fix(parallel-issues): enforce the cap for every agent role

[thewrz]

This was written agentically; verify its assertions:

Why

The parallel workflow limited issue-lead waves but left assessor, waiter, and other fan-outs outside its stated cap.

What

Apply the limit to every agent role, require a prospective total before each fan-out, and reject counts above the lower of the runtime cap and ten. Bound thin-Ready vetting by the same available slots.

Decisions

Count root and all live roles together. Overflow diagnostics preserve the supplied count and role, including integers too large for shell arithmetic. Existing size limits remain unchanged. Structured verification remains unknown because repository configuration cannot produce the installed validator’s required cache; native full verification passed.

Reject empty assertion flags, stop when cap advertisement fails, and advertise the effective runtime/workflow minimum. The root recovered the final pushed result after the worker provider failed during handback.

Diff size facts:
base=origin/main
files=5
total.insertions=125
total.deletions=41
total.lines=166
operational.files=5
operational.insertions=125
operational.deletions=41
operational.lines=166
generated.files=0
generated.insertions=0
generated.deletions=0
generated.lines=0
lockfile.files=0
lockfile.insertions=0
lockfile.deletions=0
lockfile.lines=0
fixture.files=0
fixture.insertions=0
fixture.deletions=0
fixture.lines=0
non_operational.files=0
non_operational.insertions=0
non_operational.deletions=0
non_operational.lines=0

Testing

• Issue and accepted-review regressions pass.
• Fresh full declared test suite passed: 20260918T085808Z-test.log, rc=0.
• Root cross-write collection and pushed-diff review pass.
• Current-head CI passed all four observed checks.

🤖 Co-authored by Codex / gpt-5.6-sol.

Closes #832

[coderabbitai]

Important

Review skipped

Auto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Team

Run ID: 8a802182-c2c5-4b2f-a453-630ad3ec8099

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

---

_{Comment @coderabbitai help to get the list of available commands.}

[thewrz]

This was written agentically; verify its assertions:

Adversarial review receipt

• Reviewer: provider=anthropic; model=claude-opus-5; effort=xhigh; mode=cross-provider (reason: n/a)
• Launcher: adversarial-run.sh sha256=4d1fc623db1b387d5d6dc0792b56ea5fcc25bf1297a77b9aca4dab243902bd50; attempt=e02517b6-ba48-41c0-8210-2e929ea6472d
• Procedure: one-shot diff review; no contract-blind or two-pass attestation
• Counts: P1=0; P2=3; total=3
• Reviewed head: 06b72eb
• Diff payload: wrzonance/agent-kit:837:164ff379a2aeed82079f7ea2505558ded9621fbe544bd5ac81dec10022c70d65
• Confirmed finding: Reject explicitly empty assertion arguments — verdict=fixed; fix commit SHA(s)=f0632f52ea9b39abb177fca2aaf300512861c77e
• Confirmed finding: Stop when runtime concurrency cannot be advertised — verdict=fixed; fix commit SHA(s)=f0632f52ea9b39abb177fca2aaf300512861c77e
• Confirmed finding: Advertise the effective concurrency limit — verdict=fixed; fix commit SHA(s)=f0632f52ea9b39abb177fca2aaf300512861c77e
• Execution: performed; adjudication=recorded
• Remediation: complete

🤖 Co-authored by Codex / GPT-6.

[thewrz]

This was written agentically; verify its assertions:

Review ledger

Machine-readable record of every review already performed on this PR.

