binky-control/integrations/railiance-llm-rhythm.md
tegwick 6e6da53c5d
All checks were successful
Work Records / validate (push) Successful in 13s
BINKY-WP-0006: wire mail-triage path and mark T01–T04 done
Document live llm-connect smoke + host port-forward; ensure git identity
and LLM_CONNECT_URL defaults for railiance timers.
2026-07-22 00:07:46 +02:00

4.8 KiB

Railiance rhythm via llm-connect (not a host coding agent)

Status: design note 2026-07-21 (BINKY-WP-0006).
Supersedes the residual “install Claude on railiance01” idea from the BINKY-WP-0004 cutover notes.

Principle

Railiance executes infrastructure + hosted LLM inference. It does not host Claude Code, Codex, or another interactive coding harness.

Layer On Railiance Not on Railiance
Secrets OpenBao AppRole / in-cluster Secret Paste into chat
Deterministic I/O email-connect scan, git commit/push with deploy key
LLM llm-connect → OpenRouter (open-weights / cheap models) Claude CLI agentic session
Policy Allow-listed apply steps (Blue/Green) Model free-form shell

This matches agent-harness INTENT (session policy shell) and llm-connect INTENT (provider abstraction): the server profile uses llm-connect HTTP; laptop coding agents remain optional for interactive work only.

Mail path (canonical)

timer / CronJob
  → agent-harness mail-scan          # deterministic, AppRole IMAP
  → agent-harness mail-triage        # NEW: llm-connect JSON + apply
  → hub progress + local commit

Phase 1 — scan (exists, proven)

  • Module: agent_harness/mailscan.py
  • Creds: tenants/binky/company-email/imap via AppRole
  • Output: mailmeta/reports/email-channel-evidence-report-*.csv
  • Hub: binky_mail_intake with counts only

Phase 2 — triage (to build)

  1. Prompt (metadata only): newest CSV rows + current mail-log tail + queue templates.
  2. llm-connect POST (same contract as activity-core llm_client.py):
    • URL: http://llm-connect.activity-core.svc.cluster.local:8080
    • Provider: OpenRouter (already configured on railiance)
    • Model: cost-efficient; prefer open-weights (pick at T03; examples to evaluate: Llama/Qwen/Mistral class on OpenRouter — measure quality on fixture CSV before locking).
  3. Response: strict JSON, e.g.
{
  "log_entries": [
    {"date": "2026-07-21", "from": "…", "subject": "…", "action": "ignore|queue|suspicious"}
  ],
  "queue_items": [],
  "notes": "one-line summary"
}
  1. Apply (deterministic Python): append mail-log; add queue YAML only if schema-valid; suspicious → log only; git commit; hub event.
  2. Never pass message bodies to the model if the scanner can omit them; never execute model-suggested shell.

Daily / weekly (same shape)

Slot Deterministic inputs LLM output Apply
Daily brief queues, open risks, yesterday brief structured sections write briefs/YYYY-MM-DD-daily-brief.md + commit
Weekly review briefs week, SuccessMilestones structured prep write weekly prep file + commit

No tool-using coding agent required if apply is code-owned.

What already runs on railiance01

Component Status (2026-07-22)
llm-connect Deployment in activity-core Running; OpenRouter; model google/gemini-2.5-flash
OpenRouter API key Secret Present (operator custody)
agent-harness mail-scan on host Proven
agent-harness mail-triage Implemented (agent-harness 7520a53); live smoke OK via port-forward
Host systemd timers Interim cadence; call mail-scan + mail-triage
Claude CLI on host Must not become a dependency

Host reachability to llm-connect

In-cluster DNS does not resolve on the bare host. Interim:

kubectl -n activity-core port-forward svc/llm-connect 18080:8080 &
export LLM_CONNECT_URL=http://127.0.0.1:18080
export STATE_HUB_URL=http://127.0.0.1:18000
agent-harness mail-triage --target-repo ~/binky-control

Prefer a CronJob in-cluster later (native DNS to llm-connect.activity-core.svc).

Git identity on the host checkout (required once):

git -C ~/binky-control config user.email agent-harness@railiance.local
git -C ~/binky-control config user.name agent-harness

Anti-patterns

  • Installing Claude Code / npm agent stacks on railiance for rhythm.
  • Defaulting runner.run_task to AgenticClaudeCodeAdapter for server Jobs.
  • Sending full email bodies or secrets to OpenRouter.
  • Dual “coding agent policy” vs “server policy” that drifts (same JSON schema and apply code for all environments).

Implementation homes

Work Repo
HTTP adapter + mail-triage command + tests agent-harness
Model/profile ConfigMap, smoke llm-connect / activity-core overlay
Timers, binky task prompts, dogfood binky-control (this doc + BINKY-WP-0006)

See also

  • integrations/executor-cutover-runbook.md — cutover status
  • workplans/BINKY-WP-0006-… — tasks
  • llm-connect docs/activity-core-llm-endpoint.md
  • agent-harness mailscan.py two-phase header comment