mirror of https://github.com/abhigyanpatwari/GitNexus.git synced 2026-08-28 05:25:25 +00:00

feat(ci): review agent runs as a coordinated reviewer swarm (#2572 )

* feat(ci): review agent on Sonnet 5 with structured, linked reviews

Bump the pinned review model from claude-sonnet-4-5-20250929 to
claude-sonnet-5 (verified against the pinned Claude Code 2.1.214 with
subscription auth and --json-schema structured output).

Restructure the published review body: verdict-first summary, findings
ordered by severity, fixed section order, and every file or symbol
reference as a GitHub permalink pinned to the analyzed head SHA (or the
merge-base SHA for deleted and rename-old paths) instead of bare
path:line text, so references are clickable and render inline previews.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* feat(ci): review agent runs as a coordinated reviewer swarm

Implement the review skill's expert-lens section in CI: the main agent
spawns four trusted lanes in parallel via the Task tool — correctness,
security, blast-radius, and coverage — each a purpose-built persona
restricted to Read/Glob/Grep plus the read-only graph MCP tools.

Personas live in the canonical skill tree (mirrored to all shipped
copies) and are installed into the reviewer's user-scope agents dir from
the exact control SHA, so a hostile PR head can never define a lane.
Lane reports are treated as unverified claims: the main agent re-anchors
findings before publishing, and the publisher's context-evidence gate
still requires the main conversation's own successful context call.
Bash and the newer Agent tool remain disallowed for every context; the
analyze timeout gets swarm headroom (45 -> 60 minutes). The workflow
contract test now pins the swarm posture.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* fix(ci): sidechain tool calls can no longer satisfy the evidence gate

The review agent's own review of this PR found that proveGraphReview()
walked the flat transcript without reading parent_tool_use_id, so a
spawned lane's context call could satisfy the publisher's graph-evidence
gate the prompt reserves for the orchestrator. Entries with a non-null
parent_tool_use_id are still strictly validated (malformed linkage fails
the transcript) but are excluded from both candidate context calls and
qualifying results; a new fixture proves sidechain-only evidence is
rejected while mainline evidence beside sidechain turns still passes.

Also gives the orchestrator turn headroom for the four dispatched lanes
(--max-turns 100 -> 150), addressing the review's LOW finding.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* refactor(skills): swarm-lane dispatch belongs to the review skill

Move the lane orchestration out of the workflow prompt and into the
gitnexus-review skill itself: a new "Swarm lanes" section names the four
ci-persona lanes, defines when and how to dispatch them (parallel, one
message, per-lane context and file slices), and owns the verification
contract (lane reports are unverified claims; re-anchor, dedup, drop
unanchored findings; lanes structure the work but never gate it). Any
runner of the skill — the CI workflow or a local harness — now triggers
the lanes from one canonical definition.

The workflow prompt keeps only its CI-specific deltas: the lanes'
trusted-control-SHA install provenance, the Task-tool dispatch surface,
and the publisher's orchestrator-only context-evidence gate. Mirrors
synced; 122 contract tests pass.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* feat(skills): add adversarial finder lane and critic gate to the swarm

ci-adversarial-lens joins the parallel finder wave: it assumes the change
is broken and constructs reachable failure scenarios — interleavings,
hostile inputs, state corruption, abuse of newly exposed surfaces — each
verified to a concrete entry point before it may be reported.

ci-critic-lens runs last as a gate on the orchestrator's finished draft:
it audits anchoring, concreteness, severity calibration, format
conformance, and honesty, returning PASS or a numbered defect list with
the smallest repair per item. The skill bounds it to two passes and the
critic hardens the review without ever blocking it; the workflow inherits
both lanes automatically through the wholesale ci-personas install.

Mirrors synced across all three shipped trees; 122 contract tests pass.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* refactor(ci): workflow defers the whole swarm contract to the skill

Now that the skill's Swarm lanes section owns dispatch, verification, the
critic gate, and the fallbacks, the workflow prompt stops restating any
of it. It contributes only what CI alone knows: the lanes' control-SHA
install provenance, the concrete environment mapping for lane inputs
(diff, manifest, head and merge-base checkouts, exact SHAs), and the one
CI override — the publisher's context-evidence gate remains
orchestrator-only. Analyze timeout gains headroom for the critic's
sequential rounds (60 -> 75 minutes).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* fix(ci): dispatch swarm lanes via the Agent tool, not the renamed Task alias

On the pinned Claude Code 2.1.214 the subagent-dispatch tool is `Agent`
(`Task` was renamed to `Agent` in 2.1.63 and is now a legacy alias), and
permission rules evaluate deny before allow. The workflow allowed `Task`
and denied `Agent`, so the orchestrator could never dispatch a lane and
every review silently fell back to the inline single-agent path while the
text-only tests certified the broken config.