{
  "version": 1,
  "pr": 837,
  "repo": "wrzonance/agent-kit",
  "reviews": [
    {
      "kind": "adversarial",
      "provider": "anthropic",
      "model": "claude-opus-5",
      "effort": "xhigh",
      "mode": "cross-provider",
      "attemptId": "e02517b6-ba48-41c0-8210-2e929ea6472d",
      "launcherSha256": "4d1fc623db1b387d5d6dc0792b56ea5fcc25bf1297a77b9aca4dab243902bd50",
      "procedure": "one-shot diff review; no contract-blind or two-pass attestation",
      "reviewerOverride": "",
      "harness": "codex",
      "head_sha": "06b72eb6eebf7eccdb0f1f7a21f913e03bcf7176",
      "covered_heads": [
        "06b72eb6eebf7eccdb0f1f7a21f913e03bcf7176",
        "1e5fca2939c8d16d602162f83879fb5a7b578e78",
        "220610ef762db84cdd98f2c882fb4e2db14a7b5c",
        "f0632f52ea9b39abb177fca2aaf300512861c77e"
      ],
      "diff_payload": "wrzonance/agent-kit:837:164ff379a2aeed82079f7ea2505558ded9621fbe544bd5ac81dec10022c70d65",
      "findings": [
        {
          "title": "Reject explicitly empty assertion arguments",
          "severity": "P2",
          "verdict": "fixed",
          "sha": "f0632f52ea9b39abb177fca2aaf300512861c77e",
          "schemaVersion": 2,
          "evidence": {
            "finding": "Reject explicitly empty assertion arguments",
            "repairSha": "f0632f52ea9b39abb177fca2aaf300512861c77e",
            "head": "1e5fca2939c8d16d602162f83879fb5a7b578e78",
            "path": "agentkit/skills/parallel-issues/scripts/concurrency-cap.sh",
            "command": "tests/run-tests.sh",
            "status": "passed",
            "log": "/home/adam/github/agent-kit/.worktrees/feat/issue-832/.agent/logs/20260919T014434Z-test.log",
            "logSha256": "b213c42464338667b875bcb814c69a41176f89d2a1568876fd89957838c2584d"
          },
          "history": [
            {
              "title": "Reject explicitly empty assertion arguments",
              "severity": "P2",
              "verdict": "open",
              "rationale": "Track whether assertion flags were supplied and reject empty values; test both empty and missing partner arguments.",
              "schemaVersion": 2
            }
          ]
        },
        {
          "title": "Stop when runtime concurrency cannot be advertised",
          "severity": "P2",
          "verdict": "fixed",
          "sha": "f0632f52ea9b39abb177fca2aaf300512861c77e",
          "schemaVersion": 2,
          "evidence": {
            "finding": "Stop when runtime concurrency cannot be advertised",
            "repairSha": "f0632f52ea9b39abb177fca2aaf300512861c77e",
            "head": "1e5fca2939c8d16d602162f83879fb5a7b578e78",
            "path": "agentkit/skills/parallel-issues/SKILL.md",
            "command": "tests/run-tests.sh",
            "status": "passed",
            "log": "/home/adam/github/agent-kit/.worktrees/feat/issue-832/.agent/logs/20260919T014434Z-test.log",
            "logSha256": "b213c42464338667b875bcb814c69a41176f89d2a1568876fd89957838c2584d"
          },
          "history": [
            {
              "title": "Stop when runtime concurrency cannot be advertised",
              "severity": "P2",
              "verdict": "open",
              "rationale": "Restore terminal stop/report behavior for config or capability errors; distinguish it from capacity refusal.",
              "schemaVersion": 2
            }
          ]
        },
        {
          "title": "Advertise the effective concurrency limit",
          "severity": "P2",
          "verdict": "fixed",
          "sha": "f0632f52ea9b39abb177fca2aaf300512861c77e",
          "schemaVersion": 2,
          "evidence": {
            "finding": "Advertise the effective concurrency limit",
            "repairSha": "f0632f52ea9b39abb177fca2aaf300512861c77e",
            "head": "1e5fca2939c8d16d602162f83879fb5a7b578e78",
            "path": "agentkit/skills/parallel-issues/scripts/concurrency-cap.sh",
            "command": "tests/run-tests.sh",
            "status": "passed",
            "log": "/home/adam/github/agent-kit/.worktrees/feat/issue-832/.agent/logs/20260919T014434Z-test.log",
            "logSha256": "b213c42464338667b875bcb814c69a41176f89d2a1568876fd89957838c2584d"
          },
          "history": [
            {
              "title": "Advertise the effective concurrency limit",
              "severity": "P2",
              "verdict": "open",
              "rationale": "Return the effective min(runtime,10) to callers so PR-loop formulas agree with enforcement; test a runtime above10.",
              "schemaVersion": 2
            }
          ]
        }
      ],
      "counts": {
        "p1": 0,
        "p2": 3
      },
      "reviewed_at": "2026-09-18T09:48:05Z",
      "coverage": [
        {
          "sha": "220610ef762db84cdd98f2c882fb4e2db14a7b5c",
          "reason": "merge-down:2a21b3f9eb77c2993201b6522fa3bdd18390e01d",
          "covered_at": "2026-09-19T01:37:08Z"
        },
        {
          "sha": "1e5fca2939c8d16d602162f83879fb5a7b578e78",
          "reason": "merge-down:09989b1738845d41d737cbb342d0b5bfaffd7498",
          "covered_at": "2026-09-19T01:49:35Z"
        }
      ]
    }
  ]
}

🤖 Co-authored by Codex.