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
chore: add issue/PR templates and dependabot config (#99)
Jordan Gibbsd7fcf7983f91
diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.ymlnew file mode 100644index 0000000..d5ba8ba--- /dev/null+++ b/.github/ISSUE_TEMPLATE/bug_report.yml@@ -0,0 +1,62 @@+name: Bug report+description: Something in the hyperresearch CLI or pipeline behaves incorrectly+labels: ["bug"]+body:+ - type: markdown+ attributes:+ value: |+ Before filing, one check that saves everyone time: **is the problem in hyperresearch, or in the agent harness running it?**++ hyperresearch is a Python CLI. If what you're seeing is about subagent scheduling, task notifications, context or token accounting, or how an agent decided to call a tool, that belongs to Claude Code or whichever harness you're using, not here. If you're unsure, file it — just say so.++ - type: input+ id: version+ attributes:+ label: hyperresearch version+ description: Output of `hyperresearch --version`.+ placeholder: "0.10.1"+ validations:+ required: true++ - type: input+ id: env+ attributes:+ label: OS and Python version+ description: Output of `python -VV`, plus your OS. Use the interpreter that actually runs the CLI (the one in `.venv`), which is not always the one on PATH.+ placeholder: "Windows 11, Python 3.11.9"+ validations:+ required: true++ - type: textarea+ id: command+ attributes:+ label: What you ran+ description: The exact command. Add `-j` if the command supports it.+ render: shell+ validations:+ required: true++ - type: textarea+ id: output+ attributes:+ label: What happened+ description: |+ Paste the literal output, including stderr — not a summary of it. Exact text matters: several past reports turned on whether a message was a parser error or a fixed string the CLI prints for any failure.+ render: shell+ validations:+ required: true++ - type: textarea+ id: expected+ attributes:+ label: What you expected instead+ validations:+ required: true++ - type: textarea+ id: repro+ attributes:+ label: Reproduction+ description: Smallest set of steps that shows the problem. If it involves a fetch, include the URL. If it involves a run, include the vault tag and `hyperresearch run status -j`.+ validations:+ required: falsediff --git a/.github/ISSUE_TEMPLATE/config.yml b/.github/ISSUE_TEMPLATE/config.ymlnew file mode 100644index 0000000..a87c08d--- /dev/null+++ b/.github/ISSUE_TEMPLATE/config.yml@@ -0,0 +1,8 @@+blank_issues_enabled: true+contact_links:+ - name: Claude Code / agent harness behavior+ url: https://github.com/anthropics/claude-code/issues+ about: Subagent scheduling, task notifications, token accounting, or how an agent chose to call a tool. Different maintainers, different repo.+ - name: Security vulnerability+ url: https://github.com/jordan-gibbs/hyperresearch/security/advisories/new+ about: Report privately through a security advisory rather than a public issue.diff --git a/.github/ISSUE_TEMPLATE/feature_request.yml b/.github/ISSUE_TEMPLATE/feature_request.ymlnew file mode 100644index 0000000..d9dc32c--- /dev/null+++ b/.github/ISSUE_TEMPLATE/feature_request.yml@@ -0,0 +1,36 @@+name: Feature request or proposal+description: Suggest a capability, or propose a design change+labels: ["enhancement"]+body:+ - type: textarea+ id: problem+ attributes:+ label: The problem+ description: What you're trying to do that you can't do today. Describe the situation, not the solution.+ validations:+ required: true++ - type: textarea+ id: proposal+ attributes:+ label: What you'd like to see+ validations:+ required: true++ - type: textarea+ id: workaround+ attributes:+ label: What you do now instead+ description: |+ If there's a config overlay, a flag, or a manual step that gets you most of the way, say so. Several proposals have turned out to be already possible via `[profile.<name>]` overrides in `.hyperresearch/config.toml` or existing CLI flags, and knowing what you already tried is the fastest way to find that out.+ validations:+ required: false++ - type: textarea+ id: scale+ attributes:+ label: Scale, if the proposal is about performance+ description: |+ For anything framed around "this won't hold up at size", the useful number is where it actually stops working for you: vault size, source count per run, or measured timings. Proposals with a real number attached get built; proposals without one usually get a cheaper fix.+ validations:+ required: falsediff --git a/.github/dependabot.yml b/.github/dependabot.ymlnew file mode 100644index 0000000..e2a5c56--- /dev/null+++ b/.github/dependabot.yml@@ -0,0 +1,23 @@+version: 2+updates:+ - package-ecosystem: pip+ directory: "/"+ schedule:+ interval: monthly+ open-pull-requests-limit: 5+ groups:+ dev-dependencies:+ patterns:+ - "pytest*"+ - "ruff"+ - "mypy"+ labels:+ - dependencies++ - package-ecosystem: github-actions+ directory: "/"+ schedule:+ interval: monthly+ open-pull-requests-limit: 3+ labels:+ - dependenciesdiff --git a/.github/pull_request_template.md b/.github/pull_request_template.mdnew file mode 100644index 0000000..712512a--- /dev/null+++ b/.github/pull_request_template.md@@ -0,0 +1,24 @@+<!-- Keep this short. Delete anything that doesn't apply. -->++## What this changes++<!-- One or two sentences. If it fixes an issue, write "Fixes #NNN" so it closes on merge — note that GitHub only auto-closes the FIRST issue in a list, so give each one its own keyword. -->++## Why++<!-- The behavior that was wrong, or the gap being filled. Link the issue if there is one. -->++## How it was verified++<!-- `pytest tests/` and `ruff check src/ tests/` at minimum. Say which tests fail without the change. -->++---++**Scope check** — the review is much faster when the diff contains only the change being proposed:++- [ ] No unrelated reformatting, whitespace, or prose rewriting outside the lines this change needs+- [ ] `CHANGELOG.md` touched only to add an entry under `[Unreleased]`+- [ ] No edits to user-facing output strings, docstrings, or test fixtures unrelated to this fix+- [ ] If you ran a formatter or an automated cleanup pass, its results are in a separate PR++<!-- If you're adding a third-party service or provider, please say up front whether you're affiliated with it. It doesn't disqualify the PR; it just saves a round trip. -->