recipe-maintainers/cc-ci-orchestrator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
34cbb60f35cbb07f6953df41e485aa20ec159623
cc-ci-orchestrator/cc-ci-plan
History
autonomic-bot 34cbb60f35 plan §4.1/§1.5: polling primary + read-only CI; webhook is optional manual-admin 
Finalize trigger model per operator: polling is the primary trigger (outbound, read-only,
no admin); the server never self-registers webhooks (that needs admin) — webhook is an
optional push optimization an admin registers manually, documented in enroll-recipe.md.
Commenter auth via org-membership endpoint (read-level), not the admin-only permission
endpoint. Bot's required privilege is read + comment + org-membership, never repo-admin.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-27 02:37:17 +01:00
..
prompts
Initial commit: cc-ci autonomous orchestrator
2026-05-26 20:46:28 +01:00
brief.md
Initial commit: cc-ci autonomous orchestrator
2026-05-26 20:46:28 +01:00
kickoff.md
Initial commit: cc-ci autonomous orchestrator
2026-05-26 20:46:28 +01:00
launch.sh
Initial commit: cc-ci autonomous orchestrator
2026-05-26 20:46:28 +01:00
plan.md
plan §4.1/§1.5: polling primary + read-only CI; webhook is optional manual-admin
2026-05-27 02:37:17 +01:00
README.md
Initial commit: cc-ci autonomous orchestrator
2026-05-26 20:46:28 +01:00

README.md

cc-ci-plan

Self-contained handoff package for building the cc-ci Co-op Cloud recipe CI server with two autonomous Claude loops (a Builder and an adversarial Reviewer) running over days.

Start here

  1. Read plan.md — the full plan and single source of truth (mission, Definition of Done, architecture, milestones, the two-agent coordination protocol, loop discipline).
  2. Read kickoff.md — how to launch and supervise the loops.
  3. Run ./launch.sh start to bring up both loops + the watchdog.

Files

File Purpose
plan.md The plan. Agents treat it as their single source of truth.
brief.md The original one-page brief (context only; plan.md supersedes it).
kickoff.md Launch & supervision guide.
launch.sh Starts both loops + a watchdog; restarts dead loops; stops on ## DONE.
prompts/builder.md Builder loop prompt (fed to claude by the script).
prompts/adversary.md Adversary loop prompt.

Before launching

  • Set the org in plan.md (git.autonomic.zone/recipe-maintainers/cc-ci) and lock the six proof recipes (§8).
  • Ensure the launching shell has: SSH+sudo to cc-ci, the Gitea token, git.autonomic.zone access.
  • Preconfigure test-app DNS + TLS (plan §4.0): point a wildcard *.ci.commoninternet.net record at a gateway that TLS-passthroughs to cc-ci, and pre-issue the wildcard cert (*.ci.commoninternet.net + ci.commoninternet.net, via Gandi DNS-01) into /var/lib/ci-certs/live/ on cc-ci. The agent handles everything else on cc-ci (Traefik file provider → that cert, swarm, routing) and does no ACME; renewal (~90 days) is an out-of-band operator task, so the DNS token never goes to the agent.
  • export CC_CI_REPO=https://git.autonomic.zone/recipe-maintainers/cc-ci.git so the watchdog can detect ## DONE.

What "done" means

The loops stop only when all of plan.md §2 (D1–D10) hold and the Adversary has independently re-verified each within 24h. The watchdog then tears the loops down automatically.