---
# =============================================================================
# The dispatcher's configuration. Everything here is NON-SECRET and reviewable in a diff;
# the two credentials live in pm-agent-credentials.sops.yaml and are referenced by name only
# (R-IDP-04).
#
# WHAT IS *NOT* HERE, on purpose:
#   * the PM persona — baked into the image at /etc/pm-agent/pm-persona.md. It is the
#     agent's standing instruction set, and a ConfigMap is `kubectl edit`-able by anyone with
#     namespace write. Changing how the PM behaves should be a reviewed commit and an image
#     rebuild, not a live edit. (PM_PERSONA_FILE below can point elsewhere, which is the
#     escape hatch for someone deliberately experimenting.)
#   * the worker Job template — likewise baked in, and for a stronger reason: the template IS
#     the shape the admission policy and the dispatcher's RBAC jointly bound. See the header
#     of infra/agent/worker-job-template.yaml.
#
# NO SHELL-STYLE EXPANSIONS BELOW — AND THAT RULE APPLIES TO THESE COMMENTS TOO.
# This namespace's Flux Kustomization substitutes from cluster-vars, and envsubst runs over
# the WHOLE rendered manifest, comment lines included. So an unescaped dollar-brace token
# anywhere in this file — even in prose explaining the rule — is either replaced with the
# empty string or, if it is not a valid name, fails the ENTIRE Kustomization. This paragraph
# used to contain two such tokens as examples and the gate refused the change for it
# (ci/l0.sh, flux-postbuild-substitution: 1 UNDEFINED + 1 FATAL-PARSE), which is the check
# working exactly as intended. Every value below is a literal, including the Gitea URL — see
# the comment on it. The escaping contract itself: catalog/README.md.
# =============================================================================
apiVersion: v1
kind: ConfigMap
metadata:
  name: pm-agent-config
  namespace: pm-agent
  labels:
    app.kubernetes.io/name: pm-agent
    app.kubernetes.io/part-of: pm-agent
data:
  # --- where the work comes from ---------------------------------------------
  # THE IN-CLUSTER SERVICE ADDRESS, NOT THE PUBLIC HOSTNAME, and for the same reason prod's
  # own Flux source uses it (clusters/prod/kustomization.yaml): this path depends on neither
  # public DNS, nor Cloudflare, nor the shared Gateway, nor the BASE_DOMAIN knob. A change of
  # domain, a certificate problem or a Gateway outage cannot sever the agent from the
  # repository it works on. It is also why the egress policy can be a pod-identity rule rather than a
  # `world` allow, and why pm-worker's baked-in host allowlist can be two entries long.
  PM_GITEA_URL: "http://gitea.gitea.svc.cluster.local:3000"
  PM_GITEA_OWNER: "Home-Network"
  PM_GITEA_REPO: "home-network-k3s-impl"
  PM_BASE_BRANCH: "main"
  PM_NAMESPACE: "pm-agent"

  # --- what runs the work ----------------------------------------------------
  # THE WORKER IMAGE, DIGEST-PINNED. This must be the SAME digest the Deployment runs, since
  # the dispatcher and its workers share the committed Job template and the env-name
  # contract. A tag here is refused at startup (and would be DENIED by admission anyway).
  #
  # PLACEHOLDER UNTIL THE IMAGE IS PUBLISHED. The all-zero digest below is deliberately
  # impossible: `infra/agent/build-image.sh` builds and verifies the image, the OPERATOR
  # pushes it, and the authoritative digest from `--digestfile` replaces this value in a
  # reviewed pull request (the same two-step the conformance-runner image follows, and for
  # the same reason: a registry credential is not an agent's to hold). Until then the
  # dispatcher starts, fails to pull, and says so — which is the visible failure, not a
  # silent one.
  PM_WORKER_IMAGE: "gitea.home.keithjackson.dev/home-network/agent-runner@sha256:0000000000000000000000000000000000000000000000000000000000000000"

  # --- the model -------------------------------------------------------------
  # The PM only reads a thread and answers with one JSON object, so it holds no tools and
  # takes one turn. The worker does real repository work against a gate. Both run on the
  # most capable general model on purpose: the failure mode that matters here is a plausible
  # change that is subtly wrong, which is exactly what a cheaper tier buys more of.
  PM_MODEL: "claude-opus-5"
  PM_WORKER_MODEL: "claude-opus-5"

  # --- pace and blast radius -------------------------------------------------
  # These five numbers are the throttle. They exist because the first minute after the
  # credentials are filled in is the dangerous one: every open issue is new to the agent at
  # once.
  #
  # PM_POLL_INTERVAL_SECONDS  how long an issue may wait before the PM looks at it.
  # PM_MAX_ACTIVE_WORKERS     concurrent worker Jobs. RAM is the binding constraint on this
  #                           3-node cluster and each worker's limit is 2Gi, so 2 is 4Gi
  #                           worst case. It is also a subscription-rate-limit throttle:
  #                           several Claude Code sessions on one subscription seat contend
  #                           for the same account limits.
  # PM_MAX_NEW_WORKERS_PER_CYCLE  at most one NEW assignment per poll, so a backlog is
  #                           drained one issue at a time rather than in one stampede.
  # PM_ISSUE_COOLDOWN_SECONDS how often one issue may cost a decision. The dispatcher stamps
  #                           this BEFORE it asks the model, so a decision that then fails
  #                           cannot be retried on every poll.
  # PM_WORKER_MAX_BUDGET_USD  per-assignment spend ceiling the CLI enforces itself. It is
  #                           Claude Code's own client-side estimate rather than a bill, so
  #                           treat it as a runaway-loop stop, not as accounting.
  PM_POLL_INTERVAL_SECONDS: "60"
  PM_MAX_ACTIVE_WORKERS: "2"
  PM_MAX_NEW_WORKERS_PER_CYCLE: "1"
  PM_ISSUE_COOLDOWN_SECONDS: "900"
  PM_WORKER_MAX_TURNS: "80"
  PM_WORKER_MAX_BUDGET_USD: "10"

  # --- scope -----------------------------------------------------------------
  # EMPTY MEANS EVERY OPEN ISSUE, which is the behaviour this service was asked for: it
  # reacts to issue creation and to comments, on all of them.
  #
  # RECOMMENDED FOR THE FIRST WEEKS, and a one-word change: set this to `agent`, and the
  # dispatcher considers only issues a human has labelled `agent`. That bounds the agent to
  # work somebody deliberately handed it while trust is being established, with no code
  # change and no redeploy of anything but this ConfigMap. The operator's call; the default
  # here honours the request as made.
  PM_REQUIRE_LABEL: ""

  # Dry run: the PM still reads threads, still asks the model and still posts its decision as
  # an issue comment — so the operator can read exactly what it WOULD have done — but creates
  # no worker Job and so changes no code. The honest way to watch this service for a day
  # before letting it write anything.
  PM_DRY_RUN: "false"

  # If the gate refuses a worker's change, the branch is NOT pushed by default and the issue
  # gets the gate log instead. Set to "true" to push anyway and open a red pull request —
  # useful when a human wants to see the work, noisy as a standing setting.
  PM_PUSH_ON_RED_GATE: "false"