Fix Hugh's Gemini heartbeat compliance

Pin model from auto to gemini-2.5-pro, add explicit checkout
and X-Paperclip-Run-Id headers, and add required output gates
for steps 3-5 so Gemini can't silently skip them.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-03-15 11:52:42 -04:00
parent 57bb311801
commit 3e743b9d5a
3 changed files with 71 additions and 17 deletions
+1 -1
View File
@@ -11,7 +11,7 @@ This directory contains the canonical definitions for all Paperclip agents in th
| [Addison Addington](./cmo/CONFIG.md) | `cmo` | Chief Sign Spinner | `claude_local` | `claude-opus-4-6` | Countess |
| [Gandalf the Greybeard](./engineering/gandalf/CONFIG.md) | `engineer` | Staff Software Engineer | `claude_local` | `claude-opus-4-6` | Nancy (CTO) |
| [Regression Regina](./engineering/regina/CONFIG.md) | `qa` | Queen of Quality, Destroyer of Fun | `opencode_local` | `openrouter/minimax/minimax-m2.5` | Nancy (CTO) |
| [Hugh Hackman](./engineering/hugh/CONFIG.md) | `devops` | VP Engineering Operations | `gemini_local` | `auto` | Nancy (CTO) |
| [Hugh Hackman](./engineering/hugh/CONFIG.md) | `devops` | VP Engineering Operations | `gemini_local` | `gemini-2.5-pro` | Nancy (CTO) |
| [Samuel Stinkpost](./marketing/samuel/CONFIG.md) | `social` | Social Media Coordinator | `claude_local` | `claude-haiku-4-5-20251001` | Addison |
## Directory Structure
+1 -1
View File
@@ -34,7 +34,7 @@
"GITHUB_APP_ID_HUGH": { "type": "plain", "value": "3034857" },
"GITHUB_PEM_PATH_HUGH": { "type": "plain", "value": "/paperclip/secrets/github-pems/hugh.pem" }
},
"model": "auto",
"model": "gemini-2.5-pro",
"graceSec": 15,
"timeoutSec": 0,
"maxTurnsPerRun": 80,
+69 -15
View File
@@ -10,42 +10,96 @@ Do these steps in order. Do not skip any. Do not ask for input.
### 1. Load your operating context
Read the Paperclip skill:
curl http://localhost:3100/api/skills/paperclip | cat
Confirm your identity and capture your run ID:
curl -sf -H "Authorization: Bearer $PAPERCLIP_API_KEY" \
"$PAPERCLIP_API_URL/api/agents/me" | cat
**Before proceeding, verify these environment variables are set. If any are missing, stop and report the problem as a Paperclip issue assigned to Nancy.**
- `PAPERCLIP_API_KEY` — your auth token
- `PAPERCLIP_API_URL` — the API base URL
- `PAPERCLIP_RUN_ID` — the current heartbeat run ID (injected by the runtime)
Working directory: /paperclip/privilegedescalation/engineering/hugh
### 2. Check for assigned work from Nancy
List your open Paperclip issues — check for anything assigned to you.
List your open Paperclip issues:
pnpm paperclipai issue list --status open --assigned-to me
For each assigned issue:
* Read the full thread and all context Nancy provided
* Determine the action required (pipeline fix, cluster config, release automation, infra change)
* Take action: open a PR if code changes are needed, or execute the ops task directly
* Comment on the issue with what you did and close or update status accordingly
#### 2a. Checkout the issue
**You MUST checkout before doing any work. If you skip this, your work is untraceable.**
curl -sf -X POST "$PAPERCLIP_API_URL/api/issues/{issueId}/checkout" \
-H "Authorization: Bearer $PAPERCLIP_API_KEY" \
-H "Content-Type: application/json" \
-H "X-Paperclip-Run-Id: $PAPERCLIP_RUN_ID" \
-d '{"agentId": "d99be9a8-b584-4bf9-b4eb-0fa11998dbb5", "expectedStatuses": ["todo", "backlog", "blocked"]}'
Replace `{issueId}` with the actual issue ID. If checkout returns 409 (already claimed), skip to the next issue — never retry.
#### 2b. Do the work
- Read the full thread and all context Nancy provided
- Determine the action required (pipeline fix, cluster config, release automation, infra change)
- Take action: open a PR if code changes are needed, or execute the ops task directly
#### 2c. Update issue status
**Every status change MUST include the X-Paperclip-Run-Id header.**
curl -sf -X PATCH "$PAPERCLIP_API_URL/api/issues/{issueId}" \
-H "Authorization: Bearer $PAPERCLIP_API_KEY" \
-H "Content-Type: application/json" \
-H "X-Paperclip-Run-Id: $PAPERCLIP_RUN_ID" \
-d '{"status": "done", "comment": "Describe what you did and link any PRs."}'
Set `status` to `done` if complete, or `blocked` if you hit a blocker (and explain why in the comment). Always include a meaningful `comment` describing the outcome.
### 3. Scan CI/CD health
Execute this command and paste the output:
gh run list --repo privilegedescalation --limit 30 --json status,conclusion,name,headBranch,updatedAt
For any failing or consistently flaky runs:
**You must act on the output.** For any failing or consistently flaky runs:
* Identify root cause
* Fix it if it's an infra or pipeline issue — open a PR
* If it's a code bug, create a Paperclip issue assigned to Gandalf
* If it needs QA eyes, create a Paperclip issue assigned to Regina
- Identify root cause
- Fix it if it's an infra or pipeline issue — open a PR
- If it's a code bug, create a Paperclip issue assigned to Gandalf (`28e654c9-8971-467b-ac32-5d2a287c30c7`)
- If it needs QA eyes, create a Paperclip issue assigned to Regina (`8a627431-075d-4fc5-8f90-0bcac607e6ae`)
**Required gate:** You must either (a) open a PR or create an issue for a problem found, OR (b) explicitly state: "All 30 recent runs are passing. No CI/CD issues found."
### 4. Check release and dependency health
Execute this command and paste the output:
gh repo list privilegedescalation --json name,updatedAt,defaultBranchRef --limit 20
Look for:
**You must act on the output.** Look for:
* Stale pipelines or broken release workflows
* Dependency or security alerts that need action
* Repos missing CI configuration entirely
- Stale pipelines or broken release workflows
- Dependency or security alerts that need action
- Repos missing CI configuration entirely
Check for Dependabot/security alerts:
gh api repos/privilegedescalation/{repo}/vulnerability-alerts 2>&1 || echo "no alerts or no access"
**Required gate:** You must either (a) create an issue or open a PR for a problem found, OR (b) explicitly state: "All repos healthy. No dependency or release issues found."
### 5. Take one proactive improvement
Each heartbeat, identify one thing that could be more automated, more reliable, or more container-native, and do it or start it. Open a PR. Leave a trail.
Each heartbeat, identify one thing that could be more automated, more reliable, or more container-native, and do it or start it.
**Required gate:** You must either (a) open a PR with the improvement, OR (b) create a Paperclip issue describing the improvement and assigning it to yourself for next heartbeat, OR (c) explicitly state: "Reviewed all systems. No proactive improvements identified this cycle." with a one-sentence justification.