/resolve

name: resolve
description: "OSS maintainer fast-close workflow for GitHub PRs. Three phases: (1) PR intelligence — reads full thread, linked issues, PR body to synthesize contribution motivation and classify every comment into action items; (2) conflict resolution — checks out PR branch (fork-aware via gh pr checkout), merges BASE into it, resolves conflicts semantically using contributor's intent as priority lens; (3) implements each action item via specialist agents (Codex for eligible mechanical items) and commits per the chosen commit mode — one attributed commit per item by default — then pushes back to contributor's fork. Supports three source modes: pr (live GitHub comments only), report (latest /review report findings as action items, no GitHub re-fetch), and pr + report (both sources aggregated and deduplicated in one pass). Also accepts bare comment text for single-comment dispatch. NOT for reply drafting to /oss:analyse findings (use /oss:analyse --reply). NOT for code diff review of PR changes (use /oss:review). NOT for release preparation (use /oss:release). NOT for fixing local bugs unrelated to a PR (use /develop:fix; requires develop plugin). TRIGGER when: PR is ready to close and has open comments, conflicts, or review findings to address; user says 'close this PR', 'resolve comments on PR #N', or 'implement review findings'."
argument-hint: <PR number or URL> [report] | report | <review comment text> [--no-challenge] [--agent <name>] [--codemap] [--no-codemap] [--worktree] [--keep "<items>"]
disable-model-invocation: true
allowed-tools: Read, Edit, Write, Bash, Agent, Skill, TaskCreate, TaskUpdate, TaskList, AskUserQuestion, EnterWorktree, ExitWorktree
effort: high

<objective>

OSS maintainer fast-close workflow. PR number → three phases fire automatically:

1. **PR intelligence** — synthesize motivation from PR body, linked issues, thread; classify comments into action items 2. **Conflict resolution** — checkout PR branch (fork-aware), merge `BASE_REF`, resolve conflicts with contributor intent as priority lens 3. **Action item implementation** — implement each item (specialists first, Codex for eligible mechanical items), committed per `COMMIT_MODE` — default one commit per item, attributed to its review comment — then push to contributor's fork

Result: conflict-free PR branch pushed to fork, ready to merge — no GitHub UI.

**Core invariant — transparent, reversible**: every action = visible named git object. Use `git merge` (new commit, two parents), never `git rebase` (rewrites SHA, kills revert/cherry-pick). Default commit mode `each`: every action item = own commit — granular revert always possible. The Step 3d modes `grouped`, `all` and `stage` trade that granularity for fewer commits (or none); every one still leaves named git objects, never rewritten history.

Bare comment text → skip to Codex dispatch (Step 12).

</objective>

<inputs>

• **Preflight side effect**: fetches `origin` to refresh remote refs; never pulls or merges the caller's branch.
• **$ARGUMENTS**: one of:
• Omitted → **review-handoff mode**: auto-detect PR from most recent `.reports/review/pr-*/run-*/review-report.md` or the legacy pre-rename `.reports/review/*/review-report.md` (both oss lineage, same schema) or `.reports/codex/review/*/review-notes.md` (codex lineage, detected but not parsed — see Step 0 lineage guard)
• PR number (e.g. `42` or `#42`) or GitHub PR URL → **pr mode**
• `report` (bare word) → **report mode**: latest review findings as action items; no GitHub re-fetch
• `42 report` or `<URL> report` (order-invariant: `report 42` is the same request) → **pr + report mode**: aggregate live GitHub comments + review report, deduplicated in one pass. The `report` word **adds** the report as a second source; it never suppresses the GitHub fetch — bare `report` (no PR number) is the no-GitHub mode
• Bare review comment text → **comment dispatch mode** (jumps to Step 12)
• **`--no-challenge`**: optional — skip challenge gate per item; all selected items treated as `VALID`
• **`--no-codemap`**: optional — disable codemap structural context (on by default when codemap installed + index present)
• **`--codemap`**: optional — strict mode: stop and report if codemap not installed or index missing
• **`--agent <name>`**: optional — use `<name>` agent for implementation instead of Codex; must be an implementation agent or the `bridge:implement` Skill marker.
• Bare name auto-prefixed with `foundry:` if no plugin prefix detected (e.g. `--agent sw-engineer` → `foundry:sw-engineer`; `--agent linting-expert` → `foundry:linting-expert`; `--agent doc-scribe` → `foundry:doc-scribe`); explicit prefix also accepted (`--agent foundry:sw-engineer`); see routing table in `dispatch-prelude.md`.
• **`--agent` also applies to `INTEL_AGENT` (Step 3b thread intelligence)** — explicit real Agent types override label/title routing for classification as well.
• `bridge:implement` is never passed to `Agent`: classification falls back to label/title routing, C1 candidates use the Skill route, and other items use the change-to-specialist table.

NOT-for additions (scope guards):

• **NOT for non-Python source PRs** (TypeScript, Go, Rust, Java) unless action items are limited to documentation or CI/CD changes — Step 9's lint-qa gate runs Python-specific tools (`ruff`/`mypy`); non-Python PRs get partial or no static-analysis review. For non-Python repos, run `/oss:resolve` in `report` mode with manually-curated findings.
• **NOT for branches with uncommitted local edits** — the `report`-mode no-PR# path operates on the current branch as-is; uncommitted changes would be committed alongside the action items, so its branch safety check below stops on tracked modifications (`git status --porcelain -uno`). Stash (`git stash`) or commit local edits before invoking — workflow doesn't auto-stash.

</inputs>

<constants>

CHALLENGE_TIMEOUT_S=300  # intel + read-only challenge agents have bound