Gator Gate

Gator Gate

Validate OpenShell GitHub issues and pull requests for project fit, then monitor valid PRs until they are ready for maintainer approval.

This skill is a gating workflow. It can start from any issue or PR state, inspect the current gator:* label, and continue the correct next action.

Skill Location

Codex and other agent harnesses should load this skill from the repository path scripts/agents/gator/skills/gator-gate/SKILL.md. After this branch is merged, the canonical GitHub location is https://github.com/NVIDIA/OpenShell/blob/main/scripts/agents/gator/skills/gator-gate/SKILL.md.

Prerequisites

• The gh CLI must be able to call GitHub APIs (gh api user --jq '.login')
• You must be in the OpenShell repository root
• GitHub write permissions are required to apply labels, comment, close issues/PRs, or post /ok to test

Do not use gh auth status as the authentication health check inside provider-backed sandboxes. Scoped provider tokens may be exposed as openshell:resolve:env:* placeholders and gh auth status probes endpoints outside the gator policy, causing false "token is invalid" reports even when allowed gh api and gh pr calls succeed. Use gh api user --jq '.login' and a repo-scoped probe instead.

Use REST-backed gh api for GitHub write actions inside gator sandboxes. Do not rely on gh issue edit, gh pr edit, or other high-level write commands when a REST path is available, because some of them use GraphQL mutations and gator policy allows GraphQL reads only. Do not fall back to curl for credentialed GitHub writes unless the active provider policy explicitly allows the curl binary for the same scoped endpoint. Preferred write shapes:

jq -Rs '{body:.}' comment.md > /tmp/comment.json
gh api --method POST repos/NVIDIA/OpenShell/issues/<number>/comments --input /tmp/comment.json --jq .html_url
gh api --method POST repos/NVIDIA/OpenShell/issues/<number>/labels -f labels[]="gator:<state>"
gh api --method DELETE repos/NVIDIA/OpenShell/issues/<number>/labels/gator%3Ablocked --silent || true

If a required GitHub REST read or write fails with EOF, Empty reply from server, or a sandbox NET:FAIL after the current policy shows the endpoint was allowed, treat it as a transient transport or provider failure. Do not convert the PR or issue to gator:blocked, do not report it as a rate-limit/auth failure, and do not keep probing optional endpoints such as /rate_limit. In supervised watch mode, finish with OPENSHELL_AGENT_RESULT {"status":"transient_failure","next_poll_seconds":120,"reason":"github_transport_eof"} so the supervisor retries soon.

If the principal-engineer-reviewer sub-agent fails before producing usable review output, treat that as transient gator infrastructure failure, not as a PR blocker. This includes Codex auth or token-refresh failures, model transport failures, sub-agent command failures, empty reviewer output, malformed reviewer output, and sandbox policy denials that only affect the sub-agent harness. Do not post a marked gator comment or PR review, do not apply gator:blocked, and do not consume the one-disposition-per-head-SHA slot. In supervised watch mode, finish with OPENSHELL_AGENT_RESULT {"status":"transient_failure","next_poll_seconds":120,"reason":"reviewer_subagent_failed"} so the supervisor retries after the operator or provider issue clears.

Authority Rules

• Do not push commits to a contributor's PR branch by default.
• You may push changes only when explicitly instructed by a GitHub comment from a maintainer or by a direct operator prompt.
• Do not post /ok to test <sha> unless the current GitHub user has maintainer authority.
• Code review is code-only. Do not run pre-commit, unit tests, or E2E locally as part of the initial PR review unless explicitly instructed.
• Security vulnerabilities must not be triaged through public GitHub issues. Follow SECURITY.md.

Maintainer authority means one of:

• User is in the NVIDIA openshell-maintainers team
• User is a CODEOWNER listed in .github/CODEOWNERS
• Repository permission is admin, maintain, or write for maintainer-only actions such as /ok to test

Use these checks where needed:

gh api user --jq '.login'
gh api repos/NVIDIA/OpenShell/collaborators/<user>/permission --jq '{permission,role_name}'
gh api orgs/NVIDIA/teams/openshell-maintainers/members --jq '.[].login'

If a permission or team-membership query fails due to API access, fall back to CODEOWNERS and repository permission where possible. If authority cannot be verified, do not perform maintainer-only actions.