Use `Agent` consistently: add it to --tools, allow it scoped to the six
ci-personas (`Agent(ci-correctness-lens,...,ci-critic-lens)`), remove it
from --disallowedTools, and update the prompt. Tests now match the scoped
allowlist on the raw string (commas inside Agent(...) break a split) and
assert Agent is no longer bare-denied.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* fix(ci): harden swarm permissions — allow Glob/Grep + merge-base reads, quarantine PR-head agents

Three permission-hygiene gaps around the swarm dispatch:
- Glob/Grep were in --tools but had no allow rule, so the lanes' declared
  tools could manufacture denied-tool errors; allow them (read-only,
  sandboxed by cwd + add-dir).
- The prompt hands lanes the merge-base source checkout for deleted /
  rename-old symbols, but no Read rule covered it; add a scoped Read()
  allow (which grants access without triggering --add-dir agent discovery).
- The --add-dir PR-head copy is scanned for spawnable agent definitions and
  the pinned runtime has no suppression env, so a PR could ship its own
  .claude/agents/*.md. Drop that subtree from the materialized copy after
  checkout-index (skills left intact), so only the trusted control-SHA
  personas can ever be dispatched.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* test(ci): pin the Agent allowlist to the ci-personas; require a dispatch canary

A text-only assertion cannot prove the pinned CLI actually dispatches the
lanes (print mode silently ignores invalid settings and does not validate
Agent(type) content at parse time) — that is what let the original
Task/Agent inversion pass CI. Two mitigations for the class:

- A cross-consistency test asserts the six names in the Agent(...) allowlist
  equal the six ci-personas filenames and each persona's frontmatter name,
  so a rename or typo in any of the three fails without auth.
- The activation checklist now requires the post-merge canary to prove a
  positive dispatch AND an unlisted-type refusal before enabling the trigger.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* fix(ci): bound swarm transcript volume with per-persona maxTurns

The six lanes stream into the single execution transcript the publisher
validates, but the personas carried no turn budget, so a large-PR swarm
run could overflow the (hard-throw) transcript caps and brick a valid
review. Bound each lane deterministically — finders maxTurns 12, the
critic maxTurns 6 — which keeps the worst case (~2×(150+5×12+2×6) ≈ 444
messages) under the unchanged 1_000 cap, so no cap needs raising. A new
test encodes that invariant: it fails if a persona's maxTurns is bumped
without revisiting the cap. Applied byte-identically across all four
shipped skill trees.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* test(ci): independently pin both sidechain evidence-gate guards

The sidechain-exclusion guards at candidate registration and result
acceptance were mutually redundant on realistic transcripts (a real
sidechain turn carries parent_tool_use_id on both its call and result),
so deleting either guard alone still passed the whole suite. Add two
asymmetric cross-wired fixtures — a mainline call with a sidechain result
(pins the acceptance guard) and a sidechain call with a mainline result
(pins the registration guard), both expecting missing_graph_evidence.
Mutation-verified: deleting either guard alone now reddens the suite.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* docs(skills): require own evidence before dispatch; document critic fail-open and swarm naming

Strengthen the gitnexus-review "Swarm lanes" contract (all four mirrors):
- The orchestrator must make its own graph context call on a changed
  symbol before dispatching any lane, so a fully-delegated run cannot
  leave the publisher's evidence gate unsatisfied (mirrored into the
  workflow prompt, with a test pinning the ordering phrase).
- Document that the critic's fail-open is deliberate (bounded to two
  passes, cannot deadlock, review still gated by evidence + schema),
  and distinguish it from the hard lane-7 gate in the separate
  gitnexus-pr-swarm-review skill.
- Give a concrete local-harness registration pointer for ci-personas.
- Add a reciprocal cross-reference in gitnexus-pr-swarm-review (single
  path — that skill is not part of the mirrored family).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* docs: record the review-agent swarm capability (AGENTS.md, CLAUDE.md, reviewer-swarm README)

