint(tmp_vault, rule="provenance")+ _, out = _run_lint(tmp_vault, rule="provenance")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "provenance"]@@ -162,7 +161,7 @@ def test_provenance_fails_on_dangling_breadcrumb(tmp_vault):_write_source(tmp_vault, "Child D", "child-d", body="*Suggested by [[seed-one]] — real*\n")tmp_vault.auto_sync()- code, out = _run_lint(tmp_vault, rule="provenance")+ _, out = _run_lint(tmp_vault, rule="provenance")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "provenance"]@@ -177,7 +176,7 @@ def test_provenance_small_corpus_is_skipped(tmp_vault):_write_source(tmp_vault, f"Source {i}", f"source-{i}")tmp_vault.auto_sync()- code, out = _run_lint(tmp_vault, rule="provenance")+ _, out = _run_lint(tmp_vault, rule="provenance")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "provenance"]@@ -200,7 +199,7 @@ def test_provenance_errors_on_under_30pct_non_seed_ratio(tmp_vault):_write_source(tmp_vault, f"Source {i}", f"source-{i}", body=body)tmp_vault.auto_sync()- code, out = _run_lint(tmp_vault, rule="provenance")+ _, out = _run_lint(tmp_vault, rule="provenance")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "provenance"]@@ -217,7 +216,7 @@ def test_orphaned_raw_files_flags_disk_leak(tmp_vault):(raw_dir / "orphan-note.pdf").write_bytes(b"%PDF-1.4 dummy")tmp_vault.auto_sync()- code, out = _run_lint(tmp_vault, rule="orphaned-raw-files")+ _, out = _run_lint(tmp_vault, rule="orphaned-raw-files")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "orphaned-raw-files"]@@ -258,7 +257,7 @@ def test_audit_gate_blocks_unresolved_criticals(tmp_vault):}]})- code, out = _run_lint(tmp_vault, rule="audit-gate")+ _, out = _run_lint(tmp_vault, rule="audit-gate")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "audit-gate"]@@ -284,7 +283,7 @@ def test_audit_gate_passes_when_all_criticals_fixed(tmp_vault):}]})- code, out = _run_lint(tmp_vault, rule="audit-gate")+ _, out = _run_lint(tmp_vault, rule="audit-gate")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "audit-gate"]@@ -320,7 +319,7 @@ def test_audit_gate_uses_most_recent_conformance_run(tmp_vault):},]})- code, out = _run_lint(tmp_vault, rule="audit-gate")+ _, out = _run_lint(tmp_vault, rule="audit-gate")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "audit-gate"]@@ -344,7 +343,7 @@ def test_audit_gate_fails_when_only_comprehensiveness_run_exists(tmp_vault):}]})- code, out = _run_lint(tmp_vault, rule="audit-gate")+ _, out = _run_lint(tmp_vault, rule="audit-gate")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "audit-gate"]@@ -375,7 +374,7 @@ def test_audit_gate_surfaces_important_findings_as_info(tmp_vault):}]})- code, out = _run_lint(tmp_vault, rule="audit-gate")+ _, out = _run_lint(tmp_vault, rule="audit-gate")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "audit-gate"]@@ -423,7 +422,7 @@ def test_audit_gate_catches_self_certification_on_provenance(tmp_vault):]})- code, out = _run_lint(tmp_vault, rule="audit-gate")+ _, out = _run_lint(tmp_vault, rule="audit-gate")import jsondata = json.loads(out)issues = data.get("data", {}).get("issues", [])@@ -471,7 +470,7 @@ def test_audit_gate_no_self_cert_when_fix_genuinely_landed(tmp_vault):]})- code, out = _run_lint(tmp_vault, rule="audit-gate")+ _, out = _run_lint(tmp_vault, rule="audit-gate")import jsondata = json.loads(out)issues = data.get("data", {}).get("issues", [])@@ -486,7 +485,7 @@ def test_audit_gate_handles_malformed_file(tmp_vault):audit_path = tmp_vault.root / "research" / "audit_findings.json"audit_path.parent.mkdir(parents=True, exist_ok=True)audit_path.write_text("{ not valid json }", encoding="utf-8")- code, out = _run_lint(tmp_vault, rule="audit-gate")+ _, out = _run_lint(tmp_vault, rule="audit-gate")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "audit-gate"]@@ -510,7 +509,7 @@ def test_orphaned_raw_files_ignores_matched_raw(tmp_vault):(raw_dir / "real-pdf-note.pdf").write_bytes(b"%PDF-1.4 dummy")tmp_vault.auto_sync()- code, out = _run_lint(tmp_vault, rule="orphaned-raw-files")+ _, out = _run_lint(tmp_vault, rule="orphaned-raw-files")import jsondata = json.loads(out)issues = [i for i in data.get("data", {}).get("issues", []) if i.get("rule") == "orphaned-raw-files"]diff --git a/tests/test_core/test_hooks.py b/tests/test_core/test_hooks.pyindex a24b54d..c5c27c7 100644--- a/tests/test_core/test_hooks.py+++ b/tests/test_core/test_hooks.py@@ -2,8 +2,6 @@from __future__ import annotations-from pathlib import Path-from hyperresearch.core.hooks import _SKILL_FILES, _install_research_skill