Comment Marker

All comments posted by this skill must begin with this marker:

> **gator-agent**

Use one canonical gator disposition per issue or PR head SHA for baseline review and status summaries. A disposition may be one issue comment or one submitted GitHub review. A submitted review, including its summary body and every inline comment in its comments array, counts as one disposition for the head SHA; do not count its inline comments separately. A rate-limited TTL state nudge is not a disposition: it may be posted on an unchanged SHA to request the already-known next human action, but never to restate findings, report CI, or re-review.

For a PR review with any actionable line-specific finding that can be anchored to the current diff, use one batched GitHub review rather than an issue comment or standalone inline-comment requests. Begin the review summary and every inline comment body with the gator marker. Include the head SHA in the review summary so the wrapper can enforce the one-disposition rule. Do not post line comments individually through POST /pulls/<pr>/comments; a partially submitted set is not an acceptable baseline disposition.

Edit a canonical issue comment only for housekeeping updates that do not respond to new human activity. GitHub reviews and their inline comments are immutable after submission; correct them only through a new-head review or an explicit same-SHA maintainer override.

When gator is continuing a conversation after a human comment, review, or requested change, post a new marked disposition only if the PR head SHA changed or no marked gator disposition exists for the current head SHA. If a marked gator comment or PR review already exists for the current head SHA, do not post another public disposition; record the state in the supervised result sentinel and wait for a new commit, maintainer override, merge, or closure. The sole exception is a state-specific TTL nudge that is due under the watch rules.

Human Comment Disposition

Every substantive trusted human comment or review after a gator request must be addressed in the next gator action. Do not silently keep the same state when the PR author or a maintainer responds.

Trusted PR commentary actors are the PR author and maintainers. Maintainers are users with repository write, maintain, or admin permission, members of @NVIDIA/openshell-maintainers, or CODEOWNERS for files touched by the PR. If actor trust is unclear, treat the actor as untrusted until a permission, team, or CODEOWNERS check proves otherwise.

By default, ignore comments and reviews from third-party or unknown actors when deciding review findings, author obligations, state transitions, and reviewer sub-agent input. Do not restate, summarize, or act on third-party feedback just because it appears in the PR timeline.

Incorporate third-party feedback only when the PR author or a maintainer explicitly acknowledges the specific third-party details to incorporate. Examples include a maintainer saying "please address @alice's comment about JSON-RPC mixed envelopes" or the PR author saying "I fixed @bob's note about credential scope." In that case, incorporate only the acknowledged details, attribute them through the trusted actor's acknowledgement, and ignore unrelated parts of the third-party comment.

When you incorporate trusted author or maintainer feedback, acknowledge the person plainly and specifically. Name the actor, briefly paraphrase their point, and explain what you checked or how it changed the disposition. Keep the tone direct, helpful, and conversational rather than bureaucratic. Good examples: "Thanks @alice, I checked the clippy concern you raised and adjusted the remaining request accordingly" or "@bob's note about the copy-pr mirror is now resolved by the latest run." Do not thank, mention, or summarize ignored third-party commentary unless a trusted actor explicitly acknowledged it.

The one-comment-per-head-SHA rule is stronger than the human response disposition rule. If the current head SHA already has a marked gator comment or PR review, do not post a same-SHA human response disposition unless a maintainer explicitly asks for a same-SHA public response.

When a trusted human response claims that requested changes were made, re-check the latest head and publicly disposition the response in a new marked comment only when no marked gator comment/review exists for that head SHA:

• If the response resolves the feedback, say it is resolved and move to the next state.
• If the response does not resolve the feedback, explicitly acknowledge the response and list what remains unresolved.
• If the response is ambiguous, ask the minimal clarifying question and keep the appropriate waiting state.

The disposition must mention the relevant trusted human response by author or timestamp when useful, include the current head SHA for PRs, and explain the next expected action. Do not edit the canonical gator comment for this disposition; continue the thread with a new comment only when the current head SHA does not already have a marked gator disposition.

