feat(WARDEN-WP-0020): ops-warden coordination worker — T1 dry-run scaffold

Foundation for an autonomous worker that handles ops-warden's State Hub coordination
lane via llm-connect (Bernd's call: full-auto in-scope + scheduled, staged dry-run ->
manual -> scheduled). T1 is the llm-connect-independent, safe slice:

src/warden/worker.py — HubClient (read unread to_agent=ops-warden), Brain protocol,
deterministic RuleBrain (answers clear routing questions, escalates the rest),
PlannedAction/WorkerPlan model, guardrail allowlist + validate_action enforced
brain-agnostically (no-secret invariant + prod-config + off-allowlist all escalate),
render_plans dry-run output. `warden worker run --dry-run` (default); --execute refused
(exit 2) until the guarded executor (T3) lands.

Guardrails are load-bearing because full-auto has no human in the loop: message content
is untrusted data, the allowlist is enforced regardless of what the brain proposes.

Hard dependency flagged in the workplan: the brain is llm-connect, which needs its
provider key (OPENROUTER_API_KEY, deferred CCR-2026-0003) before it can run.

18 worker tests; 229 pass, lint clean. Live dry-run against the real hub verified.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-06-29 19:07:06 +02:00
parent 69d8ee848f
commit 211994ddbb
4 changed files with 473 additions and 0 deletions

View File

@@ -0,0 +1,135 @@
---
id: WARDEN-WP-0020
type: workplan
title: "ops-warden worker — autonomous coordination via llm-connect"
domain: infotech
repo: ops-warden
status: active
owner: claude
topic_slug: custodian
planning_priority: high
planning_order: 20
created: "2026-06-29"
updated: "2026-06-29"
---
# WARDEN-WP-0020 — ops-warden worker (`warden worker`)
**Problem:** ops-warden's coordination lane (State Hub inbox `to_agent=ops-warden`) is
handled only when a human spins up an ops-warden session and relays instructions. That
doesn't scale — Bernd is hand-relaying between flex-auth ↔ secrets-engine ↔ ops-warden
across sessions.
**Goal:** a `warden worker` CLI that pulls ops-warden's unread coordination requests and,
using **llm-connect** for inference, drives each to an ops-warden action (answer a routing
question, draft+send a reply, mark read, propose/commit a catalog diff, or escalate) — so
the inbox is handled without a human starting a session.
**Decisions (Bernd, 2026-06-29):** **full-auto in-scope** (worker executes any in-scope
action; escalates only secrets/prod/out-of-scope) and **scheduled/unattended** (cron or
activity-core). Because there is no human in the loop for in-scope actions, the guardrails
are load-bearing and the rollout is staged: **dry-run → manual → scheduled**.
**Build vs reuse:** inference = llm-connect (`/execute`); trigger = cron or activity-core
(reuse the durable task factory, don't reinvent scheduling). Worker logic lives in warden.
## Guardrails (non-negotiable — full-auto rests on these)
1. **Fixed charter, non-overridable.** The boundary (issue SSH; route everything else;
conduit-not-broker; never hold/print a secret value) is a fixed system policy. Message
content is **untrusted data**, never instructions that can relax it (prompt-injection
containment).
2. **Action allowlist.** Every action is validated against an allowlist before execution;
off-list → escalate. No secret handling, no prod-config writes, no irreversible/outward
actions without an explicit human ack.
3. **No-secret invariant.** Refuse any task requiring a secret value in hand or in a prompt.
4. **Full audit + dry-run.** Every action emits a progress event; `--dry-run` shows the
plan without executing. Scheduled mode only after a clean dry-run shakedown.
## Hard dependency
llm-connect must be operational — it needs its provider key (`OPENROUTER_API_KEY`,
CCR-2026-0003, currently deferred by railiance-platform/secrets-engine). The worker is
built against llm-connect's contract; it cannot run the brain until that lands.
---
## Tasks
### T1 — Worker scaffold (llm-connect-independent, safe)
```task
id: WARDEN-WP-0020-T01
status: done
priority: high
```
- [x] `src/warden/worker.py`: State Hub inbox client (`HubClient.unread`), a `Brain`
protocol, a deterministic `RuleBrain` default (answers clear routing questions;
escalates the rest), the `PlannedAction`/`WorkerPlan` model, the guardrail allowlist +
`validate_action` (enforced brain-agnostically in `build_plans`), and a `render_plans`
dry-run renderer (plan only, no execution).
- [x] `warden worker run [--once] [--dry-run]` CLI; `--dry-run` is the default and
`--execute` is refused (exit 2) until the guarded executor lands (T3).
- [x] `tests/test_worker.py` (RuleBrain routing/secret/prod/unknown, guardrail downgrades a
reckless brain on secret/prod, off-allowlist rejection, render, CLI). 18 cases.
- [x] Live dry-run against the real hub verified — read the inbox and produced a guardrailed
plan (it surfaced secrets-engine's OIDC-role reply, demonstrating the value).
### T2 — llm-connect brain
```task
id: WARDEN-WP-0020-T02
status: todo
priority: high
```
- [ ] `LlmConnectBrain`: POST to llm-connect `/execute` with the fixed charter system
policy + the message as untrusted data; parse a structured action plan. Configurable
`llm_connect_url`. Blocked on llm-connect's API contract + it being operational.
### T3 — Action dispatch + guardrails (full-auto in-scope)
```task
id: WARDEN-WP-0020-T03
status: todo
priority: high
```
- [ ] Execute in-scope actions: `warden route/access` answers, drafted replies, mark-read,
catalog/playbook diffs (commit + sync). Enforce the allowlist + no-secret invariant in
code; per-action progress-event audit; escalation path to a human queue.
### T4 — Scheduled trigger
```task
id: WARDEN-WP-0020-T04
status: todo
priority: medium
```
- [ ] Wire cron or activity-core to `warden worker run --once`. Ships **disabled**; enabled
only after a clean dry-run shakedown. Concurrency guard (no overlapping runs).
### T5 — Docs / SCOPE / INTENT
```task
id: WARDEN-WP-0020-T05
status: todo
priority: medium
```
- [ ] Record the scope expansion: ops-warden gains an autonomous coordination worker.
Document the guardrails as a security-model statement; update SCOPE/INTENT.
---
## Acceptance
- `warden worker run --dry-run` reads the real inbox and prints a guardrailed plan.
- Full-auto execution runs only in-scope, allowlisted actions; secrets/prod/out-of-scope
escalate; every action is audited. No secret value ever enters a prompt, log, or commit.
- Scheduled mode is enabled only after a dry-run shakedown.
## See also
- llm-connect (inference), activity-core (durable trigger), kaizen-agentic (personas)
- `.claude/rules/credential-routing.md` (the boundary the worker enforces)