home-network-k3s-impl/platform/pm-agent/README.md

# pm-agent — an AI Program Manager that turns Gitea issues into pull requests

A service that runs in the cluster, reads the issues of
`Home-Network/home-network-k3s-impl`, decides what to do about each thread **as the Program
Manager persona this repository already works under**, and runs one worker agent per
assignment that authors the change, runs the merge gate and opens a pull request.

It reacts to issue creation and to comments on issues. Every assignment and every piece of
correspondence travels through the issue thread and the pull request, so the whole record of
what the agent did, and why, is in the same place a human is already looking.

It **never pushes to `main`** and **never merges a pull request**. The merge gate remains the
approver, and a sensitive-path change still needs the human review `ci/approval-policy.sh`
requires.

| | |
|---|---|
| Design, alternatives considered, threat model | [`docs/plans/pm-agent-issue-to-pr.md`](../../docs/plans/pm-agent-issue-to-pr.md) |
| Operator runbook — stopping it, reading its logs, rotating its tokens | [`runbooks/pm-agent.md`](../../runbooks/pm-agent.md) |
| The image, the two entrypoints, the PM persona | [`infra/agent/`](../../infra/agent/) |
| The security boundary | [`platform/kyverno/admission/pm-agent-job-shape.yaml`](../kyverno/admission/pm-agent-job-shape.yaml) |

---

## It does nothing at all until an operator does two things

Both are deliberate, and both fail **visibly** rather than silently:

1. **The image does not exist.** `platform/pm-agent/deployment.yaml` and
   `PM_WORKER_IMAGE` in `configmap.yaml` carry an all-zero digest placeholder. Build it with
   `infra/agent/build-image.sh` (which verifies it and refuses to push), push it as the
   operator, then update **both** places with the digest `podman push --digestfile` returned,
   in one pull request. Until then: `ImagePullBackOff`.

   **Two things have to be true before any digest will pull, and neither is declared in this
   repository.** Both were measured after PR #57 merged — this service is the first workload
   in the cluster ever to reference the in-cluster registry, so nothing had exercised the
   path. Details and the exact commands:
   [`decisions/2026-10-05-pm-agent-registry-pull-prereq.md`](../../decisions/2026-10-05-pm-agent-registry-pull-prereq.md).

   - **The nodes must be able to verify the registry's TLS certificate.** containerd
     currently fails with `x509: certificate is not valid for any names, but wanted to match
     gitea.home.keithjackson.dev`, while the same name from the LAN serves a healthy
     Let's Encrypt `*.home.keithjackson.dev`. Correcting the digest will not clear this.
   - **The pull must be authenticated.** An unauthenticated client gets nothing from this
     Gitea's registry (its anonymous token carries no access scope; every path 401s), and
     there is no `imagePullSecret` anywhere in the tree. Either add one — a
     `dockerconfigjson`, SOPS-encrypted like `pm-agent-credentials`, referenced from the
     Deployment *and* from the committed worker Job template — or allow anonymous reads of
     that package in Gitea, which makes the image readable to anything that can reach the
     host. That is a posture decision, so it is yours rather than an agent's.

   The same two apply to `conformance-runner`: same registry path, same push-then-pin model,
   never pulled either.
2. **The credentials are placeholders.** `pm-agent-credentials.sops.yaml` is encrypted to the
   repository's age recipient but holds `REPLACE-ME-…` strings. The hand-off —
   which Gitea account to create, which scopes, and why it must *not* be an administrator —
   is in [`pm-agent-credentials.sops.yaml.example`](./pm-agent-credentials.sops.yaml.example).
   Until then the dispatcher CrashLoops with `GET /user returned no login — is GITEA_TOKEN
   valid?`.

Its Flux Kustomization is `wait: false` precisely because of those two states: a workload
that is *expected* to be unhealthy for a while must never be able to gate anything.