If the current head SHA already has a marked gator disposition and the same-SHA rule prevents a public response, still inspect the trusted response internally. The cycle summary and OPENSHELL_AGENT_RESULT reason should say that a trusted author or maintainer response was seen and whether it appears to require a new commit, maintainer override, or no action. Do not describe the response as third-party when the actor is the PR author or a verified maintainer.

Durable review dispositions

Every prior Gator finding is a durable review disposition across later head SHAs. A new commit permits a delta review; it does not erase trusted feedback history or reopen the unchanged PR.

Before every fresh reviewer run, collect Gator review summaries, general findings, issue-comment dispositions, inline review threads, replies, resolution state, resolver, stable finding IDs, and review-head context:

review-feedback-ledger NVIDIA OpenShell <pr-number> \
  > /tmp/gator-review-feedback-ledger.json
jq -e '
  .schema_version == 4 and
  (.dispositions | type == "array") and
  (.threads | type == "array") and
  (.review_scope.mode |
    IN("initial", "follow_up", "already_reviewed", "critical_only"))
' \
  /tmp/gator-review-feedback-ledger.json >/dev/null

Treat the ledger as required reviewer input, not optional background:

• Verify whether the PR author, resolver, or replying actor is trusted under the rules above.
• Treat review_scope.mode and previous_reviewed_sha as authoritative. Use initial for a complete PR review, follow_up for an unresolved-feedback plus <previous_reviewed_sha>..HEAD delta review, and already_reviewed to suppress another reviewer run. Use critical_only after three finding-bearing rounds as described below.
• Use current_patch_id, previous_reviewed_patch_id, base SHA, and merge-base SHA to preserve review identity across rebases and merge-main commits. If rebase_equivalent is true, do not review the same effective patch again.
• For a non-equivalent rebase, compare author patch IDs or use git range-diff to isolate the author-only delta. Upstream changes are context, not new PR findings.
• Carry every still-open finding forward as an existing obligation. Do not post a new thread or semantically equivalent general finding for it.
• A Gator thread resolved by a verified maintainer is addressed. If the resolver is only the PR author, inspect the trusted reply and latest diff to decide whether the finding was fixed; resolution alone does not grant a non-maintainer author waiver authority.
• When a later commit demonstrably fixes an open inline Gator finding, resolve that Gator-owned GitHub review thread as part of the same reconciliation cycle. Also resolve it after a verified maintainer explicitly waives the finding. Do not resolve a thread merely because it is outdated, the author says it is fixed, or a new review omits it.
• Preserve a verified maintainer's reply as the rationale. An explicit rejection such as "invalid", "intentional", "fine as implemented", or "won't fix" is a waiver, not an unanswered request.
• An unresolved thread with an explicit verified-maintainer waiver is also waived. A non-maintainer author's disagreement remains context for review but does not override a maintainer-required change.
• Preserve each GATOR-<origin-sha-prefix>-<ordinal> finding ID across later reviews. Use the ledger's gator-inline-<comment-id> fallback for legacy inline findings that predate explicit IDs.
• Do not re-raise an open, resolved, or waived finding, or a semantically equivalent finding with different wording, merely because the head SHA changed.
• Re-raise it only when the new diff materially invalidates the prior rationale or reintroduces the defect. State what changed since the resolution and why the earlier disposition no longer applies.
• If the ledger lookup or validation fails, do not run a context-free reviewer. Return a transient supervised result. Use github_transport_eof for the transport failures described above; otherwise use review_feedback_lookup_failed.
• Record the ledger's review_telemetry in the internal cycle summary. Treat a nonzero duplicate finding-ID count, a waived finding reappearing, or an unchanged-code proposal as a reviewer-quality signal, not an author defect.

Resolve addressed Gator threads

After checking the new diff and trusted replies, partition every open ledger finding into still-open, fixed by the current head, or explicitly waived by a verified maintainer. Before posting the current-head disposition or advancing out of review, resolve each fixed or waived inline Gator thread by stable finding ID:

resolve-gator-review-threads \
  /tmp/gator-review-feedback-ledger.json \
  GATOR-<origin-sha-prefix>-<ordinal> [...]

The resolver accepts only exact threads from the feedback ledger whose first comment carries the Gator marker. Never resolve a human-owned review thread, a still-open finding, or a thread whose disposition is ambiguous. General findings and issue comments have no review thread to resolve; retain their durable disposition in the ledger.