Reflect the shipped swarm in the standing docs: bump AGENTS.md to 1.14.0
and CLAUDE.md to 1.8.0 with changelog rows, extend the gitnexus-review
description to mention the ci-personas swarm lanes, and refresh the
reviewer-swarm README so its differentiator names the real distinction
(interactive on-demand swarm vs the CI review agent's in-workflow lanes)
now that both run swarms. No CHANGELOG.md edit (feature-PR rule).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* fix(ci): close pre-push review findings on the swarm permission change

Adversarial review of the fix diff caught two issues introduced by the
permission-hygiene commit:
- Bare Glob/Grep in --allowedTools are separate tools that the Read()-scoped
  path denies (/proc, github.workspace, ...) do not cover, opening an
  undenied read path to the raw checkouts and host paths via a prompt-
  injected lane. Drop the bare allow — under dontAsk they stay denied by
  omission; lanes read via the scoped Read() rules and the graph MCP.
- The agents quarantine removed only the add-dir root's .claude/agents; make
  it recursive so a nested (e.g. monorepo subpackage) .claude/agents cannot
  survive and be discovered.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* feat(ci): post an "in progress" marker while the review swarm runs

Swarm reviews can take up to 75 minutes, and until now the PR showed no
sign a review was running. Add a dedicated write-scoped `acknowledge` job
that, under the same authorization gate as analyze, upserts a per-PR
"🔄 GitNexus review in progress" sticky comment linking to the live run
(and reacts 👀 to the trigger comment); the publisher removes that marker
when the review — or a clean failure — posts.

The marker lives in its own job so the model-facing analyze job stays
secretless and read-only: it cannot post to the PR, so per-lane live
progress isn't exposed there — the marker is a binary "running" state with
a link to the Actions run where lane-by-lane progress is visible.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

2026-07-20 07:31:40 +01:00

7 KiB

Raw Permalink Blame History

Last reviewed: 2026-07-16

Project: GitNexus · Environment: dev · Maintainer: repository maintainers (see GitHub)

Follow AGENTS.md for the canonical rules; this file adds Claude Code–specific deltas. Cursor-specific notes live only in AGENTS.md.

Scope

See the Scope table in AGENTS.md for read/write/execute/off-limits boundaries. Cursor-specific workflow notes also live only in AGENTS.md.

Model Configuration

Primary: Pin per Claude Code / Anthropic org policy (explicit model id). Do not rely on an unversioned latest alias for governed workflows.
Fallback: As configured in Claude Code (organization default or user override).
Notes: The GitNexus CLI analyzer does not call an LLM.

Execution Sequence (complex tasks)

Same discipline as AGENTS.md: before large multi-step work, state which AGENTS.md / GUARDRAILS.md rules apply, current Scope, and planned validation commands (npm test, tsc, etc.). When pausing, summarize progress in the chat or a local scratch file (do not add HANDOFF.md to the repo), then /clear and resume with that summary.

Claude Code hooks

Prefer PreToolUse hooks for hard gates (e.g. tests before git_commit). Adapt hook commands to gitnexus/ npm scripts.

Context budget

If always-on instructions grow, load deep conventions via conditional reads (e.g. “When writing new code, read STANDARDS.md”) instead of pasting long blocks here. In Cursor, prefer .cursor/index.mdc plus optional .cursor/rules/*.mdc globs (see AGENTS.md § Context budget).

Reference Documentation

This repository: AGENTS.md (Cursor + monorepo notes), ARCHITECTURE.md, CONTRIBUTING.md, GUARDRAILS.md.
Call & inheritance resolution: See ARCHITECTURE.md § Scope-Resolution Pipeline. Shared pipeline code in gitnexus/src/core/ingestion/ must not name languages — use LanguageProvider / ScopeResolver hooks instead (see AGENTS.md). (The legacy call-resolution DAG was removed in #942.)
GitNexus: standard skills in .claude/skills/gitnexus-*/; MCP and indexed-repo rules live only in AGENTS.md (gitnexus:start … gitnexus:end). See GitNexus rules below.
Engineering plans, execution & review: /gitnexus-plan <task> (implementation-ready plans via GitNexus + statement-level PDG + source verification; Deepen mode for existing plans), /gitnexus-work [plan] (executes a plan as impact-checked, detect_changes-gated atomic commits), /gitnexus-review [PR|branch|range|local] (read-only graph-backed review), /gitnexus-lfg <task> (plan with depth asked up front → proceed/stop gate → work → review pipeline). Specs in .claude/skills/gitnexus-{plan,work,review,lfg}/SKILL.md (see AGENTS.md § Engineering planning & execution).

