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
docs: changelog for #122 and the #126-#130 batch (#139)
Jordan Gibbs7f7e35f6360a
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 57d03af..6daeb17 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -5,6 +5,12 @@- **A run tag is a slug (#116).** `Vault.run_dir()` joined the tag onto `research/runs/` unchecked, and pathlib replaces the base on an absolute segment, so `hpr run init ../../x` or `hpr run init C:/anything` scaffolded a run workspace outside the vault and every later `run` subcommand followed it there. Tags are now validated at that one seam: letters, digits, `-`, `_` and `.`, starting with a letter or digit, which is what `hpr vault-tag` mints. `run`, `levers` and `citecheck` report a bad tag as a clean error instead of a traceback. Same bug class as the `claims ingest --tag` traversal fixed in 0.11.1; exposure is low because the tag comes from the operator or the orchestrating agent, not from fetched content.- **The builtin provider fetches PDFs (#82, reported by @earldodd).** The PDF lane (`_is_pdf_url` / `_fetch_pdf`) lived inside the crawl4ai provider only, so a vault still on `provider = "builtin"` (the default until `hpr install` switches it) had no PDF handling at all: a direct `.pdf` link was decoded as HTML text and rejected by the junk gate as "Binary PDF garbage in content", identically for every mirror of the same document, and an arXiv `/abs/` link saved the 900-word abstract page instead of the paper. The lane now lives in `web/pdf.py` and both providers use it; the crawl4ai module keeps the old names. The builtin provider also detects a PDF from its bytes when the URL does not look like one. When the PDF lane declines a URL and the HTML fallback turns out to be junk, `hpr fetch -j` now says why the lane declined it (`PDF lane: HTTP 403`, `no extractable text layer`, ...) instead of the generic junk verdict, and the pymupdf document handle is closed on the exception path instead of leaking one per encrypted PDF.- **`serply` web provider.** Google organic results with page fetch through the same `SERPLY_API_KEY`; opt-in via `[web] provider = "serply"`, no new dependency.+- **Quote integrity pairs short quoted spans (#120 reported by @earldodd, #122 from @akshaypal912).** `_QUOTE_SPAN_RE` required 20+ characters between quote marks, so a short quoted term ("TVL") failed to match at its opening mark; the scan then treated its closing mark as a new opening mark and reported the unquoted prose up to the next quote character as a hallucinated quote. One real report turned 38 legitimate short quotes into 42 false errors. The regex now matches any span up to 600 characters, and the existing fewer-than-5-words skip decides what gets verified.+- **The SSRF gate classifies IPv4-mapped IPv6 by its embedded IPv4 (#127, from @fduple).** On Python 3.12+ the stdlib `is_*` properties see through `::ffff:a.b.c.d` to ranges they don't flag, and the CGNAT check only looked at IPv4 objects, so `::ffff:100.64.0.1` was fetchable. On 3.11 the opposite held: `::ffff:8.8.8.8` was refused. Mapped addresses are unmapped before classification on every version. An `allow_private_hosts` entry of the form `host:port` or `[v6]:port` now raises a clear error; it never matched anything, but note that it surfaces on every fetch while it is in the config. Bracketed IPv6 entries (`[::1]`) now parse.+- **A bad TLS certificate on the builtin provider raises `CertVerificationError` (#130, from @fduple).** It surfaced as a bare `httpx.ConnectError`. The failure is still final: nothing retries without verification, and the fetch is not queued as an escalation. The crawl4ai provider raises the same error on its PDF lane; its browser lanes still accept bad certificates (#137).+- **Note ids are fixed points of the slugifier, and the link validator rejects shell fragments and traversal (#126, from @fduple).** `write_note` built the filename from the raw id while the frontmatter id was slugified, and `repair` / `graph stub` pass broken-link text through as the id, so fetched content chose the path: `[[../../outside]]` wrote outside the vault, and `[[-n "$kernel"]]` crashed on Windows. Stub files now get slug filenames. `is_valid_wiki_link_target` also refuses targets containing `$ " \` = \ < > ;`, a leading `-` or `!`, or a `.`/`..` segment. Slug ids never contain those, but a title or alias link such as `[[E=mc2]]` that used to resolve by title will drop out of the links table on the next sync.+- **`note mv` keeps notes where sync can see them (#128, from @fduple).** The destination was joined onto the vault root verbatim, so a bare name landed at the root with no `.md` and left the index, `../x.md` wrote outside the vault, and an existing file was overwritten (POSIX) or crashed the command (Windows). A bare name now lands in `research/notes/` with `.md` added; destinations outside `research/notes/` and `research/temp/` are refused with `OUTSIDE_SYNCED_TREE`, and an existing file with `DESTINATION_EXISTS`. `research/index/` is refused too, since `repair` regenerates it and deletes every `.md` there. Case-only renames work on case-insensitive filesystems. The docstring no longer claims `mv` updates references; the id lives in frontmatter, so it never needed to.+- **The builtin provider keeps fetched code as markdown code (#129, from @fduple).** `<pre>` blocks and inline `<code>` were flattened to prose, so bash test syntax (`[[ -n "$k" ]]`) reached the wiki-link parser and `repair` minted stub notes named after shell fragments. `<pre>` now becomes a fenced block whose fence outruns any backtick run inside it, inline `<code>` becomes a backtick span, and indentation survives in the stdlib fallback. Because `strip_markdown` drops code before indexing, code on builtin-fetched pages is no longer in full-text search, embeddings, or the quote-integrity comparison, which is how crawl4ai-fetched pages already behaved. A report that quotes a sentence containing an inline identifier can now fail quote integrity where it passed before.## [0.11.1] - 2026-09-11