Thread resolution is required housekeeping for an addressed inline finding, not a new review disposition, and does not consume the one-disposition-per-head SHA slot. If GitHub does not confirm every requested resolution, do not advance the Gator state or post the follow-up disposition. Return OPENSHELL_AGENT_RESULT {"status":"transient_failure","next_poll_seconds":120,"reason":"review_thread_resolution_failed"} and retry the reconciliation later.

Labels

There must be at most one gator:* label on an issue or PR at any time.

If labels are missing and you have permission to create them, create them with clear descriptions. Otherwise report the missing labels to the operator.

gh label create "gator:follow-up-needed" --description "Gator needs submitter or maintainer follow-up" --color "FBCA04"
gh label create "gator:blocked" --description "Gator is blocked by process or repository gates" --color "BFD4F2"
gh label create "gator:validated" --description "Gator validated this issue as ready for work" --color "0E8A16"
gh label create "gator:in-review" --description "Gator is reviewing or awaiting PR review feedback" --color "1D76DB"
gh label create "gator:watch-pipeline" --description "Gator is monitoring PR CI/CD status" --color "5319E7"
gh label create "gator:approval-needed" --description "Gator completed review; maintainer approval needed" --color "C5DEF5"
gh label create "gator:merge-ready" --description "Gator completed review and approval is present; merge decision pending" --color "0E8A16"

When changing state, remove all existing gator:* labels first, then add the new one.

for label in gator%3Afollow-up-needed gator%3Ablocked gator%3Avalidated gator%3Ain-review gator%3Awatch-pipeline gator%3Aapproval-needed gator%3Amerge-ready; do
  gh api --method DELETE repos/NVIDIA/OpenShell/issues/<number>/labels/$label --silent || true
done
gh api --method POST repos/NVIDIA/OpenShell/issues/<number>/labels -f labels[]="gator:<state>"

Pull requests are also GitHub issues for label operations, so the REST issue label endpoints are valid for PR labels.

Invocation Modes

The user may provide:

• A GitHub issue number
• A GitHub PR number
• Both an issue and a PR number
• No number, with an instruction to process untriaged or active gator items

Resolve PRs and issues carefully:

gh issue view <issue> --json number,title,body,state,author,labels,comments,createdAt,updatedAt,closedAt,url
gh pr view <pr> --json number,title,body,state,author,labels,comments,reviews,closingIssuesReferences,files,isDraft,mergeStateStatus,reviewDecision,headRefOid,headRefName,baseRefName,mergedAt,closedAt,url

For a PR-only input, derive linked issues from closingIssuesReferences, PR body references such as Fixes #123, and issue comments that mention the PR. If no linked issue exists, validate the PR directly.

Invocation Scope

Before discovering work, define the invocation target selector and keep every later query within that selector.

• Explicit issue or PR numbers: process only those items, even if a PR is closed or merged.
• "My PRs" or similar operator-owned requests: resolve the current GitHub user with gh api user --jq '.login' and process only PRs authored by that login.
• "All active PRs", "all gator-labeled PRs", or repo-wide requests: process across authors only when the operator explicitly asks for repo-wide scope. For write actions across authors, verify maintainer authority first.
• No-number requests that mention untriaged issues: process only the issue set implied by the request, such as open issues with state:triage-needed.

For PR watch requests, normal discovery should include open non-draft PRs matching the target selector. Closed/merged reconciliation may also include closed or merged PRs matching the same selector when they still have an active gator:* label. This is a cleanup extension of the current invocation scope, not permission to scan or mutate all gator-labeled PRs in the repository.

When searching for closed or merged PRs with active gator labels, query each label separately and de-dupe by PR number. Do not combine labels into one comma-separated search term; GitHub search does not treat that as an OR query and can miss PRs. Example for "my PRs":

author="$(gh api user --jq '.login')"
for label in \
  gator:follow-up-needed \
  gator:blocked \
  gator:validated \
  gator:in-review \
  gator:watch-pipeline \
  gator:approval-needed \
  gator:merge-ready; do
  gh pr list --repo NVIDIA/OpenShell --author "$author" --state closed \
    --search "label:$label" \
    --json number,title,state,mergedAt,closedAt,labels,url,updatedAt
done | jq -s 'add | unique_by(.number)'

When using closed/merged reconciliation for a PR that was not explicitly requested by number, require a prior comment beginning with > **gator-agent** before mutating labels.