Changelog

Date	Version	Change
2026-07-20	1.8.0	The CI review agent runs `gitnexus-review` as a coordinated swarm — six `ci-personas/` lanes dispatched via the `Agent` tool with a bounded critic gate.
2026-07-16	1.7.0	`/gitnexus-plan` asks depth up front in interactive runs; `/gitnexus-lfg` gate slimmed to proceed/stop.
2026-07-16	1.6.0	Renamed `/gitnexus-pr-review` to `/gitnexus-review` and added PR, branch/range, and local-change targets.
2026-07-11	1.5.0	Added `/gitnexus-work` and `/gitnexus-lfg` to the engineering plans & execution pointer.
2026-07-11	1.4.0	Added `/gitnexus-plan` pointer to Reference Documentation.
2026-04-13	1.3.0	Updated GitNexus index stats after DAG refactor.
2026-03-24	1.2.0	Removed duplicated gitnexus:start block and scope table; replaced with pointers to AGENTS.md.
2026-03-23	1.1.0	Updated agent instructions to match AGENTS.md.
2026-03-22	1.0.0	Added structured header and changelog.

GitNexus rules

See the  …  block in AGENTS.md for the canonical MCP tools, impact analysis rules, and index instructions.

GitNexus — Code Intelligence

This project is indexed by GitNexus as GitNexus (20319 symbols, 54304 relationships, 300 execution flows). Use the GitNexus MCP tools to understand code, assess impact, and navigate safely.

Index stale? Run node .gitnexus/run.cjs analyze from the project root — it auto-selects an available runner. No .gitnexus/run.cjs yet? npx gitnexus analyze (npm 11 crash → npm i -g gitnexus; #1939).

Always Do

MUST run impact analysis before editing any symbol. Before modifying a function, class, or method, run impact({target: "symbolName", direction: "upstream"}) and report the blast radius (direct callers, affected processes, risk level) to the user.
MUST run detect_changes() before committing to verify your changes only affect expected symbols and execution flows. For regression review, compare against the default branch: detect_changes({scope: "compare", base_ref: "main"}).
MUST warn the user if impact analysis returns HIGH or CRITICAL risk before proceeding with edits.
When exploring unfamiliar code, use query({search_query: "concept"}) to find execution flows instead of grepping. It returns process-grouped results ranked by relevance.
When you need full context on a specific symbol — callers, callees, which execution flows it participates in — use context({name: "symbolName"}).
For security review, explain({target: "fileOrSymbol"}) lists taint findings (source→sink flows; needs analyze --pdg).

Never Do

NEVER edit a function, class, or method without first running impact on it.
NEVER ignore HIGH or CRITICAL risk warnings from impact analysis.
NEVER rename symbols with find-and-replace — use rename which understands the call graph.
NEVER commit changes without running detect_changes() to check affected scope.

Resources

Resource	Use for
`gitnexus://repo/GitNexus/context`	Codebase overview, check index freshness
`gitnexus://repo/GitNexus/clusters`	All functional areas
`gitnexus://repo/GitNexus/processes`	All execution flows
`gitnexus://repo/GitNexus/process/{name}`	Step-by-step execution trace

CLI

Task	Read this skill file
Understand architecture / "How does X work?"	`.claude/skills/gitnexus-exploring/SKILL.md`
Blast radius / "What breaks if I change X?"	`.claude/skills/gitnexus-impact-analysis/SKILL.md`
Trace bugs / "Why is X failing?"	`.claude/skills/gitnexus-debugging/SKILL.md`
Rename / extract / split / refactor	`.claude/skills/gitnexus-refactoring/SKILL.md`
Tools, resources, schema reference	`.claude/skills/gitnexus-guide/SKILL.md`
Index, status, clean, wiki CLI commands	`.claude/skills/gitnexus-cli/SKILL.md`

7 KiB Raw Permalink Blame History Unescape Escape