---

## How it works

```
                   ┌──────────────────────── pm-agent namespace ─────────────────────────┐
                   │                                                                     │
  Gitea issue  ───▶│  pm-dispatch (1 replica, Recreate)                                  │
  (poll, 60s)      │    1. list open issues                                              │
                   │    2. act iff the NEWEST thing in the thread is not mine            │
                   │    3. ask the model, under the PM persona, with NO tools             │
                   │       → {action, branch, brief, comment}                            │
                   │    4. validate it, then: create the Job, then post the comment      │
                   │                        │                                            │
                   │                        ▼                                            │
                   │  pm-worker (one Job per assignment, no SA token, read-only rootfs)   │
                   │    clone → branch → read the live thread → Claude Code session →     │
                   │    ./ci/gate.sh → commit → push → open the PR → comment on the issue│
                   └─────────────────────────────────────────────────────────────────────┘
          egress: gitea:3000 · kube-apiserver (dispatcher only) · tcp/443 · DNS.  ingress: none.
```

**There is no database and no PVC.** The trigger is a question asked of the issue thread
itself — *act iff the newest thing in this thread was not written by me* — and since the PM
always answers in the thread, acting makes the thread quiet again until a human (or a worker)
says something else. The Gitea thread **is** the state. It survives restarts with no recovery
path to get wrong, it is readable by the operator in the place they already look, and it
creates no R-STATE-03 obligation for irreplaceable state.

**It polls; it does not receive webhooks.** Gitea's webhook SSRF guard
(`[webhook] ALLOWED_HOST_LIST`) does not by default permit calling a private in-cluster
address, a missed delivery is simply lost, and a receiver would need inbound reach into a
namespace whose entire purpose is running model-authored code. The cost is up to 60s of
latency. The full argument is in the header of
[`infra/agent/pm-dispatch.py`](../../infra/agent/pm-dispatch.py).

**The PM holds no tools.** It runs `claude --print --tools ""` against a JSON schema: text
in, one JSON object out, no Bash, no file access, no network of its own. The dispatcher then
validates every field — the action against a fixed set, the branch against `CLAUDE.md` §4's
pattern, `revise` against the branch that actually carries the issue's work — and builds the
Job from a committed template. **The model's output is data, never a command.**

---

## What the worker can and cannot do

| | |
|---|---|
| **can** | change any file in its own clone; run any command in the container; run the gate; read the issue thread and the pull requests |
| **can** | push **one** branch (the one the PM named, validated twice against `^(feat\|fix\|docs\|chore)/…`) and open/update its pull request |
| **can** | post comments on its own issue |
| **cannot** | push to `main` — refused by `pm-worker` before anything runs, and by branch protection regardless |
| **cannot** | merge anything — the gate is the approver, and the service makes no merge call |
| **cannot** | reach the Kubernetes API: no ServiceAccount token is mounted, the `pm-agent-worker` identity is bound to nothing, and the egress policy does not include the API server. `kubectl` is on its `PATH` (the gate's toolchain needs it) and is inert |
| **cannot** | reach anything except this Gitea and tcp/443 — no package registry, no GitHub |
| **cannot** | clone from or push to anywhere but `gitea.gitea.svc.cluster.local:3000`: `pm-worker` validates `PM_GITEA_URL` against a one-entry allowlist baked into the image. In-cluster consumers reach a service by its cluster-local name — a different path by design from how a client outside the cluster reaches it — so the external hostname is not an accepted value |
| **cannot** | authenticate a `git push` **during the model session**: `GIT_ASKPASS` is unset for its duration, so the restriction is structural rather than a request in a prompt |
| **cannot** | be created in any shape but the committed one — see the admission policy |

### What is *not* defended, stated plainly

- **The worker's own credentials are inside the model's reach.** The session runs as the same
  uid in the same container as the wrapper, so it can read the environment, including its
  `GITEA_TOKEN` and `CLAUDE_CODE_OAUTH_TOKEN`. There is no isolation between them and none is
  claimed. What bounds it: the Gitea token is scoped `write:repository, write:issue` on **one
  repository** with no admin permission, and egress reaches only this Gitea and tcp/443.
- **`world:443` is wider than `api.anthropic.com`.** Cilium can express the tighter rule
  (`toFQDNs`) but nothing in this repository uses FQDN policy and its prerequisite (Cilium's
  DNS proxy) has not been measured here. Narrowing it is a tracked follow-up with that
  measurement as its first step, not a one-line edit.
- **A `write` collaborator in Gitea can merge a pull request.** No token scope separates
  "push a branch and open a PR" from "merge it". The service issues no merge call — that is
  all of `pm-worker`'s API calls, readable in one file — but it is a property of the code, not
  of the credential. What the non-admin permission *does* buy structurally is that the bot
  **cannot** post `/approve-override`, so a sensitive-path pull request from the agent
  correctly sits unmergeable until a human reviews it.
- **The PM cannot see the repository.** It triages from the thread alone, so its brief is a
  belief about where the work lives, not a verified fact — which is why the persona requires
  it to say so, and why the worker is told to investigate before changing anything.
- **Nothing here has run.** Everything in this directory is authored and gate-checked
  offline. No part of this service has been built, pushed, deployed or observed; see the
  handoff entry's "What I did NOT verify".