If a closed or merged PR has an active gator:* label but no gator marker and was not explicitly requested, report the label drift in the cycle summary and leave the labels unchanged.

State Machine

No gator label
  -> gator:follow-up-needed  missing why, UX path, repro, RFC/roadmap link, or author action
  -> gator:blocked           process blocker prevents progress
  -> gator:validated         issue is valid and ready for work
  -> gator:in-review         PR is valid and enters monitoring
  -> close not planned       invalid or out of project scope

gator:follow-up-needed
  -> gator:validated         issue clarified and valid
  -> gator:in-review         PR clarified and valid
  -> gator:blocked           process blocker discovered
  -> close not planned       48 business-hour TTL expired

gator:blocked
  -> previous intended state blocker resolved
  -> stay blocked            blocker still present
  -> nudge responsible party blocker unchanged after 48 business hours
  -> stop                    closed by vouch gate; wait for vouch and reopen

gator:validated
  -> stop                    issue is already ready for work, no new PR or comments
  -> gator:in-review         linked PR appears and is valid
  -> re-evaluate             new substantive comments or labels change scope

gator:in-review
  -> gator:watch-pipeline    review feedback resolved
  -> nudge PR author         review feedback unanswered after 48 business hours
  -> gator:follow-up-needed  author action needed
  -> gator:blocked           draft, vouch, DCO, merge conflict, or authority blocker

gator:watch-pipeline
  -> gator:approval-needed   required checks are green and maintainer approval is missing
  -> gator:merge-ready       required checks are green and maintainer approval is present
  -> gator:in-review         new review feedback or code changes need attention
  -> gator:follow-up-needed  author action needed for failures
  -> gator:blocked           process blocker prevents test execution

gator:approval-needed
  -> gator:merge-ready       maintainer approval arrives and checks remain green
  -> nudge maintainers       no approval after 48 business hours
  -> gator:watch-pipeline    checks are no longer green
  -> gator:in-review         maintainer requests changes or author updates PR

gator:merge-ready
  -> stop                    PR merged or closed
  -> nudge maintainers       no merge or close decision after 48 business hours
  -> gator:watch-pipeline    checks are no longer green
  -> gator:in-review         maintainer requests changes or author updates PR

Step 1: Fetch Context

Fetch issue, PR, comments, reviews, files, labels, and linked references. Also inspect existing gator state.

For PRs, record:

• PR number and URL
• PR author login
• Head SHA from headRefOid
• Linked issue numbers
• Draft status
• Merge state
• Review decision
• Changed files and affected subsystems
• Existing test:* labels
• Trusted commentary actors: PR author plus verified maintainers or CODEOWNERS relevant to changed files
• Untrusted third-party comments only when a trusted actor explicitly acknowledged the specific details to incorporate

For issues, record:

• Issue number and URL
• Author and author association where available
• Current labels
• Whether a linked PR exists
• Last human or maintainer comment after any gator follow-up request

Step 2: Recover From Current State

If exactly one gator:* label exists, resume from that state in the state machine.

If multiple gator:* labels exist:

1. Treat this as label drift.
2. Read recent comments and labels to infer the most advanced safe state.
3. Comment with the correction.
4. Remove all but the chosen gator:* label.

If no gator:* label exists, begin validation.

Closed/Merged PR Reconciliation

Before running normal PR validation, review, CI, or approval logic, check whether each target PR is already closed or merged.

For merged PRs:

1. Post a Monitoring Complete comment when the PR still has an active gator:* label or the latest gator comment does not already record monitoring completion.
2. Remove all active gator:* labels.
3. Do not run duplicate detection, review, CI watch, approval nudges, or other active-state transitions.

For closed-unmerged PRs:

1. Post a Monitoring Complete comment when the PR still has an active gator:* label or the latest gator comment does not already record monitoring completion.
2. Remove all active gator:* labels.
3. Do not run duplicate detection, review, CI watch, approval nudges, or other active-state transitions.

