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
release: v0.11.0 (#113)
Jordan Gibbscbaaaf7841e3
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 8d95b34..be416b2 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -2,7 +2,7 @@## [Unreleased]-- **The PreToolUse reminder now reaches the model (#94).** The installed hook wrote its reminder to stderr and exited 0, and for PreToolUse that channel is discarded — so the "check the research base before searching the web" nudge shipped since 0.x had never once been delivered. It is emitted as `hookSpecificOutput.additionalContext` now, which is the documented injection channel. The matcher is narrowed to `WebSearch|WebFetch`: on `Glob` and `Grep` the advice is noise, and delivering it there for the first time would have made every local vault operation pay for a reminder about the web.+## [0.11.0] - 2026-09-11### SSRF gate + size caps for fetches (builtin, crawl4ai entry points, PDF and image downloads)@@ -41,6 +41,9 @@ The "Academic APIs before web search" section of the injected agent instructions- **`run finish` no longer blocks every light-classified run started on the installed gear (@maximilliangrand in #95).** `verify_run()` took its required-artifact step set from the manifest's `profile_steps`, so a run initialized with `--profile full` whose step-1 decomposition classified it `light` was asked for `critic-findings-*.json` and `patch-log.json` — artifacts the light tier correctly never writes, because steps 12 and 14 are skipped by the tier gate. The run did all its light-tier work and then sat at `blocked (verify)` with no legitimate way to pass. The gate now resolves the tier declared in `prompt-decomposition.json` when it disagrees with the manifest profile, which is what the router already documents ("the manifest's profile field is informational — the decomposition's tier rules"). A missing, unreadable or unknown tier still falls back to `profile_steps`.- **The MCP `fetch_url` tool works again, and a deleted note's URL can be fetched again (#84, fixed by @AmirF194 in #86).** Two bugs on the same path. `Crawl4AIProvider.fetch()` and `fetch_many()` called `asyncio.run()`, which raises before the coroutine runs when the caller already has a loop — and the MCP server dispatches sync tools on its own loop thread, so the tool failed on every call while the CLI never noticed. Both now go through a wrapper that runs the coroutine on a dedicated thread when a loop is present. Separately, `sources.note_id` is `ON DELETE SET NULL`, so deleting a note leaves its row behind with a NULL id; every duplicate-URL check tested row truthiness, so that URL was `DUPLICATE_URL` ("already fetched as note 'None'") forever. All four fetch paths (`fetch_and_save`, `hpr fetch`, `hpr fetch-batch`, `hpr research`) now share one orphan-aware check. The three CLI paths also record the source with `INSERT OR IGNORE`, which was a no-op on the orphaned row too — so the new note was left with no source record, and `hpr fetch`'s duplicate-race detector then deleted the note it had just written and reported `note_id: null`. Those paths now reclaim the orphaned row after the insert; the guard on `note_id IS NULL` leaves a genuine race winner untouched.+- **The PreToolUse reminder now reaches the model (#94; @dajiaohuang in #97 and #98).** The installed hook wrote its reminder to stderr and exited 0, and for PreToolUse that channel is discarded — so the "check the research base before searching the web" nudge shipped since 0.x had never once been delivered. It is emitted as `hookSpecificOutput.additionalContext` now, which is the documented injection channel. The matcher is narrowed to `WebSearch|WebFetch`: on `Glob` and `Grep` the advice is noise, and delivering it there for the first time would have made every local vault operation pay for a reminder about the web.+- **Parallel Search is a fifth web provider (@georgeatparallel in #57).** `[web] provider = "parallel"` searches through Parallel's keyless Search MCP endpoint — the first search-capable provider that needs no account, since `builtin` cannot search at all and `exa` and `tavily` both need a key. Search only: bulk fetch waves degrade to per-URL, so it complements the crawl4ai fetch path rather than replacing it. The README gained a **Web providers** section listing all five on equal footing; none had been documented there before. This PR had been red on CI since August for an `asyncio.run()`-inside-a-running-loop error — the same class of bug #86 fixed — and got the same loop-safe runner.+## [0.10.1] - 2026-09-11diff --git a/pyproject.toml b/pyproject.tomlindex 1b5dcc1..c44c638 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,7 @@ build-backend = "hatchling.build"[project]name = "hyperresearch"-version = "0.10.1"+version = "0.11.0"description = "Claude Code harness for disciplined, adversarially-audited deep research with full provenance."readme = "README.md"license = "MIT"diff --git a/src/hyperresearch/__init__.py b/src/hyperresearch/__init__.pyindex 65bc045..21edd5f 100644--- a/src/hyperresearch/__init__.py+++ b/src/hyperresearch/__init__.py@@ -1,3 +1,3 @@"""Hyperresearch — agent-driven research knowledge base."""-__version__ = "0.10.1"+__version__ = "0.11.0"