---

## The escalation this service is built around

Kubernetes places **no `use` check** on a Pod's `serviceAccountName`. So "may create Jobs in
namespace X" is equivalent to "may run arbitrary code as the most privileged identity in
namespace X" — no matter how narrow the creator's own Role looks. The dispatcher creates
Jobs. That is the whole problem, and this repository has met it before
(`conformance/incluster/rbac.yaml`).

Two things answer it, and neither is sufficient alone:

1. **There is nothing to escalate to.** `pm-agent-worker` is bound to no Role at all, and the
   Job template mounts no token. The prize is empty.
2. **The shape is constrained at the API server.**
   `platform/kyverno/admission/pm-agent-job-shape.yaml` is `Enforce` + `failurePolicy: Fail`
   and admits only: the digest-pinned `agent-runner` image, exactly one container, the pinned
   `command` with no args, that powerless SA, no mounted token, `restartPolicy: Never`,
   non-root with no privilege escalation and a read-only root filesystem, only the
   `workspace`/`tmp` **emptyDir** volumes, no init or ephemeral containers, only the
   committed env **names**, and no `envFrom`.

Six rules, because pinning `command` only moves the injection to whatever adjacent field
nobody enumerated — on the sibling policy that was `initContainers` (measured: a Job with a
compliant `containers[0]` and a privileged init container was **admitted**, pass 3 fail 0),
then `ephemeralContainers`, then `env`, then `envFrom`. All of them are closed here from the
start, and `platform/kyverno/tests/pm-agent/` proves each refusal offline: **28 assertions,
28 passing** under the pinned `kyverno` CLI. The worker's own input guards have their own
offline probe — `infra/agent/probe-validation.sh`, **17 refusals** — because a guard nothing
exercises is a claim rather than a control.

> The policy is applied by `platform-config/kustomization.yaml`, and it has to be: adding a
> ClusterPolicy only to `platform/kyverno/admission/kustomization.yaml` is a **silent
> no-op**. That is exactly how the conformance boundary shipped green and never reached the
> cluster on 2026-09-29.

---

## Operating it

Every knob is in [`configmap.yaml`](./configmap.yaml), with the reasoning next to it. The
five that matter:

| knob | default | what it is for |
|---|---|---|
| `PM_REQUIRE_LABEL` | `""` (every open issue) | set it to `agent` and only issues a human has labelled are in scope. **Recommended for the first weeks** — it bounds the agent to work somebody deliberately handed it, with no code change |
| `PM_DRY_RUN` | `false` | still triages and still posts what it would have done; creates no worker. The honest way to watch it for a day |
| `PM_MAX_ACTIVE_WORKERS` | `2` | concurrent workers. RAM is the binding constraint (2Gi limit each) and the subscription seat's rate limits are shared with every other use of that seat |
| `PM_MAX_NEW_WORKERS_PER_CYCLE` | `1` | drains a backlog one issue at a time instead of in one stampede the first minute the credentials work |
| `PM_PUSH_ON_RED_GATE` | `false` | a change the gate refused is not pushed; the issue gets the gate log instead |

Changing a knob requires bumping the `config-generation` annotation in `deployment.yaml` in
the same commit — the process reads its configuration once, at startup, so without the bump
the ConfigMap changes and nothing does. (Same class of defect as the inert merged
`cilium-config`: `decisions/2026-10-05-cilium-roll-out-on-config-change.md`.)

**To stop it**, in increasing severity: `PM_DRY_RUN`, scale to zero, suspend the
Kustomization, or revoke the Gitea token. Step-by-step in
[`runbooks/pm-agent.md`](../../runbooks/pm-agent.md).