For closed or merged PRs that have no active gator:* label and already have a monitoring-complete gator comment, take no GitHub write action.

In supervised watch mode, return OPENSHELL_AGENT_RESULT {"status":"complete","reason":"pr_merged"} or OPENSHELL_AGENT_RESULT {"status":"complete","reason":"pr_closed"} only when all targeted PRs in the cycle are closed, merged, or otherwise complete. If any targeted PR still needs future reconciliation, return the appropriate waiting or blocked sentinel for the active work.

Watch Loop Rules

Every gator state is a watch state. On each invocation, determine the current state, inspect the latest issue/PR activity, and either advance to the next state, keep waiting, or post a TTL nudge.

When OPENSHELL_AGENT_RUN_MODE=watch, the OpenShell agent supervisor owns the sleep/relaunch loop. In that mode, perform exactly one reconciliation cycle, do not run sleep 900 or an unbounded polling loop inside the harness, and finish with a single final-line result sentinel:

OPENSHELL_AGENT_RESULT {"status":"waiting","next_poll_seconds":900,"reason":"checks_pending"}

Use status=waiting for routine CI/PR activity waits, status=blocked for human or process blockers, status=complete for closed or merged PRs and other complete items, status=terminal_failure for unrecoverable errors, and status=transient_failure only when the supervisor should retry soon. The supervisor will sleep and invoke the harness again with fresh GitHub state.

When not running under supervised watch mode, do not stop after a one-shot check when a PR is in an active waiting state unless the operator explicitly asks for a one-shot status check. Enter a polling loop and state the interval and stop conditions before waiting.

Default live-watch cadence:

• For supervised watch mode, set next_poll_seconds to 900 for PRs in active states: gator:in-review, gator:watch-pipeline, gator:approval-needed, gator:merge-ready, and gator:blocked.
• Watch PRs indefinitely across gator state transitions until they close, merge, or the operator stops the session. In supervised watch mode this means return a waiting or blocked result sentinel and let the supervisor sleep outside the model session.
• For supervised watch mode, set next_poll_seconds to 3600 for issue-only gator:follow-up-needed or issue-only gator:blocked states until they progress, close, or reach a TTL threshold.
• Stop immediately for issue-only gator:validated items that have no associated PR.
• Do not stop PR monitoring just because the gator state changes, a human comments, or new commits arrive. Treat those as triggers to re-evaluate and continue from the new state.
• Stop PR monitoring only when the PR closes, merges, the operator stops the session, or an unrecoverable process blocker prevents further agent action.

Use a concise cycle summary before returning the result sentinel, for example: "No action needed for PR #123; supervisor should recheck in 15 minutes until it closes, merges, or the session is stopped."

Use 48 business hours as the default inactivity threshold for states that are waiting on a person. Business hours are Monday through Friday; do not count Saturday or Sunday.

State-specific monitoring:

• gator:follow-up-needed: wait for submitter or maintainer clarification. If no substantive response arrives after 48 business hours, close as not planned or close the PR with a TTL-expired comment.
• gator:blocked: re-check the blocker. If resolved, continue to the previous intended state. If still blocked after 48 business hours, nudge the responsible party unless the PR was auto-closed by the vouch system.
• gator:validated: for an issue-only item with no associated PR, stop; the issue is ready for work. If an associated PR exists or appears during a later invocation, validate the PR and move it to gator:in-review. If new information changes the scope, re-run validation.
• gator:in-review: watch for author commits, trusted author responses, trusted maintainer comments, and unresolved gator findings. Ignore unacknowledged third-party comments. If feedback is addressed, move to E2E/test-label decision and then gator:watch-pipeline. If feedback is unanswered after 48 business hours, nudge the PR author. Continue watching after either action.
• gator:watch-pipeline: watch checks until green, failed, or blocked. Move to gator:approval-needed when required checks are green, no review feedback remains, and maintainer approval is missing. Move directly to gator:merge-ready when required checks are green, no review feedback remains, and maintainer approval is present. Continue watching after either state transition because maintainer feedback can arrive later.
• gator:approval-needed: watch for maintainer approval, merge, closure, new commits, author responses, or maintainer requested changes. If maintainer approval arrives while checks remain green and no review feedback remains, move to gator:merge-ready. If no approval arrives after 48 business hours, nudge maintainers and CODEOWNERS. If humans request changes, move back to gator:in-review and continue watching author follow-up.
• gator:merge-ready: watch for merge, closure, new commits, failed checks, or maintainer requested changes. If no merge or close decision occurs after 48 business hours, nudge maintainers and CODEOWNERS. If checks are no longer green, move back to gator:watch-pipeline. If humans request changes or the author updates the PR, move back to gator:in-review.

