[codex] Document terminal bench dispatch config (#4961)

## Thinking Path

> - Paperclip agents rely on skills for repeatable operating procedures
> - The Terminal-Bench loop skill needs to preserve enough dispatch
configuration to reproduce real heartbeat behavior
> - A bare benchmark command can create unassigned work with no
heartbeat-enabled agent, which is a harness setup failure rather than
product evidence
> - The Paperclip heartbeat skill also needs to keep escalation biased
toward agent-owned follow-through
> - This pull request documents dispatch runner config requirements and
strengthens the agent follow-through rule
> - The benefit is fewer misleading benchmark loops and clearer agent
operating guidance

## What Changed

- Documented `PAPERCLIP_HARBOR_RUNNER_CONFIG` / runner dispatch config
as required Terminal-Bench loop input.
- Updated the Terminal-Bench loop smoke check to require the dispatch
config mention.
- Added stronger Paperclip skill guidance to avoid asking humans for
work an agent can perform.

## Verification

- `pnpm smoke:terminal-bench-loop-skill`

## Risks

- Low risk: documentation and smoke expectation changes only. The
stricter smoke assertion is intentional so future edits do not drop the
dispatch config requirement.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

- OpenAI Codex, GPT-5 coding agent, tool use and local command
execution. Exact context window was not exposed in the runtime.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>

scripts/smoke/terminal-bench-loop-skill-smoke.mjs

@@ -91,6 +91,7 @@ async function assertLocalSkillPackage() {
     "diagnosis",
     "blockedByIssueIds",
     "PAPERCLIPAI_CMD",
+    "PAPERCLIP_HARBOR_RUNNER_CONFIG",
   ]) {
     assert(markdown.includes(expected), `Skill smoke expected ${skillPath} to mention ${expected}`);
   }
@@ -194,6 +195,8 @@ async function main() {
         `- Manifest: ${artifactRoot}/manifest.json`,
         `- Results JSONL: ${artifactRoot}/results.jsonl`,
         `- Harbor raw job folder: ${artifactRoot}/harbor/raw-job`,
+        "- Dispatch config: PAPERCLIP_HARBOR_RUNNER_CONFIG=<omitted - harness/setup no-dispatch smoke>",
+        "- Heartbeat-enabled agents: 0 (harness/setup no-dispatch; not a product signal)",
         "",
         "No benchmark process, Harbor job, model call, or provider call was started.",
       ].join("\n"),
@@ -309,6 +312,7 @@ async function main() {
     `Expected iteration issue to be in_review, got ${verifiedIteration.status}`,
   );
   assert(verifiedRunDoc.body.includes(`${artifactRoot}/results.jsonl`), "Expected run doc to include mocked results path");
+  assert(verifiedRunDoc.body.includes("PAPERCLIP_HARBOR_RUNNER_CONFIG"), "Expected run doc to record dispatch config");
   assert(
     verifiedDiagnosisDoc.body.includes("Exact stop point") && verifiedDiagnosisDoc.body.includes("Next-action owner"),
     "Expected diagnosis doc to include exact stop point and next-action owner",