When calculating a nudge TTL, use the latest relevant event for that state:

• The first comment that entered the current state
• The most recent gator comment in the current state
• The most recent comment or review from the expected actor
• The most recent commit pushed to the PR, when waiting on code changes

Do not post repeated nudges more often than once per 48 business hours for the same state and actor.

Step 3: Check Process Blockers

Before project-validity review, check blockers.

Move to gator:blocked when any of these apply:

• PR is draft and not ready for review
• PR is blocked by the vouch system or was auto-closed for lack of vouch
• DCO is missing or failing
• PR has merge conflicts or mergeStateStatus indicates dirty/blocked for conflict reasons
• Required /ok to test <sha> is needed and the current user lacks maintainer authority
• Required CI cannot run because the copy-pr mirror is missing or stale and maintainer authority is unavailable

For auto-closed vouch-gate PRs, do not treat the proposal as invalid. Comment only if useful, then stop and wait until the author is vouched and the PR is reopened.

For blocked open PRs, post a concise gator comment that lists the blocker and the exact next human action. On later invocations, re-check the blocker and nudge the responsible party after 48 business hours if it remains unresolved.

Step 4: Duplicate Detection

For newer issues and PRs, check for duplicates before deciding validity. Duplicate detection is a project-fit input, not a substitute for human judgment.

Search for existing issues and PRs using the title, subsystem labels, changed files, key error strings, and important feature terms:

gh search issues --repo NVIDIA/OpenShell "<keywords>" --state open --json number,title,state,url,labels,updatedAt
gh search issues --repo NVIDIA/OpenShell "<keywords>" --state closed --json number,title,state,url,labels,updatedAt
gh search prs --repo NVIDIA/OpenShell "<keywords>" --state open --json number,title,state,url,labels,updatedAt
gh search prs --repo NVIDIA/OpenShell "<keywords>" --state closed --json number,title,state,url,labels,updatedAt

Treat items as duplicate candidates when they share the same user-visible problem, requested capability, affected subsystem, or implementation approach. Do not rely on title similarity alone.

If a submission is an exact duplicate of an open validated issue or active PR:

1. Comment with the matching issue or PR.
2. Apply duplicate if available.
3. Close only when the duplicate relationship is clear and no extra author-specific context is needed.

If a submission appears related but may contain new constraints, reproduction details, or a different use case:

1. Move to gator:follow-up-needed.
2. Link the duplicate candidates.
3. Ask the author to explain what is different or whether the older issue/PR covers their need.
4. Flag the candidate duplicate set for human review in the comment.

If a PR duplicates another open PR or implements a feature already being reviewed elsewhere, move to gator:follow-up-needed unless a maintainer has already directed both PRs to proceed independently.

Step 5: Auto-Validation

Auto-validate submissions from maintainers, but still review PR implementations.

Auto-validation applies when the submitter is:

• A CODEOWNER
• In @NVIDIA/openshell-maintainers

For maintainer-authored issues without PRs, move to gator:validated unless the issue is clearly security-sensitive and belongs outside GitHub.

For maintainer-authored PRs, move to gator:in-review and start PR monitoring. Auto-validation means the change is project-valid; it does not mean the implementation is merge-ready.

Step 6: Validate Issues and PRs

Apply the criteria below in order. If evaluating an issue/PR pair, validate both as one submission but set each object to its appropriate current state:

• Issue without PR: gator:validated
• PR with or without linked issue: gator:in-review
• Issue linked to a valid active PR: gator:validated on the issue and gator:in-review on the PR

Already Validated Issue

If a PR is mapped to an issue that is already valid for the same work, consider the PR project-valid and enter gator:in-review unless the PR clearly exceeds the issue scope.

RFCs

For PRs that add or modify rfc/**, validate against rfc/README.md and rfc/0000-template/README.md:

• RFC lives in rfc/NNNN-short-name/README.md
• Front matter includes authors, state, and links
• State is one of draft, review, accepted, rejected, implemented, superseded
• RFC has summary, motivation, non-goals, proposal, implementation plan, risks, alternatives, prior art, and open questions
• RFC is appropriate for cross-cutting, architectural, API, process, or multi-team decisions
• Small bug fixes, small single-component features, docs, dependency updates, and interface-preserving refactors should not use RFCs

Distinguish structural validity from acceptance. A structurally valid RFC PR can enter gator:in-review, but implementation work should not be considered ready until the RFC is accepted or an explicit maintainer says otherwise.

Small Concentrated Work

Validate small and concentrated work when it has clear motivation and one of these shapes:

• One subsystem: gateway, CLI, supervisor, drivers, network proxy, policy, sandbox, TUI, docs, build/release
• Refactor that removes duplicate code or simplifies internals without UX or functional impact
• Logical packaging refactor, such as splitting crates or separating proto/native schema boundaries
• Test improvements for important code paths or features
• Concentrated bug fix with reproducibility steps and a clear test path
• TUI, CLI, or API quality-of-life improvement with a clear user path
• Driver improvement that makes sandbox lifecycle management easier or more efficient
• Documentation clarification, typo fix, errata, or missing documentation
• CI/CD/build/release improvement, including Snap, package, release, or test harness work

Documentation changes from non-maintainers must not reorder ToC items, change fundamental hierarchy, or restructure docs without a clear maintainer-approved reason.

Provider Profiles and Credential Support

Provider-profile work is a supported high-traction area, but requires all of the following:

• Clear UX path for how users configure and use the provider feature in OpenShell
• Clear statement of why the change is important
• Clear statement of who will use it
• Security boundary analysis for credential handling
• Explanation of whether secrets remain hidden from the sandbox agent

Provider profiles are the authoritative provider model. Provider additions and updates must define their network policy, credentials, discovery, refresh metadata, and user-facing semantics through a built-in or imported profile. Treat any new or modified legacy ProviderDiscoverySpec entries as a blocking review finding unless a maintainer explicitly requests the legacy path. Do not ask contributors to update both systems for compatibility or to enable a gateway feature switch; profile-backed behavior is always active.

Be skeptical of changes that expose raw credentials to agents or weaken the credential proxy model, even if the user story is clear.

Large or Cross-Cutting Work

For larger changes that impact multiple subsystems, introduce major architecture changes, or touch high single-digit or double-digit file counts, require at least one:

• Fits an existing roadmap issue
• Directly follows an already validated issue or PR
• Has an accepted or actively reviewed RFC for the design
• Has explicit maintainer confirmation in the issue or PR thread

If this evidence is missing, use gator:follow-up-needed and ask for roadmap/RFC/linkage or maintainer clarification.

Follow-Up Triggers

Use gator:follow-up-needed when the submission:

• Does not meet validation criteria yet
• Lacks practical demonstration of why the author is submitting it
• Lacks reproduction steps for a bug
• Lacks a clear UX path for a user-facing feature
• Supports a narrow upstream project convenience without showing why OpenShell should own it
• Suggests swapping core OpenShell components for another project's technology without a strong OpenShell-specific reason
• Introduces CLI/API/UX changes that only work for one driver implementation
• Overlaps existing work and needs reconciliation with the linked issue/PR/RFC

When requesting follow-up, ask only for the minimal missing information needed to validate.

Invalid or Out of Scope

Close as not planned or wontfix when the submission is clearly outside OpenShell's scope, duplicates a resolved decision, weakens a project invariant without acceptable rationale, or remains unvalidated after the follow-up TTL.

Comment before closing and include a concise reason. Apply wontfix if appropriate and available.

Step 7: Follow-Up TTL

When applying gator:follow-up-needed, post a comment with:

• What information is missing
• Who needs to respond, usually the original submitter
• That the item may be closed if no author or maintainer response arrives within 48 business hours

Business hours are Monday th

